Dale Schuurmans' on-line papers

Papers available on-line

(More recent papers can be found on Google Scholar or DBLP.)

J Mei, B Dai, A Agarwal, M Ghavamzadeh, C Szepesvari, D Schuurmans (2023) Ordering based conditions for global convergence of policy gradient methods. In Advances in Neural Information Processing Systems (NeurIPS-23). neurips23a.pdf
Y Du, M Yang, B Dai, O Nachum, J Tennenbaum, D Schuurmans, P Abbeel (2023) Learning universal policies via text guided video generation. In Advances in Neural Information Processing Systems (NeurIPS-23). neurips23b.pdf
Z Zhang, J Kirschner, J Zhang, F Zanini, A Ayoub, M Dehghan, D Schuurmans (2023) Managing temporal resolution in continuous value estimation: A fundamental trade-off. In Advances in Neural Information Processing Systems (NeurIPS-23). neurips23c.pdf
K Goshvadi, H Sun, X Liu, A Nova, R Zhang, W Grathwohl, D Schuurmans, H Dai (2023) DISCS: A benchmark for discrete sampling. In Advances in Neural Information Processing Systems (NeurIPS-23) Datasets, Benchmarks Track. neurips23d.pdf
C Muslimani, A Lewandowski, D Schuurmans, M Taylor, Luo, J. (2023) Reinforcement teaching. In Transactions on Machine Learning Research. tmlr23.pdf
T Zhang, T Ren, C Xiao, W Xiao, J Gonzalez, D Schuurmans, B Dai (2023) Energy-based predictive representations for partially observed reinforcement learning. In Conference on Uncertainty in Artificial Intelligence (UAI-2023). uai23.pdf
A Nova, H Dai, D Schuurmans (2023) Gradient-free structured pruning with unlabeled data. In International Conference on Machine Learning (ICML-23). icml23a.pdf
J Mei, Z Zhong, B Dai, A Agarwal, C Szepesvari, D Schuurmans (2023) Stochastic gradient succeeds for bandits. In International Conference on Machine Learning (ICML-23). icml23b.pdf
H Sun, K Goshvadi, A Nova, D Schuurmans, H Dai (2023) Revisiting sampling for combinatorial optimization. In International Conference on Machine Learning (ICML-23). icml23c.pdf
H Sun, H Dai, B Dai, H Zhou, D Schuurmans (2023) Discrete Langevin samplers via Wasserstein gradient flow. In International Conference on Artificial Intelligence and Statistics (AISTATS-23). aistats23a.pdf
H Dai, Y Xue, Y Wang, N Li, D Schuurmans, B Dai (2023) Learning to optimize with stochastic dominance constraints. In International Conference on Artificial Intelligence and Statistics (AISTATS-23). aistats23b.pdf
D Schuurmans (2023) Memory augmented large language models are computationally universal. arXiv 2301.04589.pdf
D Zhou, N Schaerli, L Hou, J Wei, N Scales, X Wang, D Schuurmans, O Bousquet, Q Le, E Chi (2023) Least-to-most prompting enables complex reasoning in large language models. In International Conference on Learning Representations (ICLR-23). iclr23a.pdf
X Wang, J Wei, D Schuurmans, Q Le, E Chi, S Narang, A Chowdhery, D Zhou (2023) Self-consistency improves chain of thought reasoning in language models. In International Conference on Learning Representations (ICLR-23). iclr23b.pdf
T Ren, T Zhang, L Lee, J Gonzalez, D Schuurmans, B Dai (2023) Spectral decomposition representation for reinforcement learning. In International Conference on Learning Representations (ICLR-23). iclr23c.pdf
E Akyurek, D Schuurmans, J Andreas, T Ma, D Zhou (2023) What learning algorithm is in-context learning? Investigations with linear models. In International Conference on Learning Representations (ICLR-23). iclr23d.pdf
T Zhang, X Wang, D Zhou, D Schuurmans, J Gonzalez (2023) TEMPERA: Test-time prompt editing via reinforcement learning. In International Conference on Learning Representations (ICLR-23). iclr23e.pdf
M Yang, D Schuurmans, P Abbeel, O Nachum (2023) Dichotomy of control: Separating what you can control from what you cannot. In International Conference on Learning Representations (ICLR-23). iclr23f.pdf
T Ren, C Xiao, T Zhang, N Li, Z Wang, S Sanghavi, D Schuurmans, B Dai (2023) Latent variable representation for reinforcement learning. In International Conference on Learning Representations (ICLR-23). iclr23g.pdf
H Sun, B Dai, C Sutton, D Schuurmans, H Dai (2023) Any-scale balanced samplers for discrete spaces. In International Conference on Learning Representations (ICLR-23). iclr23h.pdf
H Sun, L Yu, B Dai, D Schuurmans, H Dai (2023) Score-based continuous-time discrete diffusion models. In International Conference on Learning Representations (ICLR-23). iclr23i.pdf
J Wei, X Wang, D Schuurmans, M Bosma, B Ichter, F Xia, E Chi, Q Le, D Zhou (2022) Chain of thought prompting elicits reasoning in large language models. In Advances in Neural Information Processing Systems (NeurIPS-22). neurips22a.pdf
M Yang, D Schuurmans, P Abbeel, O Nachum (2022) Chain of thought imitation with procedure cloning. In Advances in Neural Information Processing Systems (NeurIPS-22). neurips22b.pdf
J Mei, W Chung, V Thomas, B Dai, C Szepesvari, D Schuurmans (2022) The role of baselines in policy gradient optimization. In Advances in Neural Information Processing Systems (NeurIPS-22). neurips22c.pdf
H Sun, H Dai, D Schuurmans (2022) Optimal scaling for locally balanced proposals in discrete spaces. In Advances in Neural Information Processing Systems (NeurIPS-22). neurips22d.pdf
R Zhang, J Mei, B Dai, D Schuurmans, N Li (2022) On the global convergence rates of decentralized softmax gradient play in Markov potential games In Advances in Neural Information Processing Systems (NeurIPS-22). neurips22e.pdf
