English
Related papers

Related papers: The Method of Infinite Descent

200 papers

We consider distributed optimization under communication constraints for training deep learning models. We propose a new algorithm, whose parameter updates rely on two forces: a regular gradient step, and a corrective direction dictated by…

Machine Learning · Computer Science 2022-04-29 Yunfei Teng , Wenbo Gao , Francois Chalus , Anna Choromanska , Donald Goldfarb , Adrian Weller

We analyze recurrent neural networks with diagonal hidden-to-hidden weight matrices, trained with gradient descent in the supervised learning setting, and prove that gradient descent can achieve optimality \emph{without} massive…

Machine Learning · Computer Science 2024-10-11 Semih Cayci , Atilla Eryilmaz

At the heart of Newton based optimization methods is a sequence of symmetric linear systems. Each consecutive system in this sequence is similar to the next, so solving them separately is a waste of computational effort. Here we describe…

Optimization and Control · Mathematics 2014-12-30 Robert Mansel Gower , Jacek Gondzio

While popular optimization methods such as SGD, AdamW, and Lion depend on steepest descent updates in either $\ell_2$ or $\ell_\infty$ norms, there remains a critical gap in handling the non-Euclidean structure observed in modern deep…

Machine Learning · Computer Science 2025-06-11 Xinyu Luo , Cedar Site Bai , Bolian Li , Petros Drineas , Ruqi Zhang , Brian Bullins

We provide several applications of Optimistic Mirror Descent, an online learning algorithm based on the idea of predictable sequences. First, we recover the Mirror Prox algorithm for offline optimization, prove an extension to Holder-smooth…

Machine Learning · Computer Science 2013-11-11 Alexander Rakhlin , Karthik Sridharan

Learn to Optimize (L2O) trains deep neural network-based solvers for optimization, achieving success in accelerating convex problems and improving non-convex solutions. However, L2O lacks rigorous theoretical backing for its own training…

Machine Learning · Computer Science 2025-12-24 Qingyu Song , Wei Lin , Hong Xu

In this paper we introduce a novel abstract descent scheme suited for the minimization of proper and lower semicontinuous functions. The proposed abstract scheme generalizes a set of properties that are crucial for the convergence of…

Numerical Analysis · Mathematics 2023-02-16 Silvia Bonettini , Peter Ochs , Marco Prato , Simone Rebegoldi

We consider the standard optimistic bilevel optimization problem, in particular upper- and lower-level constraints can be coupled. By means of the lower-level value function, the problem is transformed into a single-level optimization…

Optimization and Control · Mathematics 2019-12-17 Andreas Fischer , Alain B. Zemkoho , Shenglong Zhou

In this paper, we study a first order solution method for a particular class of set optimization problems where the solution concept is given by the set approach. We consider the case in which the set-valued objective mapping is identified…

Optimization and Control · Mathematics 2021-07-27 Gemayqzel Bouza , Ernest Quintana , Christiane Tammer

In this work, we provide a non-asymptotic convergence analysis of projected gradient descent for physics-informed neural networks for the Poisson equation. Under suitable assumptions, we show that the optimization error can be bounded by…

Optimization and Control · Mathematics 2025-05-13 Jonas Nießen , Johannes Müller

Recent progress in deep learning has been driven by increasingly larger models. However, their computational and energy demands have grown proportionally, creating significant barriers to their deployment and to a wider adoption of deep…

Machine Learning · Computer Science 2025-09-16 Pedro Savarese

Unrestricted mean-variance-skewness-kurtosis portfolio optimization can capture asymmetry and tail risk, but sample-moment formulations become computationally impractical when the asset universe is large: they produce dense nonconvex…

Portfolio Management · Quantitative Finance 2026-04-29 Ya-Juan Wang , Yi-Shuai Niu , Artan Sheshmani , Shing-Tung Yau

We describe inexact proximal Newton-like methods for solving degenerate regularized optimization problems and for the broader problem of finding a zero of a generalized equation that is the sum of a continuous map and a maximal monotone…

Optimization and Control · Mathematics 2026-02-12 Ching-pei Lee , Stephen J. Wright

Large-scale optimization problems require algorithms both effective and efficient. One such popular and proven algorithm is Stochastic Gradient Descent which uses first-order gradient information to solve these problems. This paper studies…

Optimization and Control · Mathematics 2021-11-11 Theodoros Mamalis , Dusan Stipanovic , Petros Voulgaris

A new type of stepsize, which was recently introduced by Liu and Liu (Optimization, 67(3), 427-440, 2018), is called approximately optimal stepsize and is quit efficient for gradient method. Interestingly, all gradient methods can be…

Optimization and Control · Mathematics 2019-07-25 Zexian Liu , Hongwei Liu

We present a new feasible proximal gradient method for constrained optimization where both the objective and constraint functions are given by the summation of a smooth, possibly nonconvex function and a convex simple function. The…

Optimization and Control · Mathematics 2024-02-01 Digvijay Boob , Qi Deng , Guanghui Lan

A computationally efficient method to solve non-convex programming problems with linear equality constraints is presented. The proposed method is based on a recursively feasible and descending sequential convex programming procedure proven…

Optimization and Control · Mathematics 2018-10-25 Josep Virgili-Llop , Marcello Romano

In [19], a general, inexact, efficient proximal quasi-Newton algorithm for composite optimization problems has been proposed and a sublinear global convergence rate has been established. In this paper, we analyze the convergence properties…

Numerical Analysis · Computer Science 2017-10-18 Hiva Ghanbari , Katya Scheinberg

Neural networks are discrete entities: subdivided into discrete layers and parametrized by weights which are iteratively optimized via difference equations. Recent work proposes networks with layer outputs which are no longer quantized but…

Neural and Evolutionary Computing · Computer Science 2019-09-09 Stefano Massaroli , Michael Poli , Federico Califano , Angela Faragasso , Jinkyoo Park , Atsushi Yamashita , Hajime Asama

Machine learning problems such as neural network training, tensor decomposition, and matrix factorization, require local minimization of a nonconvex function. This local minimization is challenged by the presence of saddle points, of which…

Optimization and Control · Mathematics 2018-07-23 Santiago Paternain , Aryan Mokhtari , Alejandro Ribeiro