Daniel M. Roy

ORCID

Publication Activity (10 Years)

Years Active: 1990-2024
Publications (10 Years): 68

Top Venues

Massachusetts Institute of Technology, Cambridge, MA, USA (PHD)

Education History

Massachusetts Institute of Technology, Cambridge, MA, USA

PHD

Publications

Ziyi Liu, Idan Attias, Daniel M. Roy
Causal Bandits: The Pareto Optimal Frontier of Adaptivity, a Reduction to Linear Bandits, and Limitations around Unknown Marginals. CoRR (2024)
Ekansh Sharma, Devin Kwok, Tom Denton, Daniel M. Roy, David Rolnick, Gintare Karolina Dziugaite
Simultaneous linear connectivity of neural networks modulo permutation. CoRR (2024)
Nathanael L. Ackerman, Cameron E. Freer, Younesse Kaddar, Jacek Karwowski, Sean K. Moss, Daniel M. Roy, Sam Staton, Hongseok Yang
Probabilistic Programming Interfaces for Random Graphs: Markov Categories, Graphons, and Nominal Sets. Proc. ACM Program. Lang. 8 (POPL) (2024)
Idan Attias, Gintare Karolina Dziugaite, Mahdi Haghifam, Roi Livni, Daniel M. Roy
Information Complexity of Stochastic Convex Optimization: Applications to Generalization and Memorization. CoRR (2024)
Lorenzo Noci, Chuning Li, Mufan Bill Li, Bobby He, Thomas Hofmann, Chris Maddison, Daniel M. Roy
The Shaped Transformer: Attention Models in the Infinite Depth-and-Width Limit. CoRR (2023)
Mahdi Haghifam, Borja Rodríguez Gálvez, Ragnar Thobaben, Mikael Skoglund, Daniel M. Roy, Gintare Karolina Dziugaite
Limitations of Information-Theoretic Generalization Bounds for Gradient Descent Methods in Stochastic Convex Optimization. ALT (2023)
Nathanael L. Ackerman, Cameron E. Freer, Younesse Kaddar, Jacek Karwowski, Sean K. Moss, Daniel M. Roy, Sam Staton, Hongseok Yang
Probabilistic programming interfaces for random graphs: Markov categories, graphons, and nominal sets. CoRR (2023)
Blair Bilodeau, Linbo Wang, Daniel M. Roy
Adaptively Exploiting d-Separators with Causal Bandits. CoRR (2022)
Mahdi Haghifam, Shay Moran, Daniel M. Roy, Gintare Karolina Dziugiate
Understanding Generalization via Leave-One-Out Conditional Mutual Information. ISIT (2022)
Tian Jin, Michael Carbin, Daniel M. Roy, Jonathan Frankle, Gintare Karolina Dziugaite
Pruning's Effect on Generalization Through the Lens of Training and Regularization. NeurIPS (2022)
Mahdi Haghifam, Borja Rodríguez Gálvez, Ragnar Thobaben, Mikael Skoglund, Daniel M. Roy, Gintare Karolina Dziugaite
Limitations of Information-Theoretic Generalization Bounds for Gradient Descent Methods in Stochastic Convex Optimization. CoRR (2022)
Mufan (Bill) Li, Mihai Nica, Daniel M. Roy
The Neural Covariance SDE: Shaped Infinite Depth-and-Width Networks at Initialization. NeurIPS (2022)
Jeffrey Negrea, Jun Yang, Haoyue Feng, Daniel M. Roy, Jonathan H. Huggins
Statistical Inference with Stochastic Gradient Algorithms. CoRR (2022)
Mahdi Haghifam, Shay Moran, Daniel M. Roy, Gintare Karolina Dziugaite
Understanding Generalization via Leave-One-Out Conditional Mutual Information. CoRR (2022)
Blair L. Bilodeau, Linbo Wang, Daniel M. Roy
Adaptively Exploiting d-Separators with Causal Bandits. NeurIPS (2022)
Mufan (Bill) Li, Mihai Nica, Daniel M. Roy
The Neural Covariance SDE: Shaped Infinite Depth-and-Width Networks at Initialization. CoRR (2022)
