Kefan Dong

According to our database, Kefan Dong authored at least 18 papers between 2019 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2024

Formal Theorem Proving by Rewarding LLMs to Decompose Proofs Hierarchically.

Kefan Dong, Arvind V. Mahankali, Tengyu Ma

CoRR, 2024

2023

Beyond NTK with Vanilla Gradient Descent: A Mean-Field Analysis of Neural Networks with Polynomial Width, Samples, and Time.

Arvind V. Mahankali, Jeff Z. HaoChen, Kefan Dong, Margalit Glasgow, Tengyu Ma

CoRR, 2023

Toward L_∞-recovery of Nonlinear Functions: A Polynomial Sample Complexity Bound for Gaussian Random Fields.

Kefan Dong, Tengyu Ma

CoRR, 2023

Beyond NTK with Vanilla Gradient Descent: A Mean-Field Analysis of Neural Networks with Polynomial Width, Samples, and Time.

Arvind V. Mahankali, Haochen Zhang, Kefan Dong, Margalit Glasgow, Tengyu Ma

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Asymptotic Instance-Optimal Algorithms for Interactive Decision Making.

Kefan Dong, Tengyu Ma

Proceedings of the Eleventh International Conference on Learning Representations, 2023

First Steps Toward Understanding the Extrapolation of Nonlinear Models to Unseen Domains.

Kefan Dong, Tengyu Ma

Proceedings of the Eleventh International Conference on Learning Representations, 2023

Toward L_∞Recovery of Nonlinear Functions: A Polynomial Sample Complexity Bound for Gaussian Random Fields.

Kefan Dong, Tengyu Ma

Proceedings of the Thirty Sixth Annual Conference on Learning Theory, 2023

Model-Based Offline Reinforcement Learning with Local Misspecification.

Kefan Dong, Yannis Flet-Berliac, Allen Nie, Emma Brunskill

Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence, 2023

2021

Design of Experiments for Stochastic Contextual Linear Bandits.

Andrea Zanette, Kefan Dong, Jonathan N. Lee, Emma Brunskill

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Provable Model-based Nonlinear Bandit and Reinforcement Learning: Shelve Optimism, Embrace Virtual Curvature.

Kefan Dong, Jiaqi Yang, Tengyu Ma

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

2020

Refined Analysis of FPL for Adversarial Markov Decision Processes.

Yuanhao Wang, Kefan Dong

CoRR, 2020

Multinomial Logit Bandit with Low Switching Cost.

Kefan Dong, Yingkai Li, Qin Zhang, Yuan Zhou

Proceedings of the 37th International Conference on Machine Learning, 2020

On the Expressivity of Neural Networks for Deep Reinforcement Learning.

Kefan Dong, Yuping Luo, Tianhe Yu, Chelsea Finn, Tengyu Ma

Proceedings of the 37th International Conference on Machine Learning, 2020

Q-learning with UCB Exploration is Sample Efficient for Infinite-Horizon MDP.

Yuanhao Wang, Kefan Dong, Xiaoyu Chen, Liwei Wang

Proceedings of the 8th International Conference on Learning Representations, 2020

Root-n-Regret for Learning in Markov Decision Processes with Function Approximation and Low Bellman Rank.

Kefan Dong, Jian Peng, Yining Wang, Yuan Zhou

Proceedings of the Conference on Learning Theory, 2020

2019

Bootstrapping the Expressivity with Model-based Planning.

Kefan Dong, Yuping Luo, Tengyu Ma

CoRR, 2019

√n-Regret for Learning in Markov Decision Processes with Function Approximation and Low Bellman Rank.

Kefan Dong, Jian Peng, Yining Wang, Yuan Zhou

CoRR, 2019

Exploration via Hindsight Goal Generation.

Zhizhou Ren, Kefan Dong, Yuan Zhou, Qiang Liu, Jian Peng

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019