English
Related papers

Related papers: M-FAC: Efficient Matrix-Free Approximations of Sec…

200 papers

This work introduces the nested-set Hessian approximation, a second-order approximation method that can be used in any derivative-free optimization routine that requires such information. It is built on the foundation of the generalized…

Optimization and Control · Mathematics 2020-11-06 Warren Hare , Gabriel Jarry-Bolduc , Chayne Planiden

It has long been a goal to efficiently compute and use second order information on a function ($f$) to assist in numerical approximations. Here it is shown how, using only basic physics and a numerical approximation, such information can be…

Machine Learning · Computer Science 2021-05-31 Michael F. Zimmer

Natural gradient descent is an optimization method traditionally motivated from the perspective of information geometry, and works well for many applications as an alternative to stochastic gradient descent. In this paper we critically…

Machine Learning · Computer Science 2020-09-22 James Martens

An algorithm for unconstrained non-convex optimization is described, which does not evaluate the objective function and in which minimization is carried out, at each iteration, within a randomly selected subspace. It is shown that this…

Optimization and Control · Mathematics 2025-01-31 S. Bellavia , S. Gratton , B. Morini , Ph. L. Toint

We propose a fast second-order method that can be used as a drop-in replacement for current deep learning solvers. Compared to stochastic gradient descent (SGD), it only requires two additional forward-mode automatic differentiation…

Machine Learning · Computer Science 2018-05-22 João F. Henriques , Sebastien Ehrhardt , Samuel Albanie , Andrea Vedaldi

We present a novel statistical inference framework for convex empirical risk minimization, using approximate stochastic Newton steps. The proposed algorithm is based on the notion of finite differences and allows the approximation of a…

Machine Learning · Computer Science 2019-02-06 Tianyang Li , Anastasios Kyrillidis , Liu Liu , Constantine Caramanis

Approximate second-order optimization methods often exhibit poorer generalization compared to first-order approaches. In this work, we look into this issue through the lens of the loss landscape and find that existing second-order methods…

Machine Learning · Computer Science 2025-06-25 Dahun Shin , Dongyeop Lee , Jinseok Chung , Namhoon Lee

In stochastic optimization problems using noisy zeroth-order (ZO) oracles only, the randomized counterpart of the Kiefer-Wolfowitz-type method is widely used to estimate the gradient. Existing algorithms generate randomized perturbation…

Optimization and Control · Mathematics 2020-11-30 Jingyi Zhu

Differentiable optimization layers enable learning systems to make decisions by solving embedded optimization problems. However, computing gradients via implicit differentiation requires solving a linear system with Hessian terms, which is…

Machine Learning · Computer Science 2025-12-03 Zihao Zhao , Kai-Chia Mo , Shing-