Tian Jin, Michael Carbin, Daniel M. Roy, Jonathan Frankle, Gintare Karolina Dziugaite
Pruning's Effect on Generalization Through the Lens of Training and Regularization. CoRR (2022)
Ali Ramezani-Kebrya, Fartash Faghri, Ilya Markov, Vitalii Aksenov, Dan Alistarh, Daniel M. Roy
NUQSGD: Provably Communication-efficient Data-parallel SGD via Nonuniform Quantization. J. Mach. Learn. Res. 22 (2021)
Mahdi Haghifam, Gintare Karolina Dziugaite, Shay Moran, Daniel M. Roy
Towards a Unified Information-Theoretic Framework for Generalization. CoRR (2021)
Mufan Bill Li, Mihai Nica, Daniel M. Roy
The Future is Log-Gaussian: ResNets and Their Infinite-Depth-and-Width Limit at Initialization. CoRR (2021)
Mufan (Bill) Li, Mihai Nica, Daniel M. Roy
The future is log-Gaussian: ResNets and their infinite-depth-and-width limit at initialization. NeurIPS (2021)
Ali Ramezani-Kebrya, Fartash Faghri, Ilia Markov, Vitaly Aksenov, Dan Alistarh, Daniel M. Roy
NUQSGD: Provably Communication-efficient Data-parallel SGD via Nonuniform Quantization. CoRR (2021)
Jeffrey Negrea, Blair Bilodeau, Nicolò Campolongo, Francesco Orabona, Daniel M. Roy
Minimax Optimal Quantile and Semi-Adversarial Regret via Root-Logarithmic Regularizers. CoRR (2021)
Yiding Jiang, Parth Natekar, Manik Sharma, Sumukh K. Aithal, Dhruva Kashyap, Natarajan Subramanyam, Carlos Lassance, Daniel M. Roy, Gintare Karolina Dziugaite, Suriya Gunasekar, Isabelle Guyon, Pierre Foret, Scott Yak, Hossein Mobahi, Behnam Neyshabur, Samy Bengio
Methods and Analysis of The First Competition in Predicting Generalization of Deep Learning. NeurIPS (Competition and Demos) (2020)
Gintare Karolina Dziugaite, Alexandre Drouin, Brady Neal, Nitarshan Rajkumar, Ethan Caballero, Linbo Wang, Ioannis Mitliagkas, Daniel M. Roy
In search of robust measures of generalization. NeurIPS (2020)
Gintare Karolina Dziugaite, Kyle Hsu, Waseem Gharbieh, Daniel M. Roy
On the role of data in PAC-Bayes bounds. CoRR (2020)
Stanislav Fort, Gintare Karolina Dziugaite, Mansheej Paul, Sepideh Kharaghani, Daniel M. Roy, Surya Ganguli
Deep learning versus kernel learning: an empirical study of loss landscape geometry and the time evolution of the Neural Tangent Kernel. NeurIPS (2020)
Gintare Karolina Dziugaite, Shai Ben-David, Daniel M. Roy
Enforcing Interpretability and its Statistical Impacts: Trade-offs between Accuracy and Interpretability. CoRR (2020)
Blair Bilodeau, Dylan J. Foster, Daniel M. Roy
Improved Bounds on Minimax Regret under Logarithmic Loss via Self-Concordance. CoRR (2020)
Stanislav Fort, Gintare Karolina Dziugaite, Mansheej Paul, Sepideh Kharaghani, Daniel M. Roy, Surya Ganguli
Deep learning versus kernel learning: an empirical study of loss landscape geometry and the time evolution of the Neural Tangent Kernel. CoRR (2020)
Mahdi Haghifam, Jeffrey Negrea, Ashish Khisti, Daniel M. Roy, Gintare Karolina Dziugaite
Sharpened Generalization Bounds based on Conditional Mutual Information and an Application to Noisy, Iterative Algorithms. NeurIPS (2020)
Yiding Jiang, Pierre Foret, Scott Yak, Daniel M. Roy, Hossein Mobahi, Gintare Karolina Dziugaite, Samy Bengio, Suriya Gunasekar, Isabelle Guyon, Behnam Neyshabur
