← Authors

Daniel M. Roy

24 papers · 2006–2025 · 7 conferences · across top CS/AI conferences

Achievements

🌍 Conference Polyglot (7) 🐝 Cross-Pollinator (14) 🌈 Renaissance Researcher (6) πŸŒ‰ Interdisciplinary Bridge πŸƒ Academic Marathon (19) πŸ—ΊοΈ Taxonomy Completionist (17) 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🀝 Dynamic Duo (11) πŸ† Keyword Champion πŸ“ˆ Trend Setter πŸš€ Conference Pioneer πŸ—ƒοΈ Keyword Collector (110) πŸ’Ž Century Club (24)

Conferences

NIPS (14) ICML (3) AISTATS (2) COLT (2) ALT (1) ICLR (1) JMLR (1)

Top co-authors

Gintare Karolina Dziugaite (11) Mahdi Haghifam (5) Idan Attias (4) Balaji Lakshminarayanan (2) Yee Whye Teh (2) Fartash Faghri (2) Nazanin Mohammadi Sepahvand (2) Dan Alistarh (2) Ziyi Liu (2) Ali Ramezani-Kebrya (2)

Research topics

Probability (1)

Keywords

generalization bound (6) relational data (3) posterior distribution (3) stochastic gradient descent (3) relational datum (3) data-parallel training (2) gradient quantization (2) mondrian forest (2) online learning (2) exchangeable arrays (2) stochastic gradient langevin dynamics (2) information-theoretic bound (2) communication efficiency (2) mutual information (2) markov chain monte carlo (2) bayesian inference (2) bayesian nonparametrics (2) mondrian process (2) pac-bayes bound (2) ensemble learning (1)

Papers

Leveraging Per-Instance Privacy for Machine Unlearning ICML 2025
The Size of Teachers as a Measure of Data Complexity: PAC-Bayes Excess Risk Bounds and Scaling Laws AISTATS 2025
Selective Unlearning via Representation Erasure Using Domain Adversarial Training ICLR 2025
Capacity-Constrained Online Learning with Delays: Scheduling Frameworks and Regret Trade-offs COLT 2025
Information Complexity of Stochastic Convex Optimization: Applications to Generalization, Memorization, and Tracing ICML 2024
Causal Bandits: The Pareto Optimal Frontier of Adaptivity, a Reduction to Linear Bandits, and Limitations around Unknown Marginals ICML 2024
Sequential Probability Assignment with Contexts: Minimax Regret, Contextual Shtarkov Sums, and Contextual Normalized Maximum Likelihood NIPS 2024
Limitations of Information-Theoretic Generalization Bounds for Gradient Descent Methods in Stochastic Convex Optimization ALT 2023
NUQSGD: Provably Communication-efficient Data-parallel SGD via Nonuniform Quantization JMLR 2021
Information-Theoretic Generalization Bounds for Stochastic Gradient Descent COLT 2021
In search of robust measures of generalization NIPS 2020
Adaptive Gradient Quantization for Data-Parallel SGD NIPS 2020
Deep learning versus kernel learning: an empirical study of loss landscape geometry and the time evolution of the Neural Tangent Kernel NIPS 2020
Sharpened Generalization Bounds based on Conditional Mutual Information and an Application to Noisy, Iterative Algorithms NIPS 2020
Information-Theoretic Generalization Bounds for SGLD via Data-Dependent Estimates NIPS 2019
Fast-rate PAC-Bayes Generalization Bounds via Shifted Rademacher Processes NIPS 2019
Data-dependent PAC-Bayes priors via differential privacy NIPS 2018
Mondrian Forests for Large-Scale Regression when Uncertainty Matters AISTATS 2016
Measuring the reliability of MCMC inference with bidirectional Monte Carlo NIPS 2016
Mondrian Forests: Efficient Online Random Forests NIPS 2014
Random function priors for exchangeable arrays with applications to graphs and relational data NIPS 2012
The Mondrian Process NIPS 2008
Bayesian Agglomerative Clustering with Coalescents NIPS 2007
Learning annotated hierarchies from relational data NIPS 2006