7 citations · 25 across the 24 of their papers we have counts for
28 papers
Group Distributionally Robust Optimization over Decentralized Networks
Haomin Bai, Junyan Sun, Quan Cheng +2
We study group distributionally robust optimization (GDRO) over decentralized networks, where workers collaborate to learn robust models by minimizing the maximum local risk. Exist…
Efficient Preconditioned Optimization Methods with Frequent Directions
Sifan Yang, Yuanyu Wan, Yibo Wang +1
Adaptive optimization methods have received considerable attention in recent years due to their strong empirical performance. However, they generally require maintaining a precondi…
Dimension-Free Decentralized Nonsmooth Nonconvex Stochastic Optimization
Yuanyu Wan, Lan Xue, Haomin Bai +2
We investigate decentralized nonsmooth nonconvex stochastic optimization over a network of nodes, with the goal of finding an -Goldstein stationary point. The best exist…
From Switching to Dynamic Regret: A Simple Reduction via Unbiased Random Sequences
Yibo Wang, Wenhao Yang, Sifan Yang +3
In non-stationary online learning, dynamic regret has attracted increasing attention as a measure of how well an online learner performs against a time-varying comparator sequence.…
Revisiting Decentralized Online Convex Optimization with Compressed Communication
Hao Zhou, Xiaoyu Wang, Chang Yao +2
Decentralized online convex optimization (D-OCO) is a popular framework for distributed applications with streaming data. To tackle the communication bottleneck, previous studies h…
Improved Approximate Regret for Decentralized Online Continuous Submodular Maximization via Reductions
Yuanyu Wan, Yu Shen, Dingzhi Yu +2
To expand the applicability of decentralized online learning, previous studies have proposed several algorithms for decentralized online continuous submodular maximization (D-OCSM)…
Sign-Based Optimizers Are Effective Under Heavy-Tailed Noise
Dingzhi Yu, Hongyi Tao, Yuanyu Wan +2
While adaptive gradient methods are the workhorse of modern machine learning, sign-based optimization algorithms such as Lion and Muon have recently demonstrated superior empirical…
Deep But Reliable: Advancing Multi-turn Reasoning for Thinking with Images
Wenhao Yang, Yu Xia, Jinlong Huang +7
Recent advances in large Vision-Language Models (VLMs) have exhibited strong reasoning capabilities on complex visual tasks by thinking with images in their Chain-of-Thought (CoT),…
Online Nonsubmodular Optimization with Delayed Feedback in the Bandit Setting
Sifan Yang, Yuanyu Wan, Lijun Zhang
We investigate the online nonsubmodular optimization with delayed feedback in the bandit setting, where the loss function is -weakly DR-submodular and -weakly DR-supermodular…
Continuous Subspace Optimization for Continual Learning
Quan Cheng, Yuanyu Wan, Lingyu Wu +2
Continual learning aims to learn multiple tasks sequentially while preserving prior knowledge, but faces the challenge of catastrophic forgetting when adapting to new tasks. Recent…
Mirror Descent Under Generalized Smoothness
Dingzhi Yu, Wei Jiang, Hongyi Tao +2
Smoothness is crucial for attaining fast rates in first-order optimization. However, many optimization problems in modern machine learning involve non-smooth objectives. Recent stu…
Revisiting Projection-Free Online Learning with Time-Varying Constraints
Yibo Wang, Yuanyu Wan, Lijun Zhang
We investigate constrained online convex optimization, in which decisions must belong to a fixed and typically complicated domain, and are required to approximately satisfy additio…
Projection-Free Variance Reduction Methods for Stochastic Constrained Multi-Level Compositional Optimization
Wei Jiang, Sifan Yang, Wenhao Yang +3
This paper investigates projection-free algorithms for stochastic constrained multi-level optimization. In this context, the objective function is a nested composition of several s…
Optimal and Efficient Algorithms for Decentralized Online Convex Optimization
Yuanyu Wan, Tong Wei, Bo Xue +2
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 comp…
Improved Regret for Bandit Convex Optimization with Delayed Feedback
Yuanyu Wan, Chang Yao, Mingli Song +1
We investigate bandit convex optimization (BCO) with delayed feedback, where only the loss value of the action is revealed under an arbitrary delay. Let denote the di…
Efficient Algorithms for Generalized Linear Bandits with Heavy-tailed Rewards
Bo Xue, Yimu Wang, Yuanyu Wan +2
This paper investigates the problem of generalized linear bandits with heavy-tailed rewards, whose -th moment is bounded for some . Although there exist methods…
Adversarial Erasing with Pruned Elements: Towards Better Graph Lottery Ticket
Yuwen Wang, Shunyu Liu, Kaixuan Chen +5
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…
Improved Projection-free Online Continuous Submodular Maximization
Yucheng Liao, Yuanyu Wan, Chang Yao +1
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 p…
Non-stationary Projection-free Online Learning with Dynamic and Adaptive Regret Guarantees
Yibo Wang, Wenhao Yang, Wei Jiang +5
Projection-free online learning has drawn increasing interest due to its efficiency in solving high-dimensional problems with complicated constraints. However, most existing projec…
Non-stationary Delayed Online Convex Optimization: From Full-information to Bandit Setting
Yuanyu Wan, Chang Yao, Yitao Ma +2
Although online convex optimization (OCO) under arbitrary delays has received increasing attention recently, previous studies focus on stationary environments with the goal of mini…
Improved Dynamic Regret for Online Frank-Wolfe
Yuanyu Wan, Lijun Zhang, Mingli Song
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…
Projection-free Online Learning with Arbitrary Delays
Yuanyu Wan, Yibo Wang, Chang Yao +2
Projection-free online learning, which eschews the projection operation via less expensive computations such as linear optimization (LO), has received much interest recently due to…
Online Convex Optimization with Continuous Switching Constraint
Guanghui Wang, Yuanyu Wan, Tianbao Yang +1
In many sequential decision making applications, the change of decision would bring an additional cost, such as the wear-and-tear cost associated with changing server status. To co…
Online Strongly Convex Optimization with Unknown Delays
Yuanyu Wan, Wei-Wei Tu, Lijun Zhang
We investigate the problem of online convex optimization with unknown delays, in which the feedback of a decision arrives with an arbitrary delay. Previous studies have presented a…