H Ren, H Dai, B Dai, X Chen, D Zhou, J Leskovec, D Schuurmans (2022) SMORE: Knowledge graph completion and multi-hop reasoning in massive knowledge graphs. In SIGKDD Conference on Knowledge Discovery and Data Mining (KDD-2022). kdd22.pdf
R Gummadi, J Wen, S Kumar, D Schuurmans (2022) Unifying approximate gradient updates for policy optimization. In International Conference on Machine Learning (ICML-22). icml22a.pdf
T Zhang, T Ren, M Yang, J Gonzalez, D Schuurmans, B Dai (2022) Making linear MDPs practical via contrastive representation learning. In International Conference on Machine Learning (ICML-22). icml22b.pdf
H Dai M Yang, Xue, Y, D Schuurmans, B Dai (2022) Marginal distribution adaptation for discrete sets via module-oriented divergence minimization. In International Conference on Machine Learning (ICML-22). icml22c.pdf
C Xiao, B Dai, J Mei, O Ramirez, R Gummadi, C Harris, D Schuurmans (2022) Understanding and leveraging overparameterization in recursive value estimation. In International Conference on Learning Representations (ICLR-22). iclr22a.pdf
H Dai, Y Xue, Z Syed, D Schuurmans, B Dai (2022) Neural stochastic dual dynamic programming. International Conference on Learning Representations (ICLR-22). iclr22b.pdf
M Yang, B Dai, O Nachum, G Tucker, D Schuurmans (2022) Offline policy selection under uncertainty. In International Conference on Artificial Intelligence and Statistics (AISTATS-22). aistats22a.pdf
C Xiao, I Lee, B Dai, D Schuurmans, C Szepesvari (2022) The curse of passive data collection in batch reinforcement learning. In International Conference on Artificial Intelligence and Statistics (AISTATS-22). aistats22b.pdf
H Ren, H Dai, B Dai, X Chen, M Yasunaga, H Sun, D Schuurmans, J Leskovec, D Zhou (2021) LEGO: Latent execution-guided reasoning for multi-hop question answering on knowledge graphs. In International Conference on Machine Learning (ICML-21). icml21a.pdf
J Wen, S Kumar, R Gummadi, D Schuurmans (2021) Characterizing the gap between actor-critic and policy gradient. In International Conference on Machine Learning (ICML-21). icml21b.pdf
J Mei, Y Gao, B Dai, C Szepesvari, D Schuurmans (2021) Leveraging non-uniformity in first-order non-convex optimization. In International Conference on Machine Learning (ICML-21). icml21c.pdf
C Xiao, Y Wu, J Mei, B Dai, T Lattimore, L Li, C Szepesvari, D Schuurmans (2021) On the optimality of batch policy optimization algorithms. In International Conference on Machine Learning (ICML-21). icml21d.pdf
K Ghasemipour, S Gu, D Schuurmans (2021) EMaQ: Expected-max Q-learning operator for simple yet effective offline and online RL. In International Conference on Machine Learning (ICML-21). icml21e.pdf
M Karami, D Schuurmans (2021) Deep probabilistic canonical correlation analysis. In AAAI Conference on Artificial Intelligence (AAAI-21). aaai21.pdf
J Mei, C Xiao, B Dai, L Li, C Szepesvari, D Schuurmans (2020) Escaping the gravitational pull of softmax. In Advances in Neural Information Processing Systems (NeurIPS-20). neurips20a.pdf
B Dai, O Nachum, Y Chow, L Li, C Szepesvari, D Schuurmans (2020) CoinDICE: Off-policy confidence interval estimation. In Advances in Neural Information Processing Systems (NeurIPS-20). neurips20b.pdf
N Lazic, D Yin, M Farajtabar, N Levine, D Gorur, C Harris, D Schuurmans (2020) A maximum-entropy approach to off-policy evaluation in average reward MDPs. In Advances in Neural Information Processing Systems (NeurIPS-20). neurips20c.pdf
H Dai, R Singh, B Dai, C Sutton, D Schuurmans (2020) Learning discrete energy-based models via auxiliary-variable local exploration. In Advances in Neural Information Processing Systems (NeurIPS-20). neurips20d.pdf
M Yang, O Nachum, B Dai, L Li, D Schuurmans (2020) Off-policy evaluation via the regularized Lagrangian. In Advances in Neural Information Processing Systems (NeurIPS-20). neurips20e.pdf
J Mei, C Xiao, C Szepesvari, D Schuurmans (2020) On the global convergence rates of softmax policy gradient methods. In International Conference on Machine Learning (ICML-20). icml20a.pdf
J Wen, B Dai, L Li, D Schuurmans (2020) Batch stationary distribution estimation. In International Conference on Machine Learning (ICML-20). icml20b.pdf
M Yang, B Dai, H Dai, D Schuurmans (2020) Energy-based processes for exchangeable data. In International Conference on Machine Learning (ICML-20). icml20c.pdf
H Dai, A Nazi, Y Li, B Dai, D Schuurmans (2020) Scalable deep generative modeling for sparse graphs. In International Conference on Machine Learning (ICML-20). icml20d.pdf
R Agarwal, D Schuurmans, M Norouzi (2020) An optimistic perspective on offline deep reinforcement learning. In International Conference on Machine Learning (ICML-20). icml20e.pdf
D Su, J Ooi, T Lu, D Schuurmans, C Boutilier (2020) ConQUR: Mitigating delusional bias in deep Q-learning. In International Conference on Machine Learning (ICML-20). icml20f.pdf
J Wen, R Greiner, D Schuurmans (2020) Domain aggregation networks for multi-source domain adaptation. In International Conference on Machine Learning (ICML-20). icml20g.pdf
D Zhou, M Ye, C Chen, T Meng, M Tan, X Song, Q Le, Q Liu, D Schuurmans (2020) Go wide, then narrow: Efficient training of deep thin networks. In International Conference on Machine Learning (ICML-20). icml20h.pdf
R Zhang, B Dai, L Li, D Schuurmans (2020) GenDICE: generalized offline estimation of stationary values. In International Conference on Learning Representations (ICLR-20). iclr20.pdf
