Skip to content
conftrace_

Dongsheng Ding

10 papers · 2020–2025 · 6 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 ↓
+4 more ↓ 🐣 Hot Topic Early Bird 🌍 Conference Polyglot Β· Silver πŸƒ Academic Marathon Β· Sprint πŸŒ‰ Interdisciplinary Bridge Β· Bronze πŸ—ΊοΈ Taxonomy Completionist (17)
🧬 Topic Evolution πŸ’Ž Century Club Β· Bronze πŸ”₯ Unstoppable Β· Bronze πŸ—ƒοΈ Keyword Collector (54)

Venues

NeurIPS (4) AISTATS (2) AAAI (1) ICML (1) JMLR (1) L4DC (1)

Top co-authors

Alejandro Ribeiro (4) Mihailo Jovanovic (4) Kaiqing Zhang (4) Chen-Yu Wei (2) Zhaoran Wang (2) Xiaohan Wei (2) Zhuoran Yang (2) Tamer Basar (2) Jiali Duan (1) Osbert Bastani (1)

Research topics

Reinforcement Learning (9) Methods (9) Machine Learning (7) Optimization & Theory (6) Artificial Intelligence (4) Core AI (4) Learning Types Β· Machine Learning (4) Applications (3) Deep Learning (1) Application Areas (1) Learning Types Β· Deep Learning (1) Models (1)

Keywords

policy optimization (5) constrained markov decision process (4) function approximation (3) primal-dual optimization (3) policy gradient (3) constrained optimization (3) reinforcement learning (2) primal-dual method (2) natural policy gradient (2) constrained mdp (2) regret bound (2) safety alignment (1) sample complexity (1) reinforcement learning from human feedback (1) constrained generation (1) policy search (1) preference alignment (1) distribution matching (1) optimal control (1) nash equilibrium (1)

Papers

Convergence and Sample Complexity of Natural Policy Gradient Primal-Dual Methods for Constrained MDPs JMLR 2025 Deterministic Policy Gradient Primal-Dual Methods for Continuous-Space Constrained MDPs AAAI 2025 Constrained Diffusion Models via Dual Training NeurIPS 2024 One-Shot Safety Alignment for Large Language Models via Optimal Dualization NeurIPS 2024 Resilient Constrained Reinforcement Learning AISTATS 2024 Last-Iterate Convergent Policy Gradient Primal-Dual Methods for Constrained MDPs NeurIPS 2023 Provably Efficient Generalized Lagrangian Policy Optimization for Safe Multi-Agent Reinforcement Learning L4DC 2023 Independent Policy Gradient for Large-Scale Markov Potential Games: Sharper Rates, Function Approximation, and Game-Agnostic Convergence ICML 2022 Provably Efficient Safe Exploration via Primal-Dual Policy Optimization AISTATS 2021 Natural Policy Gradient Primal-Dual Method for Constrained Markov Decision Processes NeurIPS 2020