Zobrazeno 1 - 10
of 3 857
pro vyhledávání: '"Jinhang"'
We study the problem of multi-agent multi-armed bandits with adversarial corruption in a heterogeneous setting, where each agent accesses a subset of arms. The adversary can corrupt the reward observations for all agents. Agents share these corrupted
Externí odkaz:
http://arxiv.org/abs/2411.08167
This paper investigates stochastic multi-armed bandit algorithms that are robust to adversarial attacks, where an attacker can first observe the learner's action and {then} alter their reward observation. We study two cases of this model, with or wit
Externí odkaz:
http://arxiv.org/abs/2408.08859
Autor:
Liu, Xutong, Wang, Siwei, Zuo, Jinhang, Zhong, Han, Wang, Xuchuang, Wang, Zhiyong, Li, Shuai, Hajiesmaili, Mohammad, Lui, John C. S., Chen, Wei
We introduce a novel framework of combinatorial multi-armed bandits (CMAB) with multivariant and probabilistically triggering arms (CMAB-MT), where the outcome of each arm is a $d$-dimensional multivariant random variable and the feedback follows a g
Externí odkaz:
http://arxiv.org/abs/2406.01386
Offline meta reinforcement learning (OMRL) has emerged as a promising approach for interaction avoidance and strong generalization performance by leveraging pre-collected data and meta-learning techniques. Previous context-based approaches predominan
Externí odkaz:
http://arxiv.org/abs/2405.12001
In the problem of quickest change detection (QCD), a change occurs at some unknown time in the distribution of a sequence of independent observations. This work studies a QCD problem where the change is either a bad change, which we aim to detect, or
Externí odkaz:
http://arxiv.org/abs/2405.00842
Foundation models (FMs) emerge as a promising solution to harness distributed and diverse environmental data by leveraging prior knowledge to understand the complicated temporal and spatial correlations within heterogeneous datasets. Unlike distribut
Externí odkaz:
http://arxiv.org/abs/2403.18451
Autor:
Chai, Jinhang, Fan, Jianqing
The problem of structured matrix estimation has been studied mostly under strong noise dependence assumptions. This paper considers a general framework of noisy low-rank-plus-sparse matrix recovery, where the noise matrix may come from any joint dist
Externí odkaz:
http://arxiv.org/abs/2401.02520
Autor:
Zuo, Jinhang, Zhang, Zhiyao, Wang, Xuchuang, Chen, Cheng, Li, Shuai, Lui, John C. S., Hajiesmaili, Mohammad, Wierman, Adam
Cooperative multi-agent multi-armed bandits (CMA2B) consider the collaborative efforts of multiple agents in a shared multi-armed bandit game. We study latent vulnerabilities exposed by this collaboration and consider adversarial attacks on a few age
Externí odkaz:
http://arxiv.org/abs/2311.01698
Autor:
Lu Yu, Jiawei Zou, Amjad Hussain, Ruoyu Jia, Yibo Fan, Jinhang Liu, Xinhui Nie, Xianlong Zhang, Shuangxia Jin
Publikováno v:
Genome Biology, Vol 25, Iss 1, Pp 1-26 (2024)
Abstract Background CRISPR/Cas13 system, recognized for its compact size and specificity in targeting RNA, is currently employed for RNA degradation. However, the potential of various CRISPR/Cas13 subtypes, particularly concerning the knockdown of en
Externí odkaz:
https://doaj.org/article/5db0cb26a63548938eaf6503b29e69ea
Publikováno v:
BMC Biology, Vol 22, Iss 1, Pp 1-16 (2024)
Abstract Drug repurposing is a promising approach in the field of drug discovery owing to its efficiency and cost-effectiveness. Most current drug repurposing models rely on specific datasets for training, which limits their predictive accuracy and s
Externí odkaz:
https://doaj.org/article/1a854e3ed4214e158d1b1cc7af65590d