M Karami, D Schuurmans, J Sohl-Dickstein, L Dinh, D Duckworth (2019) Invertible convolutional flow. In Advances in Neural Information Processing Systems (NeurIPS-19). neurips19a.pdf
M Bellemare, W Dabney, R Dadashi, A Ali Taiga, P Castro, N Le Roux, D Schuurmans (2019) A geometric perspective on optimal representations for reinforcement learning. In Advances in Neural Information Processing Systems (NeurIPS-19). neurips19b.pdf
B Dai, Z Liu, H Dai, N He, A Gretton, L Song, D Schuurmans (2019) Exponential family estimation via adversarial dynamics embedding. In Advances in Neural Information Processing Systems (NeurIPS-19). neurips19c.pdf
M Chen, R Gummadi, C Harris, D Schuurmans (2019) Surrogate objectives for batch policy optimization in one-step decision making. In Advances in Neural Information Processing Systems (NeurIPS-19). neurips19d.pdf
C Xiao, R Huang, J Mei, D Schuurmans (2019) Maximum entropy Monte-Carlo planning. In Advances in Neural Information Processing Systems (NeurIPS-19). neurips19e.pdf
R Dadashi, A Ali Taiga, N Le Roux, D Schuurmans, M Bellemare (2019) The value function polytope in reinforcement learning. In International Conference on Machine Learning (ICML-19). icml19a.pdf
R Agarwal, C Liang, M Norouzi, D Schuurmans (2019) Learning to generalize from sparse and underspecified rewards. In International Conference on Machine Learning (ICML-19). icml19b.pdf
Z Ahmed, N Le Roux, M Norouzi, D Schuurmans (2019) Understanding the role of entropy on policy optimization. In International Conference on Machine Learning (ICML-19). icml19c.pdf
C Xiao, J Mei, R Huang, M Meuller, D Schuurmans (2019) On principled exploration in policy optimization. In International Joint Conference on Artificial Intelligence (IJCAI-19). ijcai19a.pdf
M Mladenov, O Meshi, J Ooi, C Boutilier, D Schuurmans (2019) Advantage amplification in slowly evolving latent-state environments. In International Joint Conference on Artificial Intelligence (IJCAI-19). ijcai19b.pdf
B Dai, H Dai, N He, L Song, A Gretton, D Schuurmans (2019) Kernel exponential family estimation via doubly dual embedding. In International Conference on Artificial Intelligence and Statistics (AISTATS-19). aistats19.pdf
T Lu, C Boutilier, D Schuurmans (2018) Overcoming delusional bias in value-based planning and reinforcement learning. In Advances in Neural Information Processing Systems (NeurIPS-18). neurips18.pdf
M Elgendi, P Bobhate, S Jain, L Guo, J Rutledge, Y Coe, R Zemp, D Schuurmans, I Adatia (2018) The voice of the heart: Vowel-like sound in pulmonary artery hypertension. In Diseases, 6(2). diseases18.pdf
O Nachum, M Norouzi G Tucker, D Schuurmans (2018) Smoothed action value functions for learning Gaussian policies. In International Conference on Machine Learning (ICML-18). icml18.pdf
C Boutilier, A Cohen, A Daniely, A Hassidim, Y Mansour, O Meshi, M Mladenov, D Schuurmans (2018) Planning and learning with stochastic action sets. In International Joint Conference on Artificial Intelligence (IJCAI-18). ijcai18.pdf
O Nachum, M Norouzi K Xu, D Schuurmans (2018) Trust-PCL: An off-policy trust region method for continuous control. In International Conference on Learning Representations (ICLR-18). iclr18.pdf
A Grover, R Gummadi, M Lazaro-Gredilla, D Schuurmans, S Ermon (2018) Variational rejection sampling. In International Conference on Artificial Intelligence and Statistics (AISTATS-18). aistats18.pdf
O Nachum, M Norouzi K Xu, D Schuurmans (2017) Bridging the gap between value and policy based reinforcement learning. In Advances in Neural Information Processing Systems (NeurIPS-17). neurips17a.pdf
M Karami, M White, D Schuurmans, C Szepesvari (2017) Multi-view Matrix Factorization for Linear Dynamical System Estimation. In Advances in Neural Information Processing Systems (NeurIPS-17). neurips17b.pdf
Y Yu, Z Zhang, D Schuurmans (2017) Generalized conditional gradient for sparse estimation. In Journal of Machine Learning Research 18:1-46. jmlr17.pdf
M Zinkevich, A Davies, D Schuurmans (2017) Holographic feature representations of deep networks. In Conference on Uncertainty in Artificial Intelligence (UAI-2017). uai17.pdf
M Mladenov, C Boutilier, D Schuurmans, O Meshi, G Elidan, T Lu (2017) Logistic Markov decision processes. In International Joint Conference on Artificial Intelligence (IJCAI-17). ijcai17.pdf
O Nachum, M Norouzi, D Schuurmans (2017) Improving policy gradient by exploring under-appreciated rewards. In International Conference on Learning Representations (ICLR-17). iclr17.pdf
D Schuurmans, M Zinkevich (2016) Deep learning games. In Advances in Neural Information Processing Systems (NeurIPS-16). nips16a.pdf
M Norouzi, S Bengio, Z Chen, N Jaitly, M Schuster, Y Wu, D Schuurmans (2016) Reward augmented maximum likelihood for neural structured prediction. In Advances in Neural Information Processing Systems (NeurIPS-16). nips16b.pdf
H Cheng, Y Yu, X Zhang, E Xing, D Schuurmans (2016) Scalable and sound low rank tensor learning. In International Conference on Artificial Intelligence and Statistics (AISTATS-16). aistats16a.pdf
S Ravanbakhsh, B Poczos, J Schneider, D Schuurmans, R Greiner (2016) Stochastic neural networks with monotonic activation functions. In International Conference on Artificial Intelligence and Statistics (AISTATS-16). aistats16b.pdf
