Zobrazeno 1 - 10
of 42
pro vyhledávání: '"Wan, Yuanyu"'
Long-tailed semi-supervised learning poses a significant challenge in training models with limited labeled data exhibiting a long-tailed label distribution. Current state-of-the-art LTSSL approaches heavily rely on high-quality pseudo-labels for larg
Externí odkaz:
http://arxiv.org/abs/2410.06109
This paper investigates projection-free algorithms for stochastic constrained multi-level optimization. In this context, the objective function is a nested composition of several smooth functions, and the decision set is closed and convex. Existing p
Externí odkaz:
http://arxiv.org/abs/2406.03787
We investigate decentralized online convex optimization (D-OCO), in which a set of local learners are required to minimize a sequence of global loss functions using only local computations and communications. Previous studies have established $O(n^{5
Externí odkaz:
http://arxiv.org/abs/2402.09173
We investigate bandit convex optimization (BCO) with delayed feedback, where only the loss value of the action is revealed under an arbitrary delay. Let $n,T,\bar{d}$ denote the dimensionality, time horizon, and average delay, respectively. Previous
Externí odkaz:
http://arxiv.org/abs/2402.09152
This paper investigates the problem of generalized linear bandits with heavy-tailed rewards, whose $(1+\epsilon)$-th moment is bounded for some $\epsilon\in (0,1]$. Although there exist methods for generalized linear bandits, most of them focus on bo
Externí odkaz:
http://arxiv.org/abs/2310.18701
Autor:
Wang, Yuwen, Liu, Shunyu, Chen, Kaixuan, Zhu, Tongtian, Qiao, Ji, Shi, Mengjie, Wan, Yuanyu, Song, Mingli
Graph Lottery Ticket (GLT), a combination of core subgraph and sparse subnetwork, has been proposed to mitigate the computational cost of deep Graph Neural Networks (GNNs) on large input graphs while preserving original performance. However, the winn
Externí odkaz:
http://arxiv.org/abs/2308.02916
We investigate the problem of online learning with monotone and continuous DR-submodular reward functions, which has received great attention recently. To efficiently handle this problem, especially in the case with complicated decision sets, previou
Externí odkaz:
http://arxiv.org/abs/2305.18442
Online convex optimization (OCO) with arbitrary delays, in which gradients or other information of functions could be arbitrarily delayed, has received increasing attention recently. Different from previous studies that focus on stationary environmen
Externí odkaz:
http://arxiv.org/abs/2305.12131
Autor:
Wang, Yibo, Yang, Wenhao, Jiang, Wei, Lu, Shiyin, Wang, Bing, Tang, Haihong, Wan, Yuanyu, Zhang, Lijun
Projection-free online learning has drawn increasing interest due to its efficiency in solving high-dimensional problems with complicated constraints. However, most existing projection-free online methods focus on minimizing the static regret, which
Externí odkaz:
http://arxiv.org/abs/2305.11726
To deal with non-stationary online problems with complex constraints, we investigate the dynamic regret of online Frank-Wolfe (OFW), which is an efficient projection-free algorithm for online convex optimization. It is well-known that in the setting
Externí odkaz:
http://arxiv.org/abs/2302.05620