Gugan Thoppe

6 papers · 2018–2026 · 4 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 ↓

+2 more ↓

🌉 Interdisciplinary Bridge · Bronze 🏃 Academic Marathon · Sprint 🗺️ Taxonomy Completionist (13) 🐣 Hot Topic Early Bird 🌍 Conference Polyglot · Bronze

🧬 Topic Evolution ❓ The Questioner

Venues

AAAI (2) ICML (2) COLT (1) UAI (1)

Top co-authors

Gal Dalal (3) Shie Mannor (2) Balázs Szörényi (2) Assaf Hallak (1) Swetha Ganesh (1) Vijay Gupta (1) Ankur Naskar (1) Sanjay P. Bhat (1) Prashanth L A (1) Rohan Deb (1)

Research topics

Machine Learning (5) Optimization & Theory (5) Mathematics & Optimization (3) Optimization (3) Reinforcement Learning (2) Methods (2) Learning Types (1) Mathematics (1)

Keywords

stochastic approximation (2) temporal difference learning (2) convergence rate (2) policy evaluation (1) policy gradient (1) sample complexity (1) markov decision process (1) polyak-ruppert averaging (1) finite-time analysis (1) variance (1) finite-sample analysis (1) quadratic optimization (1) momentum method (1) gradient variance (1) markov process (1) risk measure (1) optimal convergence rate (1) conditional value at risk (1) discounted cost (1) two-timescale algorithm (1)

Papers

Parameter-free Optimal Rates for Nonlinear Semi-Norm Contractions with Applications to Q-Learning AAAI 2026 Policy Gradient with Tree Expansion ICML 2025 Risk Estimation in a Markov Cost Process: Lower and Upper Bounds ICML 2024 Does Momentum Help in Stochastic Optimization? A Sample Complexity Analysis. UAI 2023 A Tale of Two-Timescale Reinforcement Learning with the Tightest Finite-Time Bound AAAI 2020 Finite Sample Analysis of Two-Timescale Stochastic Approximation with Applications to Reinforcement Learning COLT 2018