T Kaddoura, K Vadaimudi, P Bobhate, L Guo, S Jain, M Elgendi, Y Coe, D Kim, D Taylor, W Tymchak, D Schuurmans, R Zemp, I Adatia (2016) Acoustic diagnosis of pulmonary hypertension: Automated speech-recognition-inspired classification algorithm outperforms physicians. In Nature Scientific Reports 6. nsr16.pdf
M Elgendi, S Kumar, L Guo, J Rutledge, Y Coe, R Zemp, D Schuurmans, I Adatia (2015) Detection of heart sounds in children with and without pulmonary hypertension---Daubecheis wavelets approach. In PLOS ONE 10(12). plosone15.pdf
X Li, Y Guo, D Schuurmans (2015) Semi-supervised zero-shot classification with label representation learning. In IEEE International Conference on Computer Vision (ICCV-15). iccv15.pdf
F Mirzazadeh, S Ravanbakhsh, N Ding, D Schuurmans (2015) Embedding inference for structured multilabel predicton. In Advances in Neural Information Processing Systems (NeurIPS-15). nips15.pdf
F Mirzazadeh, M White, A Gyorgy, D Schuurmans (2015) Scalable metric learning for co-embedding. In European Conference on Machine Learning (ECML-15). ecml15a.pdf
K Abou-Moustafa, D Schuurmans (2015) Generalization in unsupervised learning. In European Conference on Machine Learning (ECML-15). ecml15b.pdf
J Wen, R Greiner, D Schuurmans (2015) Correcting covariate shift with the Frank-Wolfe algorithm. In International Joint Conference on Artificial Intelligence (IJCAI-15). ijcai15.pdf
J Neufeld, M Bowling, D Schuurmans (2015) Variance reduction via antithetic Markov chains. In International Conference on Artificial Intelligence and Statistics (AISTATS-15). aistats15.pdf
M White, J Wen, M Bowling, D Schuurmans (2015) Optimal estimation of multivariate ARMA models. In Twenty-Ninth Annual Conference on Artificial Intelligence (AAAI-15). aaai15.pdf
M Elgendi, P Bobhate, S Jain, L Guo, J Rutledge, Y Coe, R Zemp, D Schuurmans, I Adatia (2015) The unique heart sound signature of children with pulmonary artery hypertension. Pulmonary Circulation 5(4). pc15.pdf
O Aslan, X Zhang, D Schuurmans (2014) Convex deep learning via normalized kernels. In Advances in Neural Information Processing Systems (NeurIPS-14). nips14.pdf
F Mirzazadeh, Y Guo, D Schuurmans (2014) Convex co-embedding. In Twenty-Eighth Annual Conference on Artificial Intelligence (AAAI-14). aaai14.pdf
J Neufeld, A Gyorgy, D Schuurmans, C Szepesvari (2014) Adaptive Monte Carlo via bandit allocation. In International Conference on Machine Learning (ICML-14). icml14.pdf
M Elgendi, P Bobhate, S Jain, L Guo, J Rutledge, Y Coe, R Zemp, D Schuurmans, I Adatia (2014) Time-domain analysis of heart sounds in children with and without pulmonary artery hypertension: A pilot study using a digital stethoscope. Pulmonary Circulation 4(4). pc14.pdf
M Elgendi, P Bobhate, S Jain, L Guo, J Rutledge, Y Coe, R Zemp, D Schuurmans, I Adatia (2014) Spectral analysis of the heart sounds in children with and without pulmonary artery hypertension. International Journal of Cardiology 173(1). ijc14.pdf
O Aslan, H Cheng, X Zhang, D Schuurmans (2013) Convex two-layer modeling. In Advances in Neural Information Processing Systems (NeurIPS-13). nips13a.pdf
X Zhang, Y Yu, D Schuurmans (2013) Polar operators for structured sparse estimation. In Advances in Neural Information Processing Systems (NeurIPS-13). nips13b.pdf
K Abou-Moustafa, D Schuurmans, F Ferrie (2013) Learning a metric space for neighborhood topology estimation: Applications to manifold learning. In Asian Conference on Machine Learning (ACML-13). acml13.pdf
M Elgendi, I Norton, M Brearley, D Abbott, D Schuurmans (2013) Systolic peak detection in acceleration photoplethysmograms measured from emergency responders in tropical conditions. In PLOS ONE 8(10). plosone13.pdf
Y Yu, H Cheng, D Schuurmans, C Szepesvari (2013) Characterizing the representer theorem. In International Conference on Machine Learning (ICML-13). icml13.pdf
H Cheng, X Zhang, D Schuurmans (2013) Convex relaxations of Bregman divergence clustering. In Conference on Uncertainty in Artificial Intelligence (UAI-13). uai13.pdf
Y Guo, D Schuurmans (2013) Multi-label classification with output kernels. In European Conference on Machine Learning (ECML-13). ecml13.pdf
Y Shi, X Zhang, X Liao, G Lin, D Schuurmans (2013) Protein-chemical interaction prediction via a kernelized sparse learning SVM. In Pacific Symposium on Biocomputing (PSB-13). psb13.pdf
Y Yu, O Aslan, D Schuurmans (2012) A polynomial-time form of robust regression. In Advances in Neural Information Processing Systems (NeurIPS-12). nips12a.pdf
M White, Y Yu, X Zhang, D Schuurmans (2012) Convex multi-view subspace learning. In Advances in Neural Information Processing Systems (NeurIPS-12). nips12b.pdf
X Zhang, Y Yu, D Schuurmans (2012) Accelerated training for matrix-norm regularization: A boosting approach. In Advances in Neural Information Processing Systems (NeurIPS-12). nips12c.pdf
Y Yu, J Neufeld, R Kiros, X Zhang, D Schuurmans (2012) Regularizers versus losses for nonlinear dimensionality reduction. In International Conference on Machine Learning (ICML-12). icml12.pdf
Y Guo, D Schuurmans (2012) Semi-supervised multi-label classification. In European Conference on Machine Learning (ECML-12). ecml12.pdf
M White, D Schuurmans (2012) Generalized optimal reverse prediction. In International Conference on Artificial Intelligence and Statistics (AISTATS-12). aistats12.pdf
