1 code implementation • NeurIPS 2023 • Piotr Indyk, Haike Xu
Graph-based approaches to nearest neighbor search are popular and powerful tools for handling large datasets in practice, but they have limited theoretical guarantees.
1 code implementation • 15 Nov 2022 • Haike Xu, Zongyu Lin, Jing Zhou, Yanan Zheng, Zhilin Yang
In the finetuning setting, our approach also achieves new state-of-the-art results on a wide range of NLP tasks, with only 1/4 parameters of previous methods.
no code implementations • 19 Nov 2021 • Talya Eden, Piotr Indyk, Haike Xu
In particular, we consider heuristics induced by norm embeddings and distance labeling schemes, and provide lower bounds for the tradeoffs between the number of dimensions or bits used to represent each graph node, and the running time of the A* algorithm.
no code implementations • 12 Jun 2021 • Haike Xu, Jian Li
Our algorithm achieves an (approximation) regret bound of $\tilde{O}\left(d\sqrt{KT}\right)$.
no code implementations • 9 Feb 2021 • Haike Xu, Tengyu Ma, Simon S. Du
We further show that for general MDPs, AMB suffers an additional $\frac{|Z_{mul}|}{\Delta_{min}}$ regret, where $Z_{mul}$ is the set of state-action pairs $(s, a)$'s satisfying $a$ is a non-unique optimal action for $s$.