NeurIPS 2020 Competition: Predicting Generalization in Deep Learning. CoRR (2020)
Fartash Faghri, Iman Tabrizian, Ilia Markov, Dan Alistarh, Daniel M. Roy, Ali Ramezani-Kebrya
Adaptive Gradient Quantization for Data-Parallel SGD. CoRR (2020)
Jonathan Frankle, Gintare Karolina Dziugaite, Daniel M. Roy, Michael Carbin
Linear Mode Connectivity and the Lottery Ticket Hypothesis. ICML (2020)
Gintare Karolina Dziugaite, Alexandre Drouin, Brady Neal, Nitarshan Rajkumar, Ethan Caballero, Linbo Wang, Ioannis Mitliagkas, Daniel M. Roy
In Search of Robust Measures of Generalization. CoRR (2020)
Blair Bilodeau, Jeffrey Negrea, Daniel M. Roy
Relaxing the I.I.D. Assumption: Adaptive Minimax Optimal Sequential Prediction with Expert Advice. CoRR (2020)
Mahdi Haghifam, Jeffrey Negrea, Ashish Khisti, Daniel M. Roy, Gintare Karolina Dziugaite
Sharpened Generalization Bounds based on Conditional Mutual Information and an Application to Noisy, Iterative Algorithms. CoRR (2020)
Fartash Faghri, Iman Tabrizian, Ilia Markov, Dan Alistarh, Daniel M. Roy, Ali Ramezani-Kebrya
Adaptive Gradient Quantization for Data-Parallel SGD. NeurIPS (2020)
Blair Bilodeau, Dylan J. Foster, Daniel M. Roy
Tight Bounds on Minimax Regret under Logarithmic Loss via Self-Concordance. ICML (2020)
Jonathan Frankle, Gintare Karolina Dziugaite, Daniel M. Roy, Michael Carbin
Pruning Neural Networks at Initialization: Why are We Missing the Mark? CoRR (2020)
Mahdi Haghifam, Gintare Karolina Dziugaite, Shay Moran, Daniel M. Roy
On the Information Complexity of Proper Learners for VC Classes in the Realizable Case. CoRR (2020)
Jun Yang, Shengyang Sun, Daniel M. Roy
Fast-rate PAC-Bayes Generalization Bounds via Shifted Rademacher Processes. NeurIPS (2019)
Ekansh Sharma, Daniel M. Roy
Approximations in Probabilistic Programs. CoRR (2019)
Nathanael L. Ackerman, Cameron E. Freer, Daniel M. Roy
On the Computability of Conditional Probability. J. ACM 66 (3) (2019)
Ali Ramezani-Kebrya, Fartash Faghri, Daniel M. Roy
NUQSGD: Improved Communication Efficiency for Data-parallel SGD via Nonuniform Quantization. CoRR (2019)
Jonathan Frankle, Gintare Karolina Dziugaite, Daniel M. Roy, Michael Carbin
Linear Mode Connectivity and the Lottery Ticket Hypothesis. CoRR (2019)
Jeffrey Negrea, Gintare Karolina Dziugaite, Daniel M. Roy
In Defense of Uniform Convergence: Generalization via derandomization with an application to interpolating predictors. CoRR (2019)
Jun Yang, Shengyang Sun, Daniel M. Roy
Fast-rate PAC-Bayes Generalization Bounds via Shifted Rademacher Processes. CoRR (2019)
Jeffrey Negrea, Mahdi Haghifam, Gintare Karolina Dziugaite, Ashish Khisti, Daniel M. Roy
Information-Theoretic Generalization Bounds for SGLD via Data-Dependent Estimates. NeurIPS (2019)
Nathanael L. Ackerman, Jeremy Avigad, Cameron E. Freer, Daniel M. Roy, Jason M. Rute
Algorithmic barriers to representing conditional independence. LICS (2019)
Jeffrey Negrea, Mahdi Haghifam, Gintare Karolina Dziugaite, Ashish Khisti, Daniel M. Roy
Information-Theoretic Generalization Bounds for SGLD via Data-Dependent Estimates. CoRR (2019)