Y Shi, X Liao, X Zhang, G Lin, D Schuurmans (2012) Sparse learning based linear coherent bi-clustering. In Workshop on Algorithms in Bioinformatics (WABI-12). wabi12.pdf
S Wang, D Schuurmans, Y Zhao (2012) The latent maximum entropy principle. In ACM Transactions on Knowledge Discovery from Data. tkdd12.pdf
Y Shi, B Yuan, G Lin, D Schuurmans (2012) Protein phosphoylation site prediction via feature discovery support vector machine. In Tsinghua Science and Technology. tst12.pdf
Y Yu, D Schuurmans (2011) Rank/norm regularization with closed-form solutions: Application to subspace clustering. In Conference on Uncertainty in Artificial Intelligence (UAI-11). uai11.pdf
X Zhang, Y Yu, M White, R Huang, D Schuurmans (2011) Convex sparse coding, subspace learning, and semi-supervised extensions. In Twenty-Fifth Annual Conference on Artificial Intelligence (AAAI-11). aaai11a.pdf
Y Guo, D Schuurmans (2011) Adaptive large margin training for multilabel classification. In Twenty-Fifth Annual Conference on Artificial Intelligence (AAAI-11). aaai11b.pdf
D Lizotte, R Greiner, D Schuurmans (2011) An experimental methodology for response surface optimization methods. In Journal of Global Optimization. jogo11a.pdf
J Peng, L Mukhergee, V Singh, D Schuurmans, L Xu (2011) An efficient algorithm for maximal margin clustering. In Journal of Global Optimization. jogo11b.pdf
W Li, D Schuurmans (2011) Modular community detection in networks. In International Joint Conference on Artificial Intelligence (IJCAI-11). ijcai11.pdf
L Cheng, M Gong, D Schuurmans, T Caelli (2011) Real-time discriminative background subtraction. In IEEE Transactions on Image Processing. ip11.pdf
Y Yu, M Yang, L Xu, M White, D Schuurmans (2010) Relaxed clipping: A global training method for robust regression and classification. In Advances in Neural Information Processing Systems (NeurIPS-2010). nips10.pdf
N Quadrianto, D Schuurmans, A Smola (2010) Distributed flow algorithms for scalable similarity visualization. In ICDM 2010 Workshop on Optimization Based Methods for Emerging Data Mining Problems (OEDM-2010). oedm10.pdf
S Bergsma, D Lin, D Schuurmans (2010) Improved natural language learning via variance-regularization support vector machines. In Conference on Computational Natural Language Learning (CoNLL-2010). conll10.pdf
Y Shi, Y Guo, G Lin, D Schuurmans (2010) Kernel-based gene regulatory network inference. In Conference on Computational Systems Bioinformatics (CSB-2010). csb10.pdf
W Li, L Xu, D Schuurmans (2010) Facility locations revisited: An efficient belief propagation approach. In IEEE International Conference on Automation and Logistics (ICAL-2010). ical10.pdf
N Quadrianto, T Caetano, J Lim, D Schuurmans (2009) Convex relaxation of mixture regression with efficient algorithms. In Advances in Neural Information Processing Systems (NeurIPS-2009). nips09a.pdf
Y Yu, Y Li, C Szepesvari, D Schuurmans (2009) A general projection property for distribution families. In Advances in Neural Information Processing Systems (NeurIPS-2009). nips09b.pdf
L Xu, M White, D Schuurmans (2009) Optimal reverse prediction: a unified perspective on supervised, unsupervised and semi-supervised learning. In International Conference on Machine Learning (ICML-09). icml09.pdf
L Xu, W Li, D Schuurmans (2009) Fast normalized cut with linear constraints. In IEEE International Conference on Computer Vision and Pattern Recognition (CVPR-09). cvpr09.pdf
Y Guo, D Schuurmans (2009) A reformulation of support vector machines for general confidence functions. In Asian Conference on Machine Learning (ACML-09). acml09.pdf
Y Li, C Szepesvari, D Schuurmans (2009) Learning exercise policies for American options. In International Conference on Artificial Intelligence and Statistics (AISTATS-09). aistats09a.pdf
M Yang, Y Li, D Schuurmans (2009) Dual temporal difference learning. In International Conference on Artificial Intelligence and Statistics (AISTATS-09). aistats09b.pdf
Y Li, L Cheng, D Schuurmans (2009) Inference of the structural credit risk model using MLE. In IEEE Symposium on Computational Intelligence for Financial Engineering (CIFEr-09). cifer09.pdf
Y Shi, Z Cai, G Lin, D Schuurmans (2009) Linear coherent bi-cluster discovery via line detection and sample majority voting. In International Conference on Combinatorial Optimization and Applications (COCOA-09). cocoa09.pdf
T Wang, D Lizotte, M Bowling, D Schuurmans (2008) Dual representations for dynamic programming. dualdp.pdf (29 pages)
Y Li, D Schuurmans (2008) Policy iteration for learning and exercise policy for American options. In European Workshop on Reinforcement Learning (EWRL-08). ewrl08.pdf
Q Wang, D Schuurmans, D Lin (2008) Semi-supervised convex training for dependency parsing. In Conference of the Association for Computational Linguistics: Human Language Technologies (ACL-08). acl08.pdf
Y Guo, D Schuurmans (2007) Convex relaxations of latent variable training. In Advances in Neural Information Processing Systems (NeurIPS-2007). nips07b.pdf
Y Guo, D Schuurmans (2007) Discriminative batch mode active learning. In Advances in Neural Information Processing Systems (NeurIPS-2007). nips07c.pdf
T Wang, D Lizotte, M Bowling, D Schuurmans (2007) Stable dual dynamic programming. In Advances in Neural Information Processing Systems (NeurIPS-2007). nips07a.pdf
T Wang, M Bowling, D Schuurmans (2007) Dual representations for dynamic programming and reinforcement learning. In IEEE International Symposium on Approximate Dynamic Programming and Reinforcement Learning (IEEE ADPRL-07). adprl07.pdf
