Peter Glynn
8 papers · 2018–2025 · 5 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Silver
🏃
Academic Marathon · Sprint
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(23)
❓
The Questioner
Top co-authors
Research topics
Machine Learning
(7)
Optimization & Theory · Machine Learning
(7)
Mathematics & Optimization
(5)
Optimization
(5)
Deep Learning
(3)
Reinforcement Learning
(2)
Bayesian & Probabilistic
(2)
Learning Types
(2)
Methods
(2)
Optimization & Theory · Deep Learning
(2)
Probability
(2)
Artificial Intelligence
(1)
Architectures
(1)
Core AI
(1)
Mathematics
(1)
Keywords
reinforcement learning
(2)
neural network
(2)
sample complexity
(2)
penalty parameter
(1)
stochastic gradient descent
(1)
offline reinforcement learning
(1)
convergence analysis
(1)
optimal transport
(1)
distributionally robust optimization
(1)
high-dimensional optimization
(1)
markov chain monte carlo
(1)
markov decision process
(1)
markov chain
(1)
optimal policy
(1)
stochastic process
(1)
variational inference
(1)
probability measure
(1)
relaxation
(1)
learning theory
(1)
stochastic optimization
(1)
Papers
Tightening Causal Bounds via Covariate-Aware Optimal Transport
ICML 2025
An Efficient High-dimensional Gradient Estimator for Stochastic Differential Equations
NeurIPS 2024
Deep Learning for Computing Convergence Rates of Markov Chains
NeurIPS 2024
Optimal Sample Complexity for Average Reward Markov Decision Processes
ICLR 2024
Finite-Sample Regret Bound for Distributionally Robust Offline Tabular Reinforcement Learning
AISTATS 2021
Optimal $δ$-Correct Best-Arm Selection for Heavy-Tailed Distributions
ALT 2020
Probability Functional Descent: A Unifying Perspective on GANs, Variational Inference, and Reinforcement Learning
ICML 2019
Distributed Asynchronous Optimization with Unbounded Delays: How Slow Can You Go?
ICML 2018