English
Related papers

Related papers: Adaptive Gradient Methods Converge Faster with Ove…

200 papers

Large Language Models (LLMs) can perform many NLP tasks well, but fully fine-tuning them is expensive and requires a lot of memory. Parameter-Efficient Fine-Tuning (PEFT) methods such as LoRA reduce this cost by adding small low-rank…

Machine Learning · Computer Science 2025-12-19 Anshul Kumar , Gagan Raj Gupta , Manisha Chawla

We propose a new stochastic gradient method called MOTAPS (Moving Targetted Polyak Stepsize) that uses recorded past loss values to compute adaptive stepsizes. MOTAPS can be seen as a variant of the Stochastic Polyak (SP) which is also a…

Machine Learning · Computer Science 2021-09-27 Robert M. Gower , Aaron Defazio , Michael Rabbat

In the first part of the paper we consider accelerated first order optimization method for convex functions with $L$-Lipschitz-continuous gradient, that is able to automatically adapts to problems which satisfies Polyak-{\L}ojasiewicz…

Optimization and Control · Mathematics 2020-06-17 Nazarii Tupitsa

We consider the decentralized optimization problem, where a network of $n$ agents aims to collaboratively minimize the average of their individual smooth and convex objective functions through peer-to-peer communication in a directed graph.…

Optimization and Control · Mathematics 2023-12-07 Zhuoqing Song , Lei Shi , Shi Pu , Ming Yan

Generating adversarial examples (AEs) can be formulated as an optimization problem. Among various optimization-based attacks, the gradient-based PGD and the momentum-based MI-FGSM have garnered considerable interest. However, all these…

Machine Learning · Computer Science 2025-12-17 Wei Tao , Sheng Long , Xin Liu , Wei Li , Qing Tao

We introduce a general method for improving the convergence rate of gradient-based optimizers that is easy to implement and works well in practice. We demonstrate the effectiveness of the method in a range of optimization problems by…

Machine Learning · Computer Science 2018-08-23 Atilim Gunes Baydin , Robert Cornish , David Martinez Rubio , Mark Schmidt , Frank Wood

We analyze the learning properties of the stochastic gradient method when multiple passes over the data and mini-batches are allowed. We study how regularization properties are controlled by the step-size, the number of passes and the…

Machine Learning · Computer Science 2019-03-18 Junhong Lin , Lorenzo Rosasco

We implement the adaptive step size scheme from the optimization methods AdaGrad and Adam in a novel variant of the Proximal Gradient Method (PGM). Our algorithm, dubbed AdaProx, avoids the need for explicit computation of the Lipschitz…

Optimization and Control · Mathematics 2020-07-06 Peter Melchior , Rémy Joseph , Fred Moolekamp

We study the convergence of the last iterate (i.e., the $(N+1)$-th iterate) of the AdaGrad method. Although AdaGrad -- an adaptive subgradient method -- underpins a wide class of algorithms, most existing convergence analyses focus on…

Optimization and Control · Mathematics 2026-04-14 Margarita Preobrazhenskaia , Makar Sidorov , Igor Preobrazhenskii , Eduard Gorbunov

In this paper, we propose an adaptive step size strategy for a class of line search methods for orthogonality constrained minimization problems, which avoids the classic backtracking procedure. We prove the convergence of the line search…

Optimization and Control · Mathematics 2020-02-21 Xiaoying Dai , Liwei Zhang , Aihui Zhou

In this paper we aim to formally explain the phenomenon of fast convergence of SGD observed in modern machine learning. The key observation is that most modern learning architectures are over-parametrized and are trained to interpolate the…

Machine Learning · Computer Science 2018-06-18 Siyuan Ma , Raef Bassily , Mikhail Belkin

Backtracking line-search is an old yet powerful strategy for finding a better step sizes to be used in proximal gradient algorithms. The main principle is to locally find a simple convex upper bound of the objective function, which in turn…

Optimization and Control · Mathematics 2019-11-06 Mahesh Chandra Mukkamala , Peter Ochs , Thomas Pock , Shoham Sabach

We develop model-based methods for solving stochastic convex optimization problems, introducing the approximate-proximal point, or aProx, family, which includes stochastic subgradient, proximal point, and bundle methods. When the modeling…

Optimization and Control · Mathematics 2019-09-20 Hilal Asi , John C. Duchi

Recently Grimmer [1] showed for smooth convex optimization by utilizing longer steps periodically, gradient descent's textbook $LD^2/2T$ convergence guarantees can be improved by constant factors, conjecturing an accelerated rate strictly…

Optimization and Control · Mathematics 2023-09-28 Benjamin Grimmer , Kevin Shu , Alex L. Wang

In non-private stochastic convex optimization, stochastic gradient methods converge much faster on interpolation problems -- problems where there exists a solution that simultaneously minimizes all of the sample losses -- than on…

Machine Learning · Computer Science 2022-11-01 Hilal Asi , Karan Chadha , Gary Cheng , John Duchi

In this work, we propose an adaptive variation on the classical Heavy-ball method for convex quadratic minimization. The adaptivity crucially relies on so-called "Polyak step-sizes", which consists in using the knowledge of the optimal…

Optimization and Control · Mathematics 2022-10-13 Baptiste Goujaud , Adrien Taylor , Aymeric Dieuleveut

Over-parameterization and adaptive methods have played a crucial role in the success of deep learning in the last decade. The widespread use of over-parameterization has forced us to rethink generalization by bringing forth new phenomena,…

Machine Learning · Statistics 2020-12-01 Vatsal Shah , Soumya Basu , Anastasios Kyrillidis , Sujay Sanghavi

In this paper, we propose a new, simplified high probability analysis of AdaGrad for smooth, non-convex problems. More specifically, we focus on a particular accelerated gradient (AGD) template (Lan, 2020), through which we recover the…

Optimization and Control · Mathematics 2022-04-07 Ali Kavis , Kfir Yehuda Levy , Volkan Cevher

We study convex optimization problems over a compact convex set where projections are expensive but a linear minimization oracle (LMO) is available. We propose the adaptive conditional gradient sliding method (AdCGS), a projection-free and…

Optimization and Control · Mathematics 2026-01-29 Shota Takahashi

We present a strikingly simple proof that two rules are sufficient to automate gradient descent: 1) don't increase the stepsize too fast and 2) don't overstep the local curvature. No need for functional values, no line search, no…

Optimization and Control · Mathematics 2020-08-18 Yura Malitsky , Konstantin Mishchenko