Jonathan Frankle, Gintare Karolina Dziugaite, Daniel M. Roy, Michael Carbin
The Lottery Ticket Hypothesis at Scale. CoRR (2019)
Sam Staton, Dario Stein, Hongseok Yang, Nathanael L. Ackerman, Cameron E. Freer, Daniel M. Roy
The Beta-Bernoulli process and algebraic effects. CoRR (2018)
Nathanael L. Ackerman, Jeremy Avigad, Cameron E. Freer, Daniel M. Roy, Jason M. Rute
On the computability of graphons. CoRR (2018)
Sam Staton, Dario Stein, Hongseok Yang, Nathanael L. Ackerman, Cameron E. Freer, Daniel M. Roy
The Beta-Bernoulli process and algebraic effects. ICALP (2018)
Gintare Karolina Dziugaite, Daniel M. Roy
Data-dependent PAC-Bayes priors via differential privacy. NeurIPS (2018)
Gintare Karolina Dziugaite, Daniel M. Roy
Data-dependent PAC-Bayes priors via differential privacy. CoRR (2018)
Gintare Karolina Dziugaite, Daniel M. Roy
Entropy-SGD optimizes the prior of a PAC-Bayes bound: Generalization properties of Entropy-SGD and data-dependent priors. ICML (2018)
Gintare Karolina Dziugaite, Daniel M. Roy
Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks with Many More Parameters than Training Data. CoRR (2017)
Gintare Karolina Dziugaite, Daniel M. Roy
Entropy-SGD optimizes the prior of a PAC-Bayes bound: Data-dependent PAC-Bayes priors via differential privacy. CoRR (2017)
Nathanael L. Ackerman, Cameron E. Freer, Daniel M. Roy
On computability and disintegration. Math. Struct. Comput. Sci. 27 (8) (2017)
Gintare Karolina Dziugaite, Daniel M. Roy
Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks with Many More Parameters than Training Data. UAI (2017)
Matej Balog, Balaji Lakshminarayanan, Zoubin Ghahramani, Daniel M. Roy, Yee Whye Teh
The Mondrian Kernel. UAI (2016)
Balaji Lakshminarayanan, Daniel M. Roy, Yee Whye Teh
Mondrian Forests for Large-Scale Regression when Uncertainty Matters. AISTATS (2016)
Gintare Karolina Dziugaite, Zoubin Ghahramani, Daniel M. Roy
A study of the effect of JPG compression on adversarial images. CoRR (2016)
Roger B. Grosse, Siddharth Ancha, Daniel M. Roy
Measuring the reliability of MCMC inference with bidirectional Monte Carlo. CoRR (2016)
Victor Veitch, Daniel M. Roy
Sampling and Estimation for (Sparse) Exchangeable Graphs. CoRR (2016)
Roger B. Grosse, Siddharth Ancha, Daniel M. Roy
Measuring the reliability of MCMC inference with bidirectional Monte Carlo. NIPS (2016)
Gintare Karolina Dziugaite, Daniel M. Roy
Neural Network Matrix Factorization. CoRR (2015)
Balaji Lakshminarayanan, Daniel M. Roy, Yee Whye Teh
Particle Gibbs for Bayesian Additive Regression Trees. CoRR (2015)
Peter Orbanz, Daniel M. Roy
Bayesian Models of Graphs, Arrays and Other Exchangeable Random Structures. IEEE Trans. Pattern Anal. Mach. Intell. 37 (2) (2015)
Victor Veitch, Daniel M. Roy
The Class of Random Graphs Arising from Exchangeable Random Measures. CoRR (2015)
Nathanael L. Ackerman, Cameron E. Freer, Daniel M. Roy
On computability and disintegration. CoRR (2015)
Balaji Lakshminarayanan, Daniel M. Roy, Yee Whye Teh
Particle Gibbs for Bayesian Additive Regression Trees. AISTATS (2015)
Balaji Lakshminarayanan, Daniel M. Roy, Yee Whye Teh
Mondrian Forests for Large-Scale Regression when Uncertainty Matters. CoRR (2015)
