English
Related papers

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

200 papers

We investigate the convergence properties of a class of iterative algorithms designed to minimize a potentially non-smooth and noisy objective function, which may be algebraically intractable and whose values may be obtained as the output…

Computation · Statistics 2025-12-04 Christophe Andrieu , Nicolas Chopin , Ettore Fincato , Mathieu Gerber

Conventional wisdom in deep learning states that increasing depth improves expressiveness but complicates optimization. This paper suggests that, sometimes, increasing depth can speed up optimization. The effect of depth on optimization is…

Machine Learning · Computer Science 2018-06-12 Sanjeev Arora , Nadav Cohen , Elad Hazan

We study the oracle complexity of nonsmooth nonconvex optimization, with the algorithm assumed to have access only to local function information. It has been shown by Davis, Drusvyatskiy, and Jiang (2023) that for nonsmooth Lipschitz…

Optimization and Control · Mathematics 2024-09-17 Guy Kornowski , Swati Padmanabhan , Ohad Shamir

Neural networks trained with standard objectives exhibit behaviors characteristic of probabilistic inference: soft clustering, prototype specialization, and Bayesian uncertainty tracking. These phenomena appear across architectures -- in…

Machine Learning · Computer Science 2026-01-01 Alan Oursland

In this paper, we introduce some new hybrid algorithms for finding a solution of a system of equilibrium problems. In these algorithms, by constructing specially cutting-halfspaces, we avoid using the extra-steps as in the extragradient…

Optimization and Control · Mathematics 2015-10-29 Dang Van Hieu

We present an approach to obtain convergence guarantees of optimization algorithms for deep networks based on elementary arguments and computations. The convergence analysis revolves around the analytical and computational structures of…

Machine Learning · Computer Science 2021-01-01 Vincent Roulet , Zaid Harchaoui

Monotonicity and nonmonotonicity play a key role in studying the global convergence and the efficiency of iterative schemes employed in the field of nonlinear optimization, where globally convergent and computationally efficient schemes are…

Optimization and Control · Mathematics 2014-08-21 Masoud Ahookhosh , Susan Ghaderi

We study a class of algorithms for solving bilevel optimization problems in both stochastic and deterministic settings when the inner-level objective is strongly convex. Specifically, we consider algorithms based on inexact implicit…

Optimization and Control · Mathematics 2022-07-12 Michael Arbel , Julien Mairal

Lanczos-type algorithms are efficient and easy to implement. Unfortunately they breakdown frequently and well before convergence has been achieved. These algorithms are typically based on recurrence relations which involve formal orthogonal…

Numerical Analysis · Mathematics 2015-05-28 Muhammad Farooq , Abdellah Salhi

Large language models (LLMs) have made fundamental contributions over the last a few years. To train an LLM, one needs to alternatingly run `forward' computations and `backward' computations. The forward computation can be viewed as…

Machine Learning · Computer Science 2024-02-08 Josh Alman , Zhao Song

Rapid advances in data collection and processing capabilities have allowed for the use of increasingly complex models that give rise to nonconvex optimization problems. These formulations, however, can be arbitrarily difficult to solve in…

Multiagent Systems · Computer Science 2020-04-01 Stefan Vlaski , Ali H. Sayed

In this paper, we consider two formulations for Linear Matrix Inequalities (LMIs) under Slater type constraint qualification assumption, namely, SDP smooth and non-smooth formulations. We also propose two first-order linearly convergent…

Optimization and Control · Mathematics 2013-09-10 Cong D. Dang , Guanghui Lan

There is a significant gap between our theoretical understanding of optimization algorithms used in deep learning and their practical performance. Theoretical development usually focuses on proving convergence guarantees under a variety of…

Machine Learning · Computer Science 2025-11-03 Hoang Tran , Qinzi Zhang , Ashok Cutkosky

The paper presents a new descent algorithm for locally Lipschitz continuous functions $f:X\to\mathbb{R}$. The selection of a descent direction at some iteration point $x$ combines an approximation of the set-valued gradient of $f$ on a…

Numerical Analysis · Mathematics 2019-10-25 Jan Mankau , Friedemann Schuricht

Recently, Arjevani et al. [1] established a lower bound of iteration complexity for the first-order optimization under an $L$-smooth condition and a bounded noise variance assumption. However, a thorough review of existing literature on…

Machine Learning · Computer Science 2023-10-30 Bohan Wang , Jingwen Fu , Huishuai Zhang , Nanning Zheng , Wei Chen

In this paper some adaptive mirror descent algorithms for problems of minimization convex objective functional with several convex Lipschitz (generally, non-smooth) functional constraints are considered. It is shown that the methods are…

Optimization and Control · Mathematics 2018-12-20 F. S. Stonyakin , M . S. Alkousa , A. A. Titov

Recent empirical work has revealed an intriguing property of deep learning models by which the sharpness (largest eigenvalue of the Hessian) increases throughout optimization until it stabilizes around a critical value at which the…

Machine Learning · Computer Science 2024-01-02 Vincent Roulet , Atish Agarwala , Fabian Pedregosa

This article provides a comprehensive understanding of optimization in deep learning, with a primary focus on the challenges of gradient vanishing and gradient exploding, which normally lead to diminished model representational ability and…

Machine Learning · Computer Science 2023-11-14 Xianbiao Qi , Jianan Wang , Lei Zhang

An Adagrad-inspired class of algorithms for smooth unconstrained optimization is presented in which the objective function is never evaluated and yet the gradient norms decrease at least as fast as $\calO(1/\sqrt{k+1})$ while second-order…

Optimization and Control · Mathematics 2023-02-16 S. Gratton , Ph. L. Toint

We study generalized smoothness in nonconvex optimization, focusing on $(L_0, L_1)$-smoothness and anisotropic smoothness. The former was empirically derived from practical neural network training examples, while the latter arises naturally…

Optimization and Control · Mathematics 2025-09-22 Alexander Bodard , Panagiotis Patrinos