English
Related papers

Related papers: Efficient Stochastic BFGS methods Inspired by Baye…

200 papers

Classical stochastic gradient methods for optimization rely on noisy gradient approximations that become progressively less accurate as iterates approach a solution. The large noise and small signal in the resulting gradients makes it…

Machine Learning · Computer Science 2017-04-10 Soham De , Abhay Yadav , David Jacobs , Tom Goldstein

Gaussian graphical models are widely used to infer dependence structures. Bayesian methods are appealing to quantify uncertainty associated with structural learning, i.e., the plausibility of conditional independence statements given the…

Methodology · Statistics 2025-11-05 Deborah Sulem , Jack Jewson , David Rossell

An algorithm is proposed for solving optimization problems arising in neural network training for supervised learning. The unique feature of the algorithm is the use of an auxiliary loss, in addition to the original loss employed for model…

Optimization and Control · Mathematics 2026-05-11 Yunlang Zhu , Lingjun Guo , Zahra Khatti , Xiaoyi Qu , Chia-Yuan Wu , Lara Zebiane , Frank E. Curtis

First-order methods such as stochastic gradient descent (SGD) are currently the standard algorithm for training deep neural networks. Second-order methods, despite their better convergence rate, are rarely used in practice due to the…

Machine Learning · Computer Science 2019-09-26 Tianle Cai , Ruiqi Gao , Jikai Hou , Siyu Chen , Dong Wang , Di He , Zhihua Zhang , Liwei Wang

The main focus in this paper is exact linesearch methods for minimizing a quadratic function whose Hessian is positive definite. We give a class of limited-memory quasi-Newton Hessian approximations which generate search directions parallel…

Optimization and Control · Mathematics 2023-05-04 David Ek , Anders Forsgren

The forward-backward splitting method (FBS) for minimizing a nonsmooth composite function can be interpreted as a (variable-metric) gradient method over a continuously differentiable function which we call forward-backward envelope (FBE).…

Optimization and Control · Mathematics 2019-11-11 Lorenzo Stella , Andreas Themelis , Panagiotis Patrinos

This paper deals with regularized Newton methods, a flexible class of unconstrained optimization algorithms that is competitive with line search and trust region methods and potentially combines attractive elements of both. The particular…

Optimization and Control · Mathematics 2022-07-13 Daniel Steck , Christian Kanzow

We study fundamental limits of first-order stochastic optimization in a range of nonconvex settings, including L-smooth functions satisfying Quasar-Convexity (QC), Quadratic Growth (QG), and Restricted Secant Inequalities (RSI). While the…

Machine Learning · Statistics 2025-06-03 El Mehdi Saad , Wei-Cheng Lee , Francesco Orabona

We consider the class of optimization problems arising from computationally intensive L1-regularized M-estimators, where the function or gradient values are very expensive to compute. A particular instance of interest is the L1-regularized…

Machine Learning · Statistics 2015-01-26 Kai Zhong , Ian E. H. Yen , Inderjit S. Dhillon , Pradeep Ravikumar

In this thesis, we disentangle the generalized Gauss-Newton and approximate inference for Bayesian deep learning. The generalized Gauss-Newton method is an optimization method that is used in several popular Bayesian deep learning…

Machine Learning · Statistics 2020-07-24 Alexander Immer

Two-level stochastic optimization formulations have become instrumental in a number of machine learning contexts such as continual learning, neural architecture search, adversarial learning, and hyperparameter tuning. Practical stochastic…

Optimization and Control · Mathematics 2023-11-08 Tommaso Giovannelli , Griffin Dean Kent , Luis Nunes Vicente

Gradient optimization algorithms using epochs, that is those based on stochastic gradient descent without replacement (SGDo), are predominantly used to train machine learning models in practice. However, the mathematical theory of SGDo and…

Machine Learning · Computer Science 2025-12-05 Stefan Perko

In this paper, we consider both first- and second-order techniques to address continuous optimization problems arising in machine learning. In the first-order case, we propose a framework of transition from deterministic or…

Machine Learning · Computer Science 2021-11-30 Sanae Lotfi , Tiphaine Bonniot de Ruisselet , Dominique Orban , Andrea Lodi

We consider the problem of how to learn a step-size policy for the Limited-Memory Broyden-Fletcher-Goldfarb-Shanno (L-BFGS) algorithm. This is a limited computational memory quasi-Newton method widely used for deterministic unconstrained…

Machine Learning · Computer Science 2021-02-11 Lucas N. Egidio , Anders Hansson , Bo Wahlberg

Optimal experimental design (OED) seeks experiments expected to yield the most useful data for some purpose. In practical circumstances where experiments are time-consuming or resource-intensive, OED can yield enormous savings. We pursue…

Computation · Statistics 2014-12-30 Xun Huan , Youssef M. Marzouk

We propose a dynamic domain semi-Lagrangian method for stochastic Vlasov equations driven by transport noises, which arise in plasma physics and astrophysics. This method combines the volume-preserving property of stochastic characteristics…

Numerical Analysis · Mathematics 2026-03-06 Jianbo Cui , Derui Sheng , Chenhui Zhang , Tau Zhou

To minimize the average of a set of log-convex functions, the stochastic Newton method iteratively updates its estimate using subsampled versions of the full objective's gradient and Hessian. We contextualize this optimization problem as…

Machine Learning · Statistics 2023-08-22 Michael C. Burkhart

We present two stochastic descent algorithms that apply to unconstrained optimization and are particularly efficient when the objective function is slow to evaluate and gradients are not easily obtained, as in some PDE-constrained…

Optimization and Control · Mathematics 2019-04-30 David Kozak , Stephen Becker , Alireza Doostan , Luis Tenorio

Stochastic convex optimization is a basic and well studied primitive in machine learning. It is well known that convex and Lipschitz functions can be minimized efficiently using Stochastic Gradient Descent (SGD). The Normalized Gradient…

Machine Learning · Computer Science 2015-10-29 Elad Hazan , Kfir Y. Levy , Shai Shalev-Shwartz

We study the local convergence of classical quasi-Newton methods for nonlinear optimization. Although it was well established a long time ago that asymptotically these methods converge superlinearly, the corresponding rates of convergence…

Optimization and Control · Mathematics 2021-06-02 Anton Rodomanov , Yurii Nesterov