English
Related papers

Related papers: Universally Empowering Zeroth-Order Optimization v…

200 papers

Leveraging the rich world knowledge of Large Language Models (LLMs) to enhance Reinforcement Learning (RL) agents offers a promising path toward general intelligence. However, a fundamental prior-dynamics mismatch hinders existing…

Machine Learning · Computer Science 2026-05-13 Junyu Xiong , Yuan Pu , Jia Tang , Yazhe Niu

Training large language models (LLMs) relies on adaptive optimizers such as Adam, which introduce extra operations and require significantly more memory to maintain first- and second-order moments than SGD. While recent works such as…

Machine Learning · Computer Science 2026-05-22 Athanasios Glentis , Jiaxiang Li , Andi Han , Mingyi Hong

Deep neural networks often lack the safety and robustness guarantees needed to be deployed in safety critical systems. Formal verification techniques can be used to prove input-output safety properties of networks, but when properties are…

Machine Learning · Computer Science 2022-05-17 Christopher A. Strong , Sydney M. Katz , Anthony L. Corso , Mykel J. Kochenderfer

Offline reinforcement learning methods hold the promise of learning policies from pre-collected datasets without the need to query the environment for new transitions. This setting is particularly well-suited for continuous control robotic…

Machine Learning · Computer Science 2022-03-18 Xi Chen , Ali Ghadirzadeh , Tianhe Yu , Yuan Gao , Jianhao Wang , Wenzhe Li , Bin Liang , Chelsea Finn , Chongjie Zhang

Hard-thresholding is an important type of algorithm in machine learning that is used to solve $\ell_0$ constrained optimization problems. However, the true gradient of the objective function can be difficult to access in certain scenarios,…

Artificial Intelligence · Computer Science 2026-05-19 Xinzhe Yuan , William de Vazelhes , Bin Gu , Huan Xiong

Cross-device federated learning (FL) is a growing machine learning setting whereby multiple edge devices collaborate to train a model without disclosing their raw data. With the great number of mobile devices participating in more FL…

Machine Learning · Computer Science 2025-02-14 Elissa Mhanna , Mohamad Assaad

Existing multi-objective preference alignment methods for large language models (LLMs) face limitations: (1) the inability to effectively balance various preference dimensions, and (2) reliance on auxiliary reward/reference models…

Machine Learning · Computer Science 2025-06-10 Qi Liu , Jingqing Ruan , Hao Li , Haodong Zhao , Desheng Wang , Jiansong Chen , Wan Guanglu , Xunliang Cai , Zhi Zheng , Tong Xu

Reinforcement Learning (RL) post-training has emerged as the dominant paradigm for eliciting mathematical reasoning in Large Language Models (LLMs), yet prevailing techniques such as GRPO and DAPO distribute rollout and gradient budgets…

Machine Learning · Computer Science 2026-05-20 Peng Cui , Boyao Yang , Jun Zhu

Learning to Optimize (L2O) approaches, including algorithm unrolling, plug-and-play methods, and hyperparameter learning, have garnered significant attention and have been successfully applied to the Alternating Direction Method of…

Optimization and Control · Mathematics 2024-09-27 Ling Liang , Cameron Austin , Haizhao Yang

Gridless methods show great superiority in line spectral estimation. These methods need to solve an atomic $l_0$ norm (i.e., the continuous analog of $l_0$ norm) minimization problem to estimate frequencies and model order. Since this…

Optimization and Control · Mathematics 2024-10-28 Bai Yan , Qi Zhao , Jin Zhang , J. Andrew Zhang , Xin Yao

Multi-objective combinatorial optimization seeks Pareto-optimal solutions over exponentially large discrete spaces, yet existing methods sacrifice generality, scalability, or theoretical guarantees. We reformulate it as an online learning…

Machine Learning · Computer Science 2026-02-13 Esha Singh , Dongxia Wu , Chien-Yi Yang , Tajana Rosing , Rose Yu , Yi-An Ma

Distributed optimization is fundamental to modern machine learning applications like federated learning, but existing methods often struggle with ill-conditioned problems and face stability-versus-speed tradeoffs. We introduce fractional…

Machine Learning · Computer Science 2024-12-04 Andrei Lixandru , Marcel van Gerven , Sergio Pequito

Large language models (LLMs) are increasingly used for long-content generation (e.g., long Chain-of-Thought reasoning) where decoding efficiency becomes a critical bottleneck: Autoregressive decoding is inherently limited by its sequential…

Computation and Language · Computer Science 2025-06-05 Zhepei Wei , Wei-Lin Chen , Xinyu Zhu , Yu Meng

Most decentralized optimization algorithms are handcrafted. While endowed with strong theoretical guarantees, these algorithms generally target a broad class of problems, thereby not being adaptive or customized to specific problem…

Optimization and Control · Mathematics 2024-10-03 Yutong He , Qiulin Shang , Xinmeng Huang , Jialin Liu , Kun Yuan

Large language models (LLMs) are notoriously memory-intensive during training, particularly with the popular AdamW optimizer. This memory burden necessitates using more or higher-end GPUs or reducing batch sizes, limiting training…

Machine Learning · Computer Science 2025-02-18 Hanqing Zhu , Zhenyu Zhang , Wenyan Cong , Xi Liu , Sem Park , Vikas Chandra , Bo Long , David Z. Pan , Zhangyang Wang , Jinwon Lee

Large Language Models (LLMs) demonstrate robust capabilities across various fields, leading to a paradigm shift in LLM-enhanced Recommender System (RS). Research to date focuses on point-wise and pair-wise recommendation paradigms, which…

Information Retrieval · Computer Science 2024-09-30 Wen-Shuo Chao , Zhi Zheng , Hengshu Zhu , Hao Liu

Large Vision-Language Models (LVLMs), such as GPT-4o and LLaVA, have recently witnessed remarkable advancements and are increasingly being deployed in real-world applications. However, inheriting the sensitivity of visual neural networks,…

Computer Vision and Pattern Recognition · Computer Science 2025-04-03 Chaohu Liu , Tianyi Gui , Yu Liu , Linli Xu

The composition of pretraining data is a key determinant of foundation models' performance, but there is no standard guideline for allocating a limited computational budget across different data sources. Most current approaches either rely…

Machine Learning · Computer Science 2024-10-16 Yiding Jiang , Allan Zhou , Zhili Feng , Sadhika Malladi , J. Zico Kolter

The rapid advancements in Large Language Models (LLMs) have revolutionized various natural language processing tasks. However, the substantial size of LLMs presents significant challenges in training or fine-tuning. While…

Machine Learning · Computer Science 2025-06-10 Pengxiang Li , Lu Yin , Xiaowei Gao , Shiwei Liu

In this paper, we focus on solving an important class of nonconvex optimization problems which includes many problems for example signal processing over a networked multi-agent system and distributed learning over networks. Motivated by…

Optimization and Control · Mathematics 2018-10-25 Ehsan Kazemi , Liqiang Wang