English
Related papers

Related papers: Adaptive Open-Loop Step-Sizes for Accelerated Conv…

200 papers

In neural network training, RMSProp and Adam remain widely favoured optimisation algorithms. One of the keys to their performance lies in selecting the correct step size, which can significantly influence their effectiveness. Additionally,…

Machine Learning · Computer Science 2024-04-05 Alokendu Mazumder , Rishabh Sabharwal , Manan Tayal , Bhartendu Kumar , Punit Rathore

Gradient descent and stochastic gradient descent are central to modern machine learning, yet their behavior under large step sizes remains theoretically unclear. Recent work suggests that acceleration often arises near the edge of…

Machine Learning · Computer Science 2026-03-02 Sacchit Kale , Piyushi Manupriya , Pierre Marion , Francis Bach , Anant Raj

We propose an accelerated block proximal linear framework with adaptive momentum (ABPL$^+$) for nonconvex and nonsmooth optimization. We analyze the potential causes of the extrapolation step failing in some algorithms, and resolve this…

Optimization and Control · Mathematics 2023-08-25 Weifeng Yang , Wenwen Min

This paper considers distributed stochastic optimization, in which a number of agents cooperate to optimize a global objective function through local computations and information exchanges with neighbors over a network. Stochastic…

Optimization and Control · Mathematics 2022-08-09 Jie Hou , Xianlin Zeng , Gang Wang , Jian Sun , Jie Chen

We study Frank-Wolfe methods for nonconvex stochastic and finite-sum optimization problems. Frank-Wolfe methods (in the convex case) have gained tremendous recent interest in machine learning and optimization communities due to their…

Optimization and Control · Mathematics 2016-08-01 Sashank J. Reddi , Suvrit Sra , Barnabas Poczos , Alex Smola

Despite the great success in Natural Language Processing (NLP) area, large pre-trained language models like BERT are not well-suited for resource-constrained or real-time applications owing to the large number of parameters and slow…

Computation and Language · Computer Science 2021-07-02 Keli Xie , Siyuan Lu , Meiqi Wang , Zhongfeng Wang

We address a large-scale and nonconvex optimization problem, involving an aggregative term. This term can be interpreted as the sum of the contributions of N agents to some common good, with N large. We investigate a relaxation of this…

Optimization and Control · Mathematics 2023-06-19 J. Frédéric Bonnans , Kang Liu , Nadia Oudjane , Laurent Pfeiffer , Cheng Wan

We present a new step-size strategy based on the secant method for Frank-Wolfe algorithms. This strategy, which requires mild assumptions about the function under consideration, can be applied to any Frank-Wolfe algorithm. It is as…

Optimization and Control · Mathematics 2025-06-11 Deborah Hendrych , Mathieu Besançon , David Martínez-Rubio , Sebastian Pokutta

We investigate the Randomized Stochastic Accelerated Gradient (RSAG) method, utilizing either constant or adaptive step sizes, for stochastic optimization problems with generalized smooth objective functions. Under relaxed affine variance…

Optimization and Control · Mathematics 2025-02-25 Chenhao Yu , Yusu Hong , Junhong Lin

The "Inertial Forward-Backward algorithm" (IFB) is a powerful tool for convex nonsmooth minimization problems, it gives the well known "fast iterative shrinkage-thresholding algorithm " (FISTA), which enjoys $O\left( {\frac{1}{{{k^2}}}}…

Optimization and Control · Mathematics 2022-02-25 Hongwei Liu , Ting Wang , Zexian Liu

The Conditional Gradient (or Frank-Wolfe) method is one of the most well-known methods for solving constrained optimization problems appearing in various machine learning tasks. The simplicity of iteration and applicability to many…

Optimization and Control · Mathematics 2024-09-17 Ruslan Nazykov , Aleksandr Shestakov , Vladimir Solodkin , Aleksandr Beznosikov , Gauthier Gidel , Alexander Gasnikov

Learning representation from relative similarity comparisons, often called ordinal embedding, gains rising attention in recent years. Most of the existing methods are based on semi-definite programming (\textit{SDP}), which is generally…

Machine Learning · Computer Science 2019-12-03 Ke Ma , Jinshan Zeng , Qianqian Xu , Xiaochun Cao , Wei Liu , Yuan Yao

In this paper, we revisit the convergence of the Heavy-ball method, and present improved convergence complexity results in the convex setting. We provide the first non-ergodic O(1/k) rate result of the Heavy-ball algorithm with constant…

Optimization and Control · Mathematics 2018-11-12 Tao Sun , Penghang Yin , Dongsheng Li , Chun Huang , Lei Guan , Hao Jiang

We consider convex optimization problems which are widely used as convex relaxations for low-rank matrix recovery problems. In particular, in several important problems, such as phase retrieval and robust PCA, the underlying assumption in…

Optimization and Control · Mathematics 2022-06-22 Dan Garber

We propose a randomized multiplicative weight update (MWU) algorithm for $\ell_{\infty}$ regression that runs in $\widetilde{O}\left(n^{2+1/22.5} \text{poly}(1/\epsilon)\right)$ time when $\omega = 2+o(1)$, improving upon the previous best…

Data Structures and Algorithms · Computer Science 2025-04-29 Deeksha Adil , Shunhua Jiang , Rasmus Kyng

It is known in \cite{beccari} that the standard explicit Euler-type scheme (such as the exponential Euler and the linear-implicit Euler schemes) with a uniform timestep, though computationally efficient, may diverge for the stochastic…

Numerical Analysis · Mathematics 2023-11-14 Chuchu Chen , Tonghe Dang , Jialin Hong

Recently the away-step Frank-Wolfe algoritm for constrained multiobjective optimization has been shown linear convergence rate over a polytope which is generated by finite points set. In this paper we design a decomposition-invariant…

Optimization and Control · Mathematics 2024-09-10 Zhuoxin Fan , Liping Tang

The low-rank adaptation (LoRA) algorithm for fine-tuning large models has grown popular in recent years due to its remarkable performance and low computational requirements. LoRA trains two ``adapter" matrices that form a low-rank…

Machine Learning · Computer Science 2026-05-12 Siqiao Mu , Diego Klabjan

This paper proves an impossibility result for stochastic network utility maximization for multi-user wireless systems, including multiple access and broadcast systems. Every time slot an access point observes the current channel states for…

Optimization and Control · Mathematics 2020-03-18 Michael J. Neely

Practitioners of Markov chain Monte Carlo (MCMC) may hesitate to use random walk Metropolis-Hastings algorithms, especially variable-at-a-time algorithms with many parameters, because these algorithms require users to select values of…

Computation · Statistics 2011-03-31 Todd L. Graves