English
Related papers

Related papers: Parabolic Approximation Line Search for DNNs

200 papers

Adaptive gradient methods are typically used for training over-parameterized models. To better understand their behaviour, we study a simplistic setting -- smooth, convex losses with models over-parameterized enough to interpolate the data.…

Machine Learning · Computer Science 2021-02-22 Sharan Vaswani , Issam Laradji , Frederik Kunstner , Si Yi Meng , Mark Schmidt , Simon Lacoste-Julien

In deep learning tasks, the learning rate determines the update step size in each iteration, which plays a critical role in gradient-based optimization. However, the determination of the appropriate learning rate in practice typically…

Machine Learning · Statistics 2020-04-08 Yingqiu Zhu , Yu Chen , Danyang Huang , Bo Zhang , Hansheng Wang

Line-search methods are commonly used to solve optimization problems. The simplest line search method is steepest descent where one always moves in the direction of the negative gradient. Newton's method on the other hand is a second-order…

Optimization and Control · Mathematics 2025-08-15 Shikhar Saxena , Tejas Bodas , Arti Yardi

We study decentralized optimization over networks where agents cooperatively minimize a smooth (strongly) convex sum of local losses while communicating only with immediate neighbors. Prevailing decentralized methods require either…

Optimization and Control · Mathematics 2026-05-04 Xiaokai Chen , Ilya Kuruzov , Gesualdo Scutari

Recently, convergence as well as convergence rate analyses of deep learning optimizers for nonconvex optimization have been widely studied. Meanwhile, numerical evaluations for the optimizers have precisely clarified the relationship…

Optimization and Control · Mathematics 2021-08-27 Hideaki Iiduka

Line search is a fundamental part of iterative optimization methods for unconstrained and bound-constrained optimization problems to determine suitable step lengths that provide sufficient improvement in each iteration. Traditional line…

Optimization and Control · Mathematics 2025-07-22 Robin Labryga , Tomislav Prusina , Sören Laue

The training of deep neural networks is inherently a nonconvex optimization problem, yet standard approaches such as stochastic gradient descent (SGD) require simultaneous updates to all parameters, often leading to unstable convergence and…

Machine Learning · Computer Science 2025-08-07 Chengcheng Yan , Jiawei Xu , Zheng Peng , Qingsong Wang

The optimization foundations of deep linear networks have recently received significant attention. However, due to their inherent non-convexity and hierarchical structure, analyzing the loss functions of deep linear networks remains a…

Optimization and Control · Mathematics 2025-09-24 Po Chen , Rujun Jiang , Peng Wang

While stochastic gradient descent (SGD) can use various learning rates, such as constant or diminishing rates, the previous numerical results showed that SGD performs better than other deep learning optimizers using when it uses learning…

Machine Learning · Computer Science 2024-02-02 Yuki Tsukada , Hideaki Iiduka

A new stepsize for gradient method is proposed. Combining it with the exact line search stepsizes, the gradient method achieves the optimal solution in 5 steps for 3 dimensional quadratic function minimization problem. The new stepsize is…

Optimization and Control · Mathematics 2026-02-16 Yixin Xie , Jin-Peng Liu , Cong Sun , Ya-Xiang Yuan

We extend the well-known BFGS quasi-Newton method and its memory-limited variant LBFGS to the optimization of nonsmooth convex objectives. This is done in a rigorous fashion by generalizing three components of BFGS to subdifferentials: the…

Machine Learning · Statistics 2010-11-30 Jin Yu , S. V. N. Vishwanathan , Simon Guenter , Nicol N. Schraudolph

We propose approximately exact line search (AELS), which uses only function evaluations to select a step size within a constant fraction of the exact line search minimizer of a unimodal objective. We bound the number of iterations and…

Optimization and Control · Mathematics 2022-04-13 Sara Fridovich-Keil , Benjamin Recht

The popularity of bi-level optimization (BO) in deep learning has spurred a growing interest in studying gradient-based BO algorithms. However, existing algorithms involve two coupled learning rates that can be affected by approximation…

Machine Learning · Computer Science 2023-11-03 Chen Fan , Gaspard Choné-Ducasse , Mark Schmidt , Christos Thrampoulidis

In component shape optimization, the component properties are often evaluated by computationally expensive simulations. Such optimization becomes unfeasible when it is focused on a global search requiring thousands of simulations to be…

Computational Engineering, Finance, and Science · Computer Science 2025-12-08 Lucie Kubíčková , Onřej Gebouský , Jan Haidl , Martin Isoz

In this work, we deal with unconstrained nonlinear optimization problems. Specifically, we are interested in methods carrying out updates possibly along directions not of descent, like Polyak's heavy-ball algorithm. Instead of enforcing…

Optimization and Control · Mathematics 2025-05-27 Federica Donnini , Matteo Lapucci , Pierluigi Mansueto

The vulnerability of deep neural networks to small and even imperceptible perturbations has become a central topic in deep learning research. Although several sophisticated defense mechanisms have been introduced, most were later shown to…

Machine Learning · Computer Science 2021-09-28 Leo Schwinn , An Nguyen , René Raab , Dario Zanca , Bjoern Eskofier , Daniel Tenbrinck , Martin Burger

Dual descent methods are used to solve network optimization problems because descent directions can be computed in a distributed manner using information available either locally or at neighboring nodes. However, choosing a stepsize in the…

Optimization and Control · Mathematics 2012-03-14 Michael Zargham , Alejandro Ribeiro , Ali Jadbabaie

In this paper, we adopt a probability distribution estimation perspective to explore the optimization mechanisms of supervised classification using deep neural networks. We demonstrate that, when employing the Fenchel-Young loss, despite…

Machine Learning · Computer Science 2025-04-01 Binchuan Qi , Wei Gong , Li Li

We study stochastic optimization of nonconvex loss functions, which are typical objectives for training neural networks. We propose stochastic approximation algorithms which optimize a series of regularized, nonlinearized losses on large…

Machine Learning · Computer Science 2019-03-12 Weiran Wang , Nathan Srebro

We provide a detailed study on the implicit bias of gradient descent when optimizing loss functions with strictly monotone tails, such as the logistic loss, over separable datasets. We look at two basic questions: (a) what are the…