Y Guo, D Schuurmans (2007) Learning gene regulatory networks via globally regularized risk minimization. In RECOMB Satellite Workshop on Comparative Genomics (RECOMB-CG-07). recombcg07.pdf
D Lizotte, T Wang, M Bowling, D Schuurmans (2007) Automatic gait optimization with Gaussian process regression. In International Joint Conference on Artificial Intelligence (IJCAI-07). ijcai07a.pdf
Q Wang, D Lin, D Schuurmans (2007) Simple training of dependency parsers via structured boosting. In International Joint Conference on Artificial Intelligence (IJCAI-07). ijcai07b.pdf
L Cheng, S Vishwanathan, D Schuurmans, S Wang, T Caelli (2006) Implicit online learning with kernels. In Advances in Neural Information Processing Systems (NeurIPS-2006). nips06a.pdf
C Lee, S Wang, F Jiao, D Schuurmans, R Greiner (2006) Learning to model spatial dependency: semi-supervised discriminative random fields. In Advances in Neural Information Processing Systems (NeurIPS-2006). nips06b.pdf
L Cheng, S Wang, D Schuurmans, T Caelli, S Vishwanathan (2006) An online discriminative approach to background subtraction. In IEEE International Conference on Advanced Video and Signal Based Serveillance (AVSS-2006). avss06.pdf
J Huang, T Zhu, R Greiner, D Zhou, D Schuurmans (2006) Information marginalization on subgraphs. In Joint European Conference on Machine Learning and European Conference on Principles and Practice of Knowledge Discovery in Databases (ECML/PKDD-06). pkdd06a.pdf
J Huang, T Zhu, D Schuurmans (2006) Web communities identification from random walks. In Joint European Conference on Machine Learning and European Conference on Principles and Practice of Knowledge Discovery in Databases (ECML/PKDD-06). pkdd06b.pdf
Y Guo, D Schuurmans (2006) Convex structure learning for Bayesian networks: polynomial feature selection and approximate ordering. In Conference on Uncertainty in Artificial Intelligence (UAI-06). uai06.pdf
L Xu, D Wilkinson, F Southey, D Schuurmans (2006) Discriminative unsupervised learning of structured predictors. In International Conference on Machine Learning (ICML-06). icml06.pdf
L Xu, K Crammer, D Schuurmans (2006) Robust support vector machine training via convex outlier ablation. In National Conference on Artificial Intelligence (AAAI-06). aaai06a.pdf
T Wang, P Poupart, M Bowling, D Schuurmans (2006) Compact, convex upper bound iteration for approximate POMDP planning. In National Conference on Artificial Intelligence (AAAI-06). aaai06b.pdf
F Jiao, S Wang, C Lee, R Greiner, D Schuurmans (2006) Semi-supervised conditional random fields for improved sequence segmentation and labeling. In Joint Conference of the International Committee on Computational Linguistics and the Association for Computational Linguistics (COLING/ACL-06). acl06.pdf
F Jiao, J Xu, L Yu, D Schuurmans (2006) Protein fold recognition using the gradient boost algorithm. In Computational Systems Bioinformatics Conference (CSB-06). csb06.pdf
Q Wang, C Cherry, D Lizotte, D Schuurmans (2006) Improved large margin dependency parsing via local constraints and Laplacian regularization. In Conference on Computational Natural Language Learning (CONLL-06). conll06.pdf
T Caetano, T Caelli, D Schuurmans, D Barone (2006) Graphical models and point pattern matching. In IEEE Transactions on Pattern Analysis and Machine Intelligence 28 (10):1646-1663. pami06.pdf
C Boutilier, R Patrascu, P Poupart, D Schuurmans (2006) Constraint-based optimization and utility elicitation using the minimax decision criterion. Artificial Intelligence 170 (8-9): 686-713. aij06.pdf
D Schuurmans, F Southey, D Wilkinson, Y Guo (2006) Metric-based approaches for semi-supervised regression and classification. In O Chapelle, B Schoelkopf and A Zien, editors, Semi-Supervised Learning, MIT Press. ssl06.pdf
S Wang, S Wang, L Cheng, R Greiner, D Schuurmans (2006) Stochastic analysis of a lexical and semantic enhanced structural language model. In International Colloquium on Grammatical Inference (ICGI-2006). icgi06.pdf
Y Guo, D Wilkinson, D Schuurmans (2005) Maximum margin Bayesian networks. In Conference on Uncertainty in Artificial Intelligence (UAI-05). uai05.pdf
L Xu, D Schuurmans (2005) Unsupervised and semi-supervised multi-class support vector machines. In National Conference on Artificial Intelligence (AAAI-05). aaai05.pdf
T Wang, D Lizotte, M Bowling, D Schuurmans (2005) Bayesian sparse sampling for on-line reward optimization. In International Conference on Machine Learning (ICML-05). icml05a.pdf
S Wang, S Wang, R Greiner, D Schuurmans, L Cheng (2005) Exploiting syntactic, semantic and lexical regularities in language modeling via directed Markov random fields. In International Conference on Machine Learning (ICML-05). icml05b.ps.gz
L Cheng, F Jiao, D Schuurmans, S Wang (2005) Variational Bayesian image modelling. In International Conference on Machine Learning (ICML-05). icml05c.pdf
Y Guo, R Greiner, D Schuurmans (2005) Learning coordination classifiers. In International Joint Conference on Artificial Intelligence (IJCAI-05). ijcai05a.pdf
C Boutilier, R Patrascu, P Poupart, D Schuurmans (2005) Regret-based utility elicitation in contraint-based decision problems. In International Joint Conference on Artificial Intelligence (IJCAI-05). ijcai05b.ps.gz
