English
Related papers

Related papers: Beyond the Ideal: Analyzing the Inexact Muon Updat…

200 papers

We present a novel framework addressing a critical vulnerability in Large Language Models (LLMs): the prevalence of factual inaccuracies within intermediate reasoning steps despite correct final answers. This phenomenon poses substantial…

Computation and Language · Computer Science 2025-08-05 Rui Jiao , Yue Zhang , Jinku Li

In this paper we analyze several inexact fast augmented Lagrangian methods for solving linearly constrained convex optimization problems. Mainly, our methods rely on the combination of excessive-gap-like smoothing technique developed in…

Optimization and Control · Mathematics 2015-05-14 Andrei Patrascu , Ion Necoara , Quoc Tran-Dinh

Integration of artificial intelligence (AI) and machine learning (ML) into the air interface has been envisioned as a key technology for next-generation (NextG) cellular networks. At the air interface, multiple-input multiple-output (MIMO)…

Signal Processing · Electrical Eng. & Systems 2024-03-06 Jiarui Xu , Shashank Jere , Yifei Song , Yi-Hung Kao , Lizhong Zheng , Lingjia Liu

Offline reinforcement learning (RL) can fail spectacularly when bootstrapped temporal-difference (TD) updates amplify their own errors, driving the critic toward extreme and unusable Q-values. A key counterintuitive insight of this work is…

Machine Learning · Computer Science 2026-05-05 Nan Qiao , Sheng Yue , Shuning Wang , Ju Ren

Learning to optimize (L2O) has gained increasing attention since classical optimizers require laborious problem-specific design and hyperparameter tuning. However, there is a gap between the practical demand and the achievable performance…

Machine Learning · Computer Science 2020-10-20 Tianlong Chen , Weiyi Zhang , Jingyang Zhou , Shiyu Chang , Sijia Liu , Lisa Amini , Zhangyang Wang

Large language models (LLMs) have demonstrated impressive generalization and emergent capabilities, yet their pre-training remains computationally expensive and sensitive to optimization dynamics. While Adam-based optimizers offer fast…

Machine Learning · Computer Science 2025-10-01 Junjie Wang , Pan Zhou , Yiming Dong , Huan Li , Jia Li , Xun Zhou , Qicheng Lao , Cong Fang , Zhouchen Lin

The study of approximate matching in the Massively Parallel Computations (MPC) model has recently seen a burst of breakthroughs. Despite this progress, however, we still have a far more limited understanding of maximal matching which is one…

Data Structures and Algorithms · Computer Science 2023-10-17 Soheil Behnezhad , MohammadTaghi Hajiaghayi , David G. Harris

Learning to perform perfect tracking tasks based on measurement data is desirable in the controller design of systems operating repetitively. This motivates the present paper to seek an optimization-based design approach for iterative…

Systems and Control · Electrical Eng. & Systems 2019-08-08 Deyuan Meng , Jingyao Zhang

Imitation learning holds tremendous promise in learning policies efficiently for complex decision making problems. Current state-of-the-art algorithms often use inverse reinforcement learning (IRL), where given a set of expert…

Robotics · Computer Science 2023-02-22 Siddhant Haldar , Vaibhav Mathur , Denis Yarats , Lerrel Pinto

Modern adaptive optimization methods, such as Adam and its variants, have emerged as the most widely used tools in deep learning over recent years. These algorithms offer automatic mechanisms for dynamically adjusting the update step based…

Machine Learning · Computer Science 2025-02-12 Son Nguyen , Bo Liu , Lizhang Chen , Qiang Liu

Multimarginal optimal transport (MOT) is a powerful framework for modeling interactions between multiple distributions, yet its applicability is bottlenecked by a high computational overhead. Entropic regularization provides computational…

Machine Learning · Computer Science 2025-06-03 Dor Tsur , Ziv Goldfeld , Kristjan Greenewald , Haim Permuter

We study clustered multitask learning in a semiparametric setting where tasks share a latent cluster structure in their target parameters but exhibit heterogeneous, potentially infinite-dimensional nuisance components. Such heterogeneity…

Machine Learning · Statistics 2026-05-05 Hanxiao Chen , Debarghya Mukherjee

Supervised Fine-Tuning (SFT) Large Language Models (LLM) fundamentally rely on high-quality training data. While data selection and data synthesis are two common strategies to improve data quality, existing approaches often face limitations…

Computation and Language · Computer Science 2025-10-23 Zinan Tang , Xin Gao , Qizhi Pei , Zhuoshi Pan , Mengzhang Cai , Jiang Wu , Conghui He , Lijun Wu

Derivative-free optimization (DFO) problems are optimization problems where derivative information is unavailable or extremely difficult to obtain. Model-based DFO solvers have been applied extensively in scientific computing. Powell's…

Optimization and Control · Mathematics 2025-04-07 Pengcheng Xie , Stefan M. Wild

In recent years, numerous vision and learning tasks have been (re)formulated as nonconvex and nonsmooth programmings(NNPs). Although some algorithms have been proposed for particular problems, designing fast and flexible optimization…

Computer Vision and Pattern Recognition · Computer Science 2017-07-03 Yiyang Wang , Risheng Liu , Xiaoliang Song , Zhixun Su

Learning to Optimize (L2O), a technique that utilizes machine learning to learn an optimization algorithm automatically from data, has gained arising attention in recent years. A generic L2O approach parameterizes the iterative update rule…

Machine Learning · Computer Science 2023-05-31 Jialin Liu , Xiaohan Chen , Zhangyang Wang , Wotao Yin , HanQin Cai

Large-scale nonsmooth optimization problems arise in many real-world applications, but obtaining exact function and subgradient values for these problems may be computationally expensive or even infeasible. In many practical settings, only…

Optimization and Control · Mathematics 2026-04-10 Jenni Lampainen , Kaisa Joki , Napsu Karmitsa , Marko M. Mäkelä

Alignment-based conformance checking is the state-of-the-art approach for comparing observed process executions with normative process models. The standard exact solution relies on an A*-based heuristic search, which can exhibit exponential…

Artificial Intelligence · Computer Science 2026-05-27 Izack Cohen

We propose an inexact proximal augmented Lagrangian framework with explicit inner problem termination rule for composite convex optimization problems. We consider arbitrary linearly convergent inner solver including in particular stochastic…

Optimization and Control · Mathematics 2019-09-23 Fei Li , Zheng Qu

We study the compute-optimal trade-off between model and training data set sizes for large neural networks. Our result suggests a linear relation similar to that supported by the empirical analysis of chinchilla. While that work studies…

Machine Learning · Computer Science 2023-10-20 Hong Jun Jeon , Benjamin Van Roy