Zobrazeno 1 - 10
of 653
pro vyhledávání: '"Liu Sihan"'
Autor:
LIU Sihan, GENG Xueqian, WANG Ye, MA Yunzhang, CHEN Defeng, ZHANG Bo, CAO Hongfa, QI Ji, LÜ Baojia
Publikováno v:
Fenmo yejin jishu, Vol 41, Iss 3, Pp 210-217 (2023)
Friction coefficients of the Cu-based powder metallurgical brake pads decline due to the high temperature during the high-speed braking, which will directly affect the train braking effectiveness. The 1:1 high-speed braking tests of Cu-based powder m
Externí odkaz:
https://doaj.org/article/9796c332b6ba44f8ae58702ca256f4bf
Autor:
Choudhury, Rohan, Zhu, Guanglei, Liu, Sihan, Niinuma, Koichiro, Kitani, Kris M., Jeni, László
Transformers are slow to train on videos due to extremely large numbers of input tokens, even though many video tokens are repeated over time. Existing methods to remove such uninformative tokens either have significant overhead, negating any speedup
Externí odkaz:
http://arxiv.org/abs/2411.05222
Autor:
Liu, Sihan, Ye, Christopher
Uniformity testing is arguably one of the most fundamental distribution testing problems. Given sample access to an unknown distribution $\mathbf{p}$ on $[n]$, one must decide if $\mathbf{p}$ is uniform or $\varepsilon$-far from uniform (in total var
Externí odkaz:
http://arxiv.org/abs/2410.10892
Publikováno v:
"Testable Learning of General Halfspaces with Adversarial Label Noise." In The Thirty Seventh Annual Conference on Learning Theory, pp. 1308-1335. PMLR, 2024
We study the task of testable learning of general -- not necessarily homogeneous -- halfspaces with adversarial label noise with respect to the Gaussian distribution. In the testable learning framework, the goal is to develop a tester-learner such th
Externí odkaz:
http://arxiv.org/abs/2408.17165
The replicability crisis is a major issue across nearly all areas of empirical science, calling for the formal study of replicability in statistics. Motivated in this context, [Impagliazzo, Lei, Pitassi, and Sorrell STOC 2022] introduced the notion o
Externí odkaz:
http://arxiv.org/abs/2406.02628
We study the sample complexity of the classical shadows task: what is the fewest number of copies of an unknown state you need to measure to predict expected values with respect to some class of observables? Large joint measurements are likely requir
Externí odkaz:
http://arxiv.org/abs/2405.09525
We study the efficient learnability of low-degree polynomial threshold functions (PTFs) in the presence of a constant fraction of adversarial corruptions. Our main algorithmic result is a polynomial-time PAC learning algorithm for this concept class
Externí odkaz:
http://arxiv.org/abs/2404.00529
Autor:
Liu, Sihan, Ma, Yiwei, Zhang, Xiaoqing, Wang, Haowei, Ji, Jiayi, Sun, Xiaoshuai, Ji, Rongrong
Referring Remote Sensing Image Segmentation (RRSIS) is a new challenge that combines computer vision and natural language processing, delineating specific regions in aerial images as described by textual queries. Traditional Referring Image Segmentat
Externí odkaz:
http://arxiv.org/abs/2312.12470
We investigate the statistical task of closeness (or equivalence) testing for multidimensional distributions. Specifically, given sample access to two unknown distributions $\mathbf p, \mathbf q$ on $\mathbb R^d$, we want to distinguish between the c
Externí odkaz:
http://arxiv.org/abs/2311.13154
We study the problem of high-dimensional robust mean estimation in an online setting. Specifically, we consider a scenario where $n$ sensors are measuring some common, ongoing phenomenon. At each time step $t=1,2,\ldots,T$, the $i^{th}$ sensor report
Externí odkaz:
http://arxiv.org/abs/2310.15932