A Ghodsi, F Southey, J Huang, D Schuurmans (2005) Tangent corrected embedding. In IEEE International Conference on Computer Vision and Pattern Recognition (CVPR-05). cvpr05.pdf
Q Wang, D Schuurmans, D Lin (2005) Strictly lexical dependency parsing. In International Workshop on Parsing Technologies (IWPT-2005). iwpt05.pdf
Q Wang, D Schuurmans (2005) Improved estimation for unsupervsied part-of-speech tagging. In EEE International Conference on Natural Language Processing and Knowledge Engineering (IEEE NLP-KE'2005). nlpke05.pdf
S Wang, D Schuurmans, F Peng, Y Zhao (2005) Combining statistical language models via the latent maximum entropy principle. In Machine Learning 60(1-3): 229-250. mlj05.ps.gz
L Xu, J Neufeld, B Larson, D Schuurmans (2004) Maximum margin clustering. In Advances in Neural Information Processing Systems (NeurIPS-2004). nips04.ps.gz
A Ghodsi, J Huang, D Schuurmans (2004) Transformation-invariant embedding. In European Conference on Computer Vision (ECCV-04). eccv04.ps.gz
J Huang, F Peng, A An, D Schuurmans (2004) Dynamic web log session identification with statistical language models. In Journal of the American Society for Information Science and Technology 55(14): 1290--1303. jasist04.ps.gz
S Wang, D Schuurmans, F Peng, Y Zhao (2004) Learning mixture models with the regularized maximum entropy principle. In IEEE Transactions on Neural Networks 15 (4): 903-916. ieeenn04.ps.gz
Earlier conference version appeared in International Conference on Machine Learning (ICML-03). icml03.ps.gz
S Wang, D Schuurmans, Y Zhao (2003) The latent maximum entropy principle. lme.ps.gz
F Peng, D Schuurmans, S Wang (2003) Augmenting Naive Bayes classifiers with statistical language models. In Information Retrieval 7 (3): 317-345. jir03b.ps.gz
X Huang, F Peng, D Schuurmans, N Cercone, S Robertson (2003) Applying machine learning to text segmentation for information retrieval. In Information Retrieval 6 (3): 333-362. jir03a.ps.gz
C Boutilier, R Patrascu, P Poupart, D Schuurmans (2003) Constraint-based optimization with the minimax decision criterion. In Conference on Principles and Practice of Constraint Programming (CP-03). cp03.ps.gz
F Lu, D Schuurmans (2003) Monte Carlo matrix inversion policy evaluation. In Conference on Uncertainty in Artificial Intelligence (UAI-03). uai03a.ps.gz
S Wang, D Schuurmans, F Peng, Y Zhao (2003) Boltzmann machine learning with the latent maximum entropy principle. In Conference on Uncertainty in Artificial Intelligence (UAI-03). uai03b.ps.gz
F Peng, D Schuurmans, S Wang (2003) Language and task independent text categorization with simple language models. In Human Language Technology Conference (HLT-NAACL-03). naacl03.ps.gz
S Wang, D Schuurmans (2003) Learning continuous latent variable models with Bregman divergences. In International Conference on Algorithmic Learning Theory (ALT-03). alt03.ps.gz
F Lu, D Schuurmans (2003) Model-based least-squares policy evaluation. In Sixteenth Canadian Conference on Artificial Intelligence (CAI-03). cai03a.ps.gz
X Huang, F Peng, A An, D Schuurmans, N Cercone (2003) Session boundary detection for association rule learning using n-gram language models. In Sixteenth Canadian Conference on Artificial Intelligence (CAI-03). cai03b.ps.gz
F Peng, D Schuurmans, V Keselj, S Wang (2003) Language independent authorship attribution using character level language models. In Tenth Conference of the European Chapter of the Association for Computational Linguistics (EACL-03). eacl03.ps.gz
F Peng, D Schuurmans (2003) Combining naive Bayes and n-gram language models for text classification. In Twenty-Fifth European Conference on Information Retrieval Research (ECIR-03). ecir03.ps.gz
S Wang, D Schuurmans, F Peng, Y Zhao (2003) Semantic n-gram language modeling with the latent maximum entropy principle. In IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP-03). icassp03.ps.gz
S Wang, D Schuurmans, F Peng (2003) Latent maximum entropy approach for semantic n-gram language modeling. In Ninth International Workshop on Artificial Intelligence and Statistics (AISTATS-03). aistats03.ps.gz
A Ghodsi, D Schuurmans (2003) Automatic basis selection techniques for RBF networks. Neural Networks 16 (5-6): 809-816. nn03.ps.gz
Earlier conference version appeared in International Joint Conference on Neural Networks (IJCNN-03). ijcnn03.ps.gz
F Southey, D Schuurmans, A Ghodsi (2002) Regularized greedy importance sampling. In Advances in Neural Information Processing Systems (NeurIPS-2002). nips02.ps.gz
F Lu, R Patrascu, D Schuurmans (2002) Investigating the maximum likelihood alternative to TD(). In International Conference on Machine Learning (ICML-02). icml02a.ps.gz
C Guestrin, R Patrascu, D Schuurmans (2002) Algorithm directed exploration for model-based reinforcement learning in factored MDPs. In International Conference on Machine Learning (ICML-02). icml02b.ps.gz
F Peng, X Huang, D Schuurmans, N Cercone (2002) Investigating the relationship between word segmentation performance and retrieval performance in Chinese IR. In International Conference on Computational Linguistics (COLING-02). coling02.ps.gz
F Peng, X Huang, D Schuurmans, N Cercone, S Robertson (2002) Using self-supervised word segmentation in Chinese information retrieval. Short version in International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR-02). sigir02.ps.gz
G Elidan, M Ninio, N Friedman, D Schuurmans (2002) Data perturbation for escaping local maxima in learning. In AAAI Conference on Artificial Intelligence (AAAI-02). aaai02a.ps.gz