Gintare Karolina Dziugaite, Daniel M. Roy, Zoubin Ghahramani
Training generative neural networks via Maximum Mean Discrepancy optimization. UAI (2015)
Gintare Karolina Dziugaite, Daniel M. Roy, Zoubin Ghahramani
Training generative neural networks via Maximum Mean Discrepancy optimization. CoRR (2015)
Balaji Lakshminarayanan, Daniel M. Roy, Yee Whye Teh
Mondrian Forests: Efficient Online Random Forests. CoRR (2014)
Balaji Lakshminarayanan, Daniel M. Roy, Yee Whye Teh
Mondrian Forests: Efficient Online Random Forests. NIPS (2014)
Balaji Lakshminarayanan, Daniel M. Roy, Yee Whye Teh
Top-down particle filtering for Bayesian decision trees CoRR (2013)
Balaji Lakshminarayanan, Daniel M. Roy, Yee Whye Teh
Top-down particle filtering for Bayesian decision trees. ICML (3) (2013)
James Robert Lloyd, Peter Orbanz, Zoubin Ghahramani, Daniel M. Roy
Random function priors for exchangeable arrays with applications to graphs and relational data. NIPS (2012)
David Wingate, Noah D. Goodman, Daniel M. Roy, Joshua B. Tenenbaum
The Infinite Latent Events Model CoRR (2012)
Cameron E. Freer, Daniel M. Roy, Joshua B. Tenenbaum
Towards common-sense reasoning via conditional simulation: legacies of Turing in Artificial Intelligence CoRR (2012)
Cameron E. Freer, Daniel M. Roy
Computable de Finetti measures. Ann. Pure Appl. Log. 163 (5) (2012)
Noah D. Goodman, Vikash K. Mansinghka, Daniel M. Roy, Kallista A. Bonawitz, Joshua B. Tenenbaum
Church: a language for generative models CoRR (2012)
Nathanael L. Ackerman, Cameron E. Freer, Daniel M. Roy
Noncomputable Conditional Distributions. LICS (2011)
Sasa Misailovic, Daniel M. Roy, Martin C. Rinard
Probabilistically Accurate Program Transformations. SAS (2011)
David A. Sontag, Daniel M. Roy
Complexity of Inference in Latent Dirichlet Allocation. NIPS (2011)
David Wingate, Noah D. Goodman, Daniel M. Roy, Leslie Pack Kaelbling, Joshua B. Tenenbaum
Bayesian Policy Search with Policy Priors. IJCAI (2011)
Cameron E. Freer, Daniel M. Roy
Posterior distributions are computable from predictive distributions. AISTATS (2010)
Nathanael L. Ackerman, Cameron E. Freer, Daniel M. Roy
On the computability of conditional probability. CoRR (2010)
Vikash K. Mansinghka, Daniel M. Roy, Eric Jonas, Joshua B. Tenenbaum
Exact and Approximate Sampling by Systematic Stochastic Search. AISTATS (2009)
Cameron E. Freer, Daniel M. Roy
Computable Exchangeable Sequences Have Computable de Finetti Measures. CiE (2009)
David Wingate, Noah D. Goodman, Daniel M. Roy, Joshua B. Tenenbaum
The Infinite Latent Events Model. UAI (2009)
Cameron E. Freer, Daniel M. Roy
Computable de Finetti measures CoRR (2009)
Noah D. Goodman, Vikash K. Mansinghka, Daniel M. Roy, Kallista A. Bonawitz, Joshua B. Tenenbaum
Church: a language for generative models. UAI (2008)
Daniel M. Roy, Yee Whye Teh
The Mondrian Process. NIPS (2008)
Daniel M. Roy, Leslie Pack Kaelbling
Efficient Bayesian Task-Level Transfer Learning. IJCAI (2007)
Yee Whye Teh, Hal Daumé III, Daniel M. Roy
Bayesian Agglomerative Clustering with Coalescents. NIPS (2007)

Daniel M. Roy.css-eqlu8i{font-size:small;padding-left:4px;}

Publication Activity (10 Years)

Top Topics

Top Venues

Daniel M. Roy