English
Related papers

Related papers: First-Order Preconditioning via Hypergradient Desc…

200 papers

We present a novel adaptive optimization algorithm for large-scale machine learning problems. Equipped with a low-cost estimate of local curvature and Lipschitz smoothness, our method dynamically adapts the search direction and step-size.…

Machine Learning · Computer Science 2021-09-14 Majid Jahani , Sergey Rusakov , Zheng Shi , Peter Richtárik , Michael W. Mahoney , Martin Takáč

First order methods, which solely rely on gradient information, are commonly used in diverse machine learning (ML) and data analysis (DA) applications. This is attributed to the simplicity of their implementations, as well as low…

Machine Learning · Computer Science 2018-03-06 Sudhir B. Kylasa , Farbod Roosta-Khorasani , Michael W. Mahoney , Ananth Grama

This paper is an attempt to remedy the problem of slow convergence for first-order numerical algorithms by proposing an adaptive conditioning heuristic. First, we propose a parallelizable numerical algorithm that is capable of solving…

Optimization and Control · Mathematics 2021-03-02 Muhammad Adil , Sasan Tavakkol , Ramtin Madani

We study bilevel optimization problems where the lower-level problems are strongly convex and have coupled linear constraints. To overcome the potential non-smoothness of the hyper-objective and the computational challenges associated with…

Optimization and Control · Mathematics 2026-02-06 Wei Shen , Jiawei Zhang , Minhui Huang , Cong Shen

We show that memory-augmented Transformers can implement the entire class of linear first-order methods (LFOMs), a class that contains gradient descent (GD) and more advanced methods such as conjugate gradient descent (CGD), momentum…

Machine Learning · Computer Science 2025-02-04 Sanchayan Dutta , Suvrit Sra

First Order Bayesian Optimization (FOBO) is a sample efficient sequential approach to find the global maxima of an expensive-to-evaluate black-box objective function by suitably querying for the function and its gradient evaluations. Such…

Machine Learning · Computer Science 2023-06-21 Utkarsh Prakash , Aryan Chollera , Kushagra Khatwani , Prabuchandran K. J. , Tejas Bodas

Pre-conditioning is a well-known concept that can significantly improve the convergence of optimization algorithms. For noise-free problems, where good pre-conditioners are not known a priori, iterative linear algebra methods offer one way…

Machine Learning · Computer Science 2019-02-21 Filip de Roos , Philipp Hennig

Randomly initialized first-order optimization algorithms are the method of choice for solving many high-dimensional nonconvex problems in machine learning, yet general theoretical guarantees cannot rule out convergence to critical points of…

Optimization and Control · Mathematics 2018-09-28 Dar Gilboa , Sam Buchanan , John Wright

In this paper, we study the Multi-Objective Bi-Level Optimization (MOBLO) problem, where the upper-level subproblem is a multi-objective optimization problem and the lower-level subproblem is for scalar optimization. Existing gradient-based…

Machine Learning · Computer Science 2024-07-11 Feiyang Ye , Baijiong Lin , Xiaofeng Cao , Yu Zhang , Ivor Tsang

Leveraging second-order information about the loss at the scale of deep networks is one of the main lines of approach for improving the performance of current optimizers for deep learning. Yet, existing approaches for accurate full-matrix…

Machine Learning · Computer Science 2024-06-06 Ionut-Vlad Modoranu , Aleksei Kalinov , Eldar Kurtic , Elias Frantar , Dan Alistarh

In this work we derive a second-order approach to bilevel optimization, a type of mathematical programming in which the solution to a parameterized optimization problem (the "lower" problem) is itself to be optimized (in the "upper"…

Optimization and Control · Mathematics 2022-05-06 Robert Dyro , Edward Schmerling , Nikos Arechiga , Marco Pavone

We propose proximal backpropagation (ProxProp) as a novel algorithm that takes implicit instead of explicit gradient steps to update the network parameters during neural network training. Our algorithm is motivated by the step size…

Machine Learning · Computer Science 2018-02-21 Thomas Frerix , Thomas Möllenhoff , Michael Moeller , Daniel Cremers

Arising in semi-parametric statistics, control applications, and as sub-problems in global optimization methods, certain optimization problems can have objective functions requiring numerical integration to evaluate, yet gradient function…

Optimization and Control · Mathematics 2025-03-06 Christian Varner , Vivak Patel

First-order methods (FOMs) have recently been applied and analyzed for solving problems with complicated functional constraints. Existing works show that FOMs for functional constrained problems have lower-order convergence rates than those…

Optimization and Control · Mathematics 2021-04-20 Yangyang Xu

Variance-reduced gradient estimators for policy gradient methods have been one of the main focus of research in the reinforcement learning in recent years as they allow acceleration of the estimation process. We propose a variance-reduced…

Machine Learning · Computer Science 2023-11-28 Saber Salehkaleybar , Sadegh Khorasani , Negar Kiyavash , Niao He , Patrick Thiran

Natural policy gradient methods are popular reinforcement learning methods that improve the stability of policy gradient methods by utilizing second-order approximations to precondition the gradient with the inverse of the…

Machine Learning · Computer Science 2022-10-12 Brennan Gebotys , Alexander Wong , David A. Clausi

This paper studies the complexity of finding an $\epsilon$-stationary point for stochastic bilevel optimization when the upper-level problem is nonconvex and the lower-level problem is strongly convex. Recent work proposed the first-order…

Optimization and Control · Mathematics 2026-03-10 Lesi Chen , Junru Li , El Mahdi Chayti , Jingzhao Zhang

First-order methods with momentum such as Nesterov's fast gradient method are very useful for convex optimization problems, but can exhibit undesirable oscillations yielding slow convergence rates for some applications. An adaptive…

Optimization and Control · Mathematics 2019-06-14 Donghwan Kim , Jeffrey A. Fessler

Mixed integer linear programming (MILP) is a powerful representation often used to formulate decision-making problems under uncertainty. However, it lacks a natural mechanism to reason about objects, classes of objects, and relations.…

Logic in Computer Science · Computer Science 2012-05-14 Geoffrey Gordon , Sue Ann Hong , Miroslav Dudik

End-to-end deep learning has achieved impressive results but remains limited by its reliance on large labeled datasets, poor generalization to unseen scenarios, and growing computational demands. In contrast, classical optimization methods…

Machine Learning · Computer Science 2025-08-19 Gal Lifshitz , Shahar Zuler , Ori Fouks , Dan Raviv
‹ Prev 1 3 4 5 6 7 10 Next ›