| 2025 | AISTATS | The Size of Teachers as a Measure of Data Complexity: PAC-Bayes Excess Risk Bounds and Scaling Laws. | Gintare Karolina Dziugaite, Daniel M. Roy |
| 2025 | COLT | Capacity-Constrained Online Learning with Delays: Scheduling Frameworks and Regret Trade-offs. | Alexander Ryabchenko, Idan Attias, Daniel M. Roy |
| 2025 | ICLR | Selective Unlearning via Representation Erasure Using Domain Adversarial Training. | Nazanin Mohammadi Sepahvand, Eleni Triantafillou, Hugo Larochelle, Doina Precup, James J. Clark, Daniel M. Roy, Gintare Karolina Dziugaite |
| 2025 | ICML | Leveraging Per-Instance Privacy for Machine Unlearning. | Nazanin Mohammadi Sepahvand, Anvith Thudi, Berivan Isik, Ashmita Bhattacharyya, Nicolas Papernot, Eleni Triantafillou, Daniel M. Roy, Gintare Karolina Dziugaite |
| 2024 | ICML | Information Complexity of Stochastic Convex Optimization: Applications to Generalization, Memorization, and Tracing. | Idan Attias, Gintare Karolina Dziugaite, Mahdi Haghifam, Roi Livni, Daniel M. Roy |
| 2024 | ICML | Causal Bandits: The Pareto Optimal Frontier of Adaptivity, a Reduction to Linear Bandits, and Limitations around Unknown Marginals. | Ziyi Liu, Idan Attias, Daniel M. Roy |
| 2023 | ALT | Limitations of Information-Theoretic Generalization Bounds for Gradient Descent Methods in Stochastic Convex Optimization. | Mahdi Haghifam, Borja Rodrguez Glvez, Ragnar Thobaben, Mikael Skoglund, Daniel M. Roy, Gintare Karolina Dziugaite |
| 2022 | ISIT | Understanding Generalization via Leave-One-Out Conditional Mutual Information. | Mahdi Haghifam, Shay Moran, Daniel M. Roy, Gintare Karolina Dziugaite |
| 2021 | AISTATS | On the role of data in PAC-Bayes. | Gintare Karolina Dziugaite, Kyle Hsu, Waseem Gharbieh, Gabriel Arpino, Daniel M. Roy |
| 2021 | ICLR | Pruning Neural Networks at Initialization: Why Are We Missing the Mark? | Jonathan Frankle, Gintare Karolina Dziugaite, Daniel M. Roy, Michael Carbin |
| 2020 | ICML | Tight Bounds on Minimax Regret under Logarithmic Loss via Self-Concordance. | Blair L. Bilodeau, Dylan J. Foster, Daniel M. Roy |
| 2020 | ICML | Linear Mode Connectivity and the Lottery Ticket Hypothesis. | Jonathan Frankle, Gintare Karolina Dziugaite, Daniel M. Roy, Michael Carbin |
| 2020 | ICML | In Defense of Uniform Convergence: Generalization via Derandomization with an Application to Interpolating Predictors. | Jeffrey Negrea, Gintare Karolina Dziugaite, Daniel M. Roy |
| 2019 | LICS | Algorithmic barriers to representing conditional independence. | Nathanael L. Ackerman, Jeremy Avigad, Cameron E. Freer, Daniel M. Roy, Jason M. Rute |
| 2018 | ICALP | The Beta-Bernoulli process and algebraic effects. | Sam Staton, Dario Stein, Hongseok Yang, Nathanael L. Ackerman, Cameron E. Freer, Daniel M. Roy |
| 2018 | ICML | Entropy-SGD optimizes the prior of a PAC-Bayes bound: Generalization properties of Entropy-SGD and data-dependent priors. | Gintare Karolina Dziugaite, Daniel M. Roy |
| 2017 | UAI | Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks with Many More Parameters than Training Data. | Gintare Karolina Dziugaite, Daniel M. Roy |
| 2016 | AISTATS | Mondrian Forests for Large-Scale Regression when Uncertainty Matters. | Balaji Lakshminarayanan, Daniel M. Roy, Yee Whye Teh |
| 2016 | UAI | The Mondrian Kernel. | Matej Balog, Balaji Lakshminarayanan, Zoubin Ghahramani, Daniel M. Roy, Yee Whye Teh |
| 2015 | AISTATS | Particle Gibbs for Bayesian Additive Regression Trees. | Balaji Lakshminarayanan, Daniel M. Roy, Yee Whye Teh |
| 2015 | UAI | Training generative neural networks via Maximum Mean Discrepancy optimization. | Gintare Karolina Dziugaite, Daniel M. Roy, Zoubin Ghahramani |
| 2013 | ICML | Top-down particle filtering for Bayesian decision trees. | Balaji Lakshminarayanan, Daniel M. Roy, Yee Whye Teh |
| 2011 | IJCAI | Bayesian Policy Search with Policy Priors. | David Wingate, Noah D. Goodman, Daniel M. Roy, Leslie Pack Kaelbling, Joshua B. Tenenbaum |
| 2011 | LICS | Noncomputable Conditional Distributions. | Nathanael L. Ackerman, Cameron E. Freer, Daniel M. Roy |
| 2011 | SAS | Probabilistically Accurate Program Transformations. | Sasa Misailovic, Daniel M. Roy, Martin C. Rinard |
| 2009 | CiE | Computable Exchangeable Sequences Have Computable de Finetti Measures. | Cameron E. Freer, Daniel M. Roy |
| 2009 | UAI | The Infinite Latent Events Model. | David Wingate, Noah D. Goodman, Daniel M. Roy, Joshua B. Tenenbaum |
| 2008 | UAI | Church: a language for generative models. | Noah D. Goodman, Vikash K. Mansinghka, Daniel M. Roy, Kallista A. Bonawitz, Joshua B. Tenenbaum |
| 2007 | IJCAI | Efficient Bayesian Task-Level Transfer Learning. | Daniel M. Roy, Leslie Pack Kaelbling |
| 2004 | ACSAC | A Dynamic Technique for Eliminating Buffer Overflow Vulnerabilities (and Other Memory Errors). | Martin C. Rinard, Cristian Cadar, Daniel Dumitran, Daniel M. Roy, Tudor Leu |
| 2004 | OSDI | Enhancing Server Availability and Security Through Failure-Oblivious Computing. | Martin C. Rinard, Cristian Cadar, Daniel Dumitran, Daniel M. Roy, Tudor Leu, William S. Beebee |