R Patrascu, P Poupart, D Schuurmans, C Boutilier, C Guestrin (2002) Greedy linear value-approximation for factored Markov decision processes. In AAAI Conference on Artificial Intelligence (AAAI-02). aaai02b.ps.gz
P Poupart, C Boutilier, R Patrascu, D Schuurmans (2002) Piecewise linear value function approximation for factored MDPs. In AAAI Conference on Artificial Intelligence (AAAI-02). aaai02c.ps.gz
S Wang, R Rosenfeld, Y Zhao, D Schuurmans (2002) The latent maximum entropy principle. Short version in 2002 IEEE International Symposium on Information Theory (ISIT-02). isit02.ps.gz
D Schuurmans, F Southey (2002) Metric-based methods for adaptive model selection and regularization. Machine Learning 48(1-3): 51-84. Special Issue on New Methods for Model Selection and Model Combination. mlj02.pdf
R Greiner, D Schuurmans, C O'Brien (2002) Efficient estimation exploiting independence constraints. bayest.ps.gz
D Schuurmans, R Patrascu (2001) Direct value-approximation for factored MDPs. In Advances in Neural Information Processing 14 (NeurIPS-2001). nips01.ps.gz
F Peng, D Schuurmans (2001) A simple closed-class/open-class factorization for language modeling. In 6th Natural Language Processing Pacific Rim Symposium (NLPRS-2001). nlprs01b.ps.gz
F Peng, D Schuurmans (2001) A hierarchical EM approach to word segmentation. In 6th Natural Language Processing Pacific Rim Symposium (NLPRS-2001). nlprs01a.ps.gz
F Peng, D Schuurmans (2001) Self-supervised Chinese word segmentation. In International Symposium on Intelligent Data Analysis (IDA-2001). ida01.ps.gz
D Schuurmans, F Southey, R Holte (2001) The exponentiated subgradient algorithm for heuristic Boolean programming. In International Joint Conference on Artificial Intelligence (IJCAI-01). ijcai01.ps.gz (See related software)
D Schuurmans, F Southey (2001) Local search characteristics of incomplete SAT procedures. Artificial Intelligence 132(2), 121-150. aij01.pdf
Earlier conference paper appeared in AAAI Conference on Artificial Intelligence (AAAI-2000). aaai00.ps.gz
(See related software)
A Grove, N Littlestone, D Schuurmans (2001) General convergence results for linear discriminant updates. Machine Learning 43(1-3), 173-210. mlj01.pdf
Earlier conference paper appeared in Conference on Learning Theory (COLT-97). colt97.ps.gz
D Schuurmans, F Southey (2000) Monte Carlo inference via greedy importance sampling. In Conference on Uncertainty in Artificial Intelligence (UAI-2000). uai00.ps.gz
D Schuurmans, F Southey (2000) An adaptive regularization criterion for supervised learning. In International Conference on Machine Learning (ICML-2000). icml00.ps.gz
A Smola, P Bartlett, B Schoelkopf, D Schuurmans (2000) Introduction to Large Margin Classifiers. In Advances in Large Margin Classifiers. MIT Press, Cambridge, MA. A Smola, P Bartlett, B Schoelkopf, D Schuurmans, editors. lmc.ps.gz
D Schuurmans (1999) Greedy importance sampling. In Advances in Neural Information Processing 12 (NeurIPS-99). nips99.ps.gz
D Schuurmans, L Greenwald (1999) Efficient exploration for optimizing immediate reward. In AAAI Conference on Artificial Intelligence (AAAI-99). aaai99.ps.gz
A Grove, D Schuurmans (1998) Boosting in the limit: maximizing the margin of learned ensembles. In AAAI Conference on Artificial Intelligence (AAAI-98). aaai98.ps.gz
D Schuurmans (1997) A new metric-based approach to model selection. In AAAI Conference on Artificial Intelligence (AAAI-97). aaai97.ps.gz
D Schuurmans, L Ungar, D Foster (1997) Characterizing the generalization performance of model selection strategies. In International Conference on Machine Learning (ICML-97). icml97.ps.gz
R Greiner, A Grove, D Schuurmans (1997) Learning Bayesian nets that perform well. In Conference on Uncertainty in Artificial Intelligence (UAI-97). uai97.ps.gz
R Greiner, A Grove, D Schuurmans (1997) On learning hierarchical classifications. hier.ps.gz
D Schuurmans (1996) Effective Classification Learning. PhD Thesis, Department of Computer Science, University of Toronto. thesis-techrept.pdf (183 pages)
D Schuurmans, R Greiner (1995) Practical PAC learning. In International Joint Conference on Artificial Intelligence (IJCAI-95). ijcai95.ps.gz
D Schuurmans, R Greiner (1995) Sequential PAC learning. In Conference on Learning Theory (COLT-95). colt95.ps.gz
D Schuurmans (1995) Characterizing rational versus exponential learning curves. In European Conference on Computational Learning Theory (EuroCOLT-95) . eurocolt95.ps.gz
Extended paper appears in Journal of Computer and System Sciences 55 (1997), 140-160.
D Schuurmans, R Greiner (1994) Learning default concepts. In Canadian Conference on Artificial Intelligence (CSCSI-94). cscsi94.ps.gz
D Schuurmans, R Greiner (1993) Learning to classify incomplete examples. In Computational Learning Theory and Natural Learning Systems, Volume 4. clnl93-incl.ps.gz, (bib)
D Schuurmans (1993) Fast distribution-specific learning. In Computational Learning Theory and Natural Learning Systems, Volume 4. clnl93-seq.ps.gz, (bib)
R Greiner, D Schuurmans (1992) Learning useful Horn approximations. In International Conference on Knowledge Representation and Reasoning (KR-92). kr92.ps.gz
W Cohen, R Greiner, D Schuurmans (1992) Probabilistic hill-climbing. In Computational Learning Theory and Natural Learning systems, Volume 2. clnl92.ps.gz