10 papers
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…
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…
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…
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)…
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),…
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…