pith. sign in

Kefan Dong

Identifiers

  • name variant Kefan Dong 0.60 · backfill

Papers (16)

  1. Scaling Self-Play with Self-Guidance cs.LG · 2026 · author #3
  2. STP: Self-play LLM Theorem Provers with Iterative Conjecturing and Proving cs.LG · 2025 · author #1
  3. Formal Theorem Proving by Rewarding LLMs to Decompose Proofs Hierarchically cs.LG · 2024 · author #1
  4. Beyond NTK with Vanilla Gradient Descent: A Mean-Field Analysis of Neural Networks with Polynomial Width, Samples, and Time cs.LG · 2023 · author #3
  5. Toward $L_\infty$-recovery of Nonlinear Functions: A Polynomial Sample Complexity Bound for Gaussian Random Fields cs.LG · 2023 · author #1
  6. Model-based Offline Reinforcement Learning with Local Misspecification cs.LG · 2023 · author #1
  7. First Steps Toward Understanding the Extrapolation of Nonlinear Models to Unseen Domains cs.LG · 2022 · author #1
  8. Asymptotic Instance-Optimal Algorithms for Interactive Decision Making cs.LG · 2022 · author #1
  9. Design of Experiments for Stochastic Contextual Linear Bandits cs.LG · 2021 · author #2
  10. Provable Model-based Nonlinear Bandit and Reinforcement Learning: Shelve Optimism, Embrace Virtual Curvature cs.LG · 2021 · author #1
  11. Refined Analysis of FPL for Adversarial Markov Decision Processes cs.LG · 2020 · author #2
  12. Multinomial Logit Bandit with Low Switching Cost cs.LG · 2020 · author #1
  13. On the Expressivity of Neural Networks for Deep Reinforcement Learning cs.LG · 2019 · author #1
  14. $\sqrt{n}$-Regret for Learning in Markov Decision Processes with Function Approximation and Low Bellman Rank cs.LG · 2019 · author #1
  15. Exploration via Hindsight Goal Generation cs.LG · 2019 · author #2
  16. Q-learning with UCB Exploration is Sample Efficient for Infinite-Horizon MDP cs.LG · 2019 · author #1

Mentions

  • 2502.00212 #1 · arxiv_oai · confidence 0.70 Kefan Dong
  • 2411.01829 #1 · arxiv_oai · confidence 0.70 Kefan Dong
  • 2306.16361 #3 · arxiv_oai · confidence 0.70 Kefan Dong
  • 2206.02326 #1 · arxiv_oai · confidence 0.70 Kefan Dong
  • 2305.00322 #1 · arxiv_oai · confidence 0.70 Kefan Dong
  • 2301.11426 #1 · arxiv_oai · confidence 0.70 Kefan Dong
  • 2211.11719 #1 · arxiv_oai · confidence 0.70 Kefan Dong
  • 2102.04168 #1 · arxiv_oai · confidence 0.70 Kefan Dong
  • 2107.09912 #2 · arxiv_oai · confidence 0.70 Kefan Dong
  • 1910.05927 #1 · arxiv_oai · confidence 0.70 Kefan Dong
  • 2008.09251 #2 · arxiv_oai · confidence 0.70 Kefan Dong
  • 2007.04876 #1 · arxiv_oai · confidence 0.70 Kefan Dong
  • 1909.02506 #1 · arxiv_oai · confidence 0.70 Kefan Dong
  • 1906.04279 #2 · arxiv_oai · confidence 0.70 Kefan Dong
  • 1901.09311 #1 · arxiv_oai · confidence 0.70 Kefan Dong

Frequent Coauthors