English
Related papers

Related papers: Complexities of Armijo-like algorithms in Deep Lea…

200 papers

Both accelerated and adaptive gradient methods are among state of the art algorithms to train neural networks. The tuning of hyperparameters is needed to make them work efficiently. For classical gradient descent, a general and efficient…

Optimization and Control · Mathematics 2024-07-23 Bilel Bensaid , Gaël Poëtte , Rodolphe Turpault

In this paper, a new conjugate gradient-like algorithm is proposed to solve unconstrained optimization problems. The step directions generated by the new algorithm satisfy sufficient descent condition independent of the line search. The…

Optimization and Control · Mathematics 2021-05-11 Ahmad Kamandi , Keyvan Amini

Armijo line-search (Armijo-LS) is a standard method to set the step-size for gradient descent (GD). For smooth functions, Armijo-LS alleviates the need to know the global smoothness constant L and adapts to the ``local'' smoothness,…

Machine Learning · Computer Science 2026-02-25 Sharan Vaswani , Reza Babanezhad

Existing convergence guarantees for the mirror descent algorithm require the objective function to have a bounded gradient or be smooth relative to a Legendre function. The bounded gradient and relative smoothness conditions, however, may…

Optimization and Control · Mathematics 2018-06-01 Yen-Huan Li , Carlos A. Riofrio , Volkan Cevher

It is widely recognized in modern machine learning practice that access to a diverse set of tasks can enhance performance across those tasks. This observation suggests that, unlike in general multi-objective optimization, the objectives in…

Machine Learning · Computer Science 2025-09-09 Ben Kretzu , Karen Ullrich , Yonathan Efroni

The Conditional Gradient Method is generalized to a class of non-smooth non-convex optimization problems with many applications in machine learning. The proposed algorithm iterates by minimizing so-called model functions over the constraint…

Optimization and Control · Mathematics 2019-01-25 Yura Malitsky , Peter Ochs

There has been much recent interest in finding unconstrained local minima of smooth functions, due in part of the prevalence of such problems in machine learning and robust statistics. A particular focus is algorithms with good complexity…

Optimization and Control · Mathematics 2017-12-12 Clément W. Royer , Stephen J. Wright

Backtracking line search is foundational in numerical optimization. The basic idea is to adjust the step-size of an algorithm by a constant factor until some chosen criterion (e.g. Armijo, Descent Lemma) is satisfied. We propose a novel way…

Optimization and Control · Mathematics 2025-05-28 Joao V. Cavalcanti , Laurent Lessard , Ashia C. Wilson

In view of training increasingly complex learning architectures, we establish a nonsmooth implicit function theorem with an operational calculus. Our result applies to most practical problems (i.e., definable problems) provided that a…

Machine Learning · Computer Science 2022-04-06 Jérôme Bolte , Tam Le , Edouard Pauwels , Antonio Silveti-Falls

This paper discusses several (sub)gradient methods attaining the optimal complexity for smooth problems with Lipschitz continuous gradients, nonsmooth problems with bounded variation of subgradients, weakly smooth problems with H\"older…

Optimization and Control · Mathematics 2016-05-02 Masoud Ahookhosh

This paper provides the first tight convergence analyses for RMSProp and Adam in non-convex optimization under the most relaxed assumptions of coordinate-wise generalized smoothness and affine noise variance. We first analyze RMSProp, which…

Machine Learning · Statistics 2025-03-11 Qi Zhang , Yi Zhou , Shaofeng Zou

We present and analyse a backtracking strategy for a general Fast Iterative Shrinkage/Thresholding Algorithm which has been recently proposed in (Chambolle, Pock, 2016) for strongly convex objective functions. Differently from classical…

Optimization and Control · Mathematics 2019-01-04 Luca Calatroni , Antonin Chambolle

In this paper we propose several adaptive gradient methods for stochastic optimization. Unlike AdaGrad-type of methods, our algorithms are based on Armijo-type line search and they simultaneously adapt to the unknown Lipschitz constant of…

We study a class of optimization problems on Riemannian manifolds, where the objective function consists of a smooth term and quasi-norm type penalties with exponent $p \in (0, 1]$. The essential difficulty lies in the fact that the…

Optimization and Control · Mathematics 2026-04-21 Lei Wang , Xiaojun Chen

In this paper, we propose Riemannian conditional gradient methods for minimizing composite functions, i.e., those that can be expressed as the sum of a smooth function and a retraction-based convex function. We analyze the convergence of…

Optimization and Control · Mathematics 2026-05-19 Kangming Chen , Ellen H. Fukuda

Gradient-based minimax optimal algorithms have greatly promoted the development of continuous optimization and machine learning. One seminal work due to Yurii Nesterov [Nes83a] established $\tilde{\mathcal{O}}(\sqrt{L/\mu})$ gradient…

Machine Learning · Computer Science 2023-12-07 Yuanshi Liu , Hanzhen Zhao , Yang Xu , Pengyun Yue , Cong Fang

It has long been known that the gradient (steepest descent) method may fail on nonsmooth problems, but the examples that have appeared in the literature are either devised specifically to defeat a gradient or subgradient method with an…

Optimization and Control · Mathematics 2018-09-21 Azam Asl , Michael L. Overton

In this paper, we provide a rigorous proof of convergence of the Adaptive Moment Estimate (Adam) algorithm for a wide class of optimization objectives. Despite the popularity and efficiency of the Adam algorithm in training deep neural…

Optimization and Control · Mathematics 2023-11-08 Haochuan Li , Alexander Rakhlin , Ali Jadbabaie

In this paper, by combining the algorithm New Q-Newton's method - developed in previous joint work of the author - with Armijo's Backtracking line search, we resolve convergence issues encountered by Newton's method (e.g. convergence to a…

Optimization and Control · Mathematics 2022-09-13 Tuyen Trung Truong

The presence of non-convexity in smooth optimization problems arising from deep learning have sparked new smoothness conditions in the literature and corresponding convergence analyses. We discuss these smoothness conditions, order them,…

Machine Learning · Computer Science 2024-09-23 Vivak Patel , Christian Varner
‹ Prev 1 2 3 10 Next ›