Daniel M. Roy

Orcid: 0000-0001-8930-0058

Affiliations:
  • University of Toronto, Department of Statistical Sciences
  • University of Toronto, Department of Computer Science (cross-appointment)
  • University of Cambridge, Department of Engineering (former)
  • Massachusetts Institute of Technology, Computer Science and Articial Intelligence Laboratory (former)


According to our database1, Daniel M. Roy authored at least 81 papers between 1990 and 2024.

Collaborative distances:

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2024
Probabilistic Programming Interfaces for Random Graphs: Markov Categories, Graphons, and Nominal Sets.
Proc. ACM Program. Lang., January, 2024

Information Complexity of Stochastic Convex Optimization: Applications to Generalization and Memorization.
CoRR, 2024

2023
The Shaped Transformer: Attention Models in the Infinite Depth-and-Width Limit.
CoRR, 2023

Limitations of Information-Theoretic Generalization Bounds for Gradient Descent Methods in Stochastic Convex Optimization.
Proceedings of the International Conference on Algorithmic Learning Theory, 2023

2022
Statistical Inference with Stochastic Gradient Algorithms.
CoRR, 2022

The Neural Covariance SDE: Shaped Infinite Depth-and-Width Networks at Initialization.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Pruning's Effect on Generalization Through the Lens of Training and Regularization.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Adaptively Exploiting d-Separators with Causal Bandits.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Understanding Generalization via Leave-One-Out Conditional Mutual Information.
Proceedings of the IEEE International Symposium on Information Theory, 2022

2021
NUQSGD: Provably Communication-efficient Data-parallel SGD via Nonuniform Quantization.
J. Mach. Learn. Res., 2021

Minimax Optimal Quantile and Semi-Adversarial Regret via Root-Logarithmic Regularizers.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

The future is log-Gaussian: ResNets and their infinite-depth-and-width limit at initialization.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Towards a Unified Information-Theoretic Framework for Generalization.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Pruning Neural Networks at Initialization: Why Are We Missing the Mark?
Proceedings of the 9th International Conference on Learning Representations, 2021

On the role of data in PAC-Bayes.
Proceedings of the 24th International Conference on Artificial Intelligence and Statistics, 2021

2020
NeurIPS 2020 Competition: Predicting Generalization in Deep Learning.
CoRR, 2020

On the Information Complexity of Proper Learners for VC Classes in the Realizable Case.
CoRR, 2020

Enforcing Interpretability and its Statistical Impacts: Trade-offs between Accuracy and Interpretability.
CoRR, 2020

Relaxing the I.I.D. Assumption: Adaptive Minimax Optimal Sequential Prediction with Expert Advice.
CoRR, 2020

Improved Bounds on Minimax Regret under Logarithmic Loss via Self-Concordance.
CoRR, 2020

On the role of data in PAC-Bayes bounds.
CoRR, 2020

Methods and Analysis of The First Competition in Predicting Generalization of Deep Learning.
Proceedings of the NeurIPS 2020 Competition and Demonstration Track, 2020

Sharpened Generalization Bounds based on Conditional Mutual Information and an Application to Noisy, Iterative Algorithms.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Deep learning versus kernel learning: an empirical study of loss landscape geometry and the time evolution of the Neural Tangent Kernel.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Adaptive Gradient Quantization for Data-Parallel SGD.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

In search of robust measures of generalization.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

In Defense of Uniform Convergence: Generalization via Derandomization with an Application to Interpolating Predictors.
Proceedings of the 37th International Conference on Machine Learning, 2020

Linear Mode Connectivity and the Lottery Ticket Hypothesis.
Proceedings of the 37th International Conference on Machine Learning, 2020

Tight Bounds on Minimax Regret under Logarithmic Loss via Self-Concordance.
Proceedings of the 37th International Conference on Machine Learning, 2020

2019
On the Computability of Conditional Probability.
J. ACM, 2019

Approximations in Probabilistic Programs.
CoRR, 2019

NUQSGD: Improved Communication Efficiency for Data-parallel SGD via Nonuniform Quantization.
CoRR, 2019

The Lottery Ticket Hypothesis at Scale.
CoRR, 2019

Fast-rate PAC-Bayes Generalization Bounds via Shifted Rademacher Processes.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Information-Theoretic Generalization Bounds for SGLD via Data-Dependent Estimates.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Algorithmic barriers to representing conditional independence.
Proceedings of the 34th Annual ACM/IEEE Symposium on Logic in Computer Science, 2019

2018
On the computability of graphons.
CoRR, 2018

Data-dependent PAC-Bayes priors via differential privacy.
Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

Entropy-SGD optimizes the prior of a PAC-Bayes bound: Generalization properties of Entropy-SGD and data-dependent priors.
Proceedings of the 35th International Conference on Machine Learning, 2018

The Beta-Bernoulli process and algebraic effects.
Proceedings of the 45th International Colloquium on Automata, Languages, and Programming, 2018

2017
On computability and disintegration.
Math. Struct. Comput. Sci., 2017

Entropy-SGD optimizes the prior of a PAC-Bayes bound: Data-dependent PAC-Bayes priors via differential privacy.
CoRR, 2017

Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks with Many More Parameters than Training Data.
Proceedings of the Thirty-Third Conference on Uncertainty in Artificial Intelligence, 2017

2016
Sampling and Estimation for (Sparse) Exchangeable Graphs.
CoRR, 2016

A study of the effect of JPG compression on adversarial images.
CoRR, 2016

The Mondrian Kernel.
Proceedings of the Thirty-Second Conference on Uncertainty in Artificial Intelligence, 2016

Measuring the reliability of MCMC inference with bidirectional Monte Carlo.
Proceedings of the Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, 2016

Mondrian Forests for Large-Scale Regression when Uncertainty Matters.
Proceedings of the 19th International Conference on Artificial Intelligence and Statistics, 2016

2015
Bayesian Models of Graphs, Arrays and Other Exchangeable Random Structures.
IEEE Trans. Pattern Anal. Mach. Intell., 2015

The Class of Random Graphs Arising from Exchangeable Random Measures.
CoRR, 2015

Neural Network Matrix Factorization.
CoRR, 2015

Training generative neural networks via Maximum Mean Discrepancy optimization.
Proceedings of the Thirty-First Conference on Uncertainty in Artificial Intelligence, 2015

Particle Gibbs for Bayesian Additive Regression Trees.
Proceedings of the Eighteenth International Conference on Artificial Intelligence and Statistics, 2015

2014
Mondrian Forests: Efficient Online Random Forests.
Proceedings of the Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014, 2014

Towards common-sense reasoning via conditional simulation: legacies of Turing in Artificial Intelligence.
Proceedings of the Turing's Legacy: Developments from Turing's Ideas in Logic, 2014

2013
Top-down particle filtering for Bayesian decision trees.
Proceedings of the 30th International Conference on Machine Learning, 2013

2012
Towards common-sense reasoning via conditional simulation: legacies of Turing in Artificial Intelligence
CoRR, 2012

Computable de Finetti measures.
Ann. Pure Appl. Log., 2012

Random function priors for exchangeable arrays with applications to graphs and relational data.
Proceedings of the Advances in Neural Information Processing Systems 25: 26th Annual Conference on Neural Information Processing Systems 2012. Proceedings of a meeting held December 3-6, 2012

2011
Computability, inference and modeling in probabilistic programming.
PhD thesis, 2011

Probabilistically Accurate Program Transformations.
Proceedings of the Static Analysis - 18th International Symposium, 2011

Complexity of Inference in Latent Dirichlet Allocation.
Proceedings of the Advances in Neural Information Processing Systems 24: 25th Annual Conference on Neural Information Processing Systems 2011. Proceedings of a meeting held 12-14 December 2011, 2011

Noncomputable Conditional Distributions.
Proceedings of the 26th Annual IEEE Symposium on Logic in Computer Science, 2011

Bayesian Policy Search with Policy Priors.
Proceedings of the IJCAI 2011, 2011

2010
Posterior distributions are computable from predictive distributions.
Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, 2010

2009
Exact and Approximate Sampling by Systematic Stochastic Search.
Proceedings of the Twelfth International Conference on Artificial Intelligence and Statistics, 2009

The Infinite Latent Events Model.
Proceedings of the UAI 2009, 2009

Computable Exchangeable Sequences Have Computable de Finetti Measures.
Proceedings of the Mathematical Theory and Computational Practice, 2009

2008
Church: a language for generative models.
Proceedings of the UAI 2008, 2008

The Mondrian Process.
Proceedings of the Advances in Neural Information Processing Systems 21, 2008

2007
AClass: A simple, online, parallelizable algorithm for probabilistic classification.
Proceedings of the Eleventh International Conference on Artificial Intelligence and Statistics, 2007

Bayesian Agglomerative Clustering with Coalescents.
Proceedings of the Advances in Neural Information Processing Systems 20, 2007

Efficient Bayesian Task-Level Transfer Learning.
Proceedings of the IJCAI 2007, 2007

2006
Learning annotated hierarchies from relational data.
Proceedings of the Advances in Neural Information Processing Systems 19, 2006

2004
Enhancing Server Availability and Security Through Failure-Oblivious Computing.
Proceedings of the 6th Symposium on Operating System Design and Implementation (OSDI 2004), 2004

A Dynamic Technique for Eliminating Buffer Overflow Vulnerabilities (and Other Memory Errors).
Proceedings of the 20th Annual Computer Security Applications Conference (ACSAC 2004), 2004

1990
Reporting test results.
Proceedings of the Working Group on Ada Performance Issues 1990, 1990

Recommendations and future trends.
Proceedings of the Working Group on Ada Performance Issues 1990, 1990

PIWG analysis methodology.
Proceedings of the Working Group on Ada Performance Issues 1990, 1990

Results introduction.
Proceedings of the Working Group on Ada Performance Issues 1990, 1990

PIWG measurement methodology.
Proceedings of the Working Group on Ada Performance Issues 1990, 1990


  Loading...