2 citations · 4 across the 6 of their papers we have counts for
9 papers
Trust the Critic More
Kaiyue Wen, Luke Bailey, Arvind Mahankali +1
Standard language model RL algorithms credit every token of a long rollout with the same advantage determined by the terminal reward. Actor-critic methods can provide finer-grained…
Divide-and-Conquer CoT: RL for Reducing Latency via Parallel Reasoning
Arvind Mahankali, Kaiyue Wen, Tengyu Ma
Long chain-of-thought reasoning (Long CoT) is now fundamental to state-of-the-art LLMs, especially in mathematical reasoning. However, LLM generation is highly sequential, and long…
Formal Theorem Proving by Rewarding LLMs to Decompose Proofs Hierarchically
Kefan Dong, Arvind Mahankali, Tengyu Ma
Mathematical theorem proving is an important testbed for large language models' deep and abstract reasoning capability. This paper focuses on improving LLMs' ability to write proof…
One Step of Gradient Descent is Provably the Optimal In-Context Learner with One Layer of Linear Self-Attention
Arvind Mahankali, Tatsunori B. Hashimoto, Tengyu Ma
Recent works have empirically analyzed in-context learning and shown that transformers trained on synthetic linear regression tasks can learn to implement ridge regression, which i…
Beyond NTK with Vanilla Gradient Descent: A Mean-Field Analysis of Neural Networks with Polynomial Width, Samples, and Time
Arvind Mahankali, Jeff Z. Haochen, Kefan Dong +2
Despite recent theoretical progress on the non-convex optimization of two-layer neural networks, it is still an open question whether gradient descent on neural networks without un…
Near-Linear Time and Fixed-Parameter Tractable Algorithms for Tensor Decompositions
Arvind V. Mahankali, David P. Woodruff, Ziyu Zhang
We study low rank approximation of tensors, focusing on the tensor train and Tucker decompositions, as well as approximations with tree tensor networks and more general tensor netw…
Streaming and Distributed Algorithms for Robust Column Subset Selection
Shuli Jiang, Dongyu Li, Irene Mengze Li +2
We give the first single-pass streaming algorithm for Column Subset Selection with respect to the entrywise -norm with . We study the norm loss since…
Optimal Column Subset Selection and a Fast PTAS for Low Rank Approximation
Arvind V. Mahankali, David P. Woodruff
We study the problem of entrywise low rank approximation. We give the first polynomial time column subset selection-based low rank approximation algorithm samplin…
A billiards-like dynamical system for attacking chess pieces
Christopher R. H. Hanusa, Arvind V. Mahankali
We apply a one-dimensional discrete dynamical system originally considered by Arnol'd reminiscent of mathematical billiards to the study of two-move riders, a type of fairy chess p…