English
Related papers

Related papers: No learning rates needed: Introducing SALSA -- Sta…

200 papers

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

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

Recent work has established an empirically successful framework for adapting learning rates for stochastic gradient descent (SGD). This effectively removes all needs for tuning, while automatically reducing learning rates over time on…

Machine Learning · Computer Science 2013-03-28 Tom Schaul , Yann LeCun

Variance-reduced algorithms, although achieve great theoretical performance, can run slowly in practice due to the periodic gradient estimation with a large batch of data. Batch-size adaptation thus arises as a promising approach to…

Optimization and Control · Mathematics 2020-07-28 Kaiyi Ji , Zhe Wang , Bowen Weng , Yi Zhou , Wei Zhang , Yingbin Liang

We extend the convergence analysis of AdaSLS and AdaSPS in [Jiang and Stich, 2024] to the nonconvex setting, presenting a unified convergence analysis of stochastic gradient descent with adaptive Armijo line-search (AdaSLS) and Polyak…

Optimization and Control · Mathematics 2025-12-02 Haotian Wu

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

Stochastic non-convex non-concave optimization, formally characterized as Stochastic Variational Inequalities (SVIs), presents unique challenges due to rotational dynamics and the absence of a global merit function. While adaptive step-size…

Optimization and Control · Mathematics 2026-03-12 Yungi Jeong , Takumi Otsuka

In deterministic optimization, line searches are a standard tool ensuring stability and efficiency. Where only stochastic gradients are available, no direct equivalent has so far been formulated, because uncertain gradients do not allow for…

Machine Learning · Computer Science 2017-07-03 Maren Mahsereci , Philipp Hennig

In deterministic optimization, line searches are a standard tool ensuring stability and efficiency. Where only stochastic gradients are available, no direct equivalent has so far been formulated, because uncertain gradients do not allow for…

Machine Learning · Computer Science 2016-01-19 Maren Mahsereci , Philipp Hennig

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

We propose an online learning algorithm for a class of machine learning models under a separable stochastic approximation framework. The essence of our idea lies in the observation that certain parameters in the models are easier to…

Machine Learning · Computer Science 2023-05-23 Min Gan , Xiang-xiang Su , Guang-yong Chen , Jing Chen

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

Hyperparameter tuning is a bothersome step in the training of deep learning models. One of the most sensitive hyperparameters is the learning rate of the gradient descent. We present the 'All Learning Rates At Once' (Alrao) optimization…

Machine Learning · Computer Science 2019-01-30 Léonard Blier , Pierre Wolinski , Yann Ollivier

The classical line search for learning rate (LR) tuning in the stochastic gradient descent (SGD) algorithm can tame the convergence slowdown due to data-sampling noise. In a federated setting, wherein the client heterogeneity introduces a…

Machine Learning · Computer Science 2025-10-28 Geetika , Somya Tyagi , Bapi Chatterjee

In this paper we present a nonmonotone line search subgradient algorithm tailored to upper-$\mathcal{C}^2$ functions. This is a family of nonsmooth and nonconvex functions that satisfies a nonsmooth and local version of the descent lemma,…

Optimization and Control · Mathematics 2026-04-22 Francisco J. Aragón-Artacho , Rubén Campoy , Pedro Pérez-Aros , David Torregrosa-Belén

Line search (or backtracking) procedures have been widely employed into first-order methods for solving convex optimization problems, especially those with unknown problem parameters (e.g., Lipschitz constant). In this paper, we show that…

Optimization and Control · Mathematics 2024-08-20 Tianjiao Li , Guanghui Lan

We develop a first-order (pseudo-)gradient approach for optimizing functions over the stationary distribution of discrete-time Markov chains (DTMC). We give insights into why solving this optimization problem is challenging and show how…

Optimization and Control · Mathematics 2024-07-23 Nanne A. Dieleman , Joost Berkhout , Bernd Heidergott

The learning rate in stochastic gradient methods is a critical hyperparameter that is notoriously costly to tune via standard grid search, especially for training modern large-scale models with billions of parameters. We identify a…

Machine Learning · Computer Science 2026-02-17 Amit Attia , Tomer Koren

A fundamental challenge in Deep Learning is to find optimal step sizes for stochastic gradient descent automatically. In traditional optimization, line searches are a commonly used method to determine step sizes. One problem in Deep…

Machine Learning · Computer Science 2022-02-22 Maximus Mutschler , Kevin Laube , Andreas Zell

A common belief in model-free reinforcement learning is that methods based on random search in the parameter space of policies exhibit significantly worse sample complexity than those that explore the space of actions. We dispel such…

Machine Learning · Computer Science 2018-03-20 Horia Mania , Aurelia Guy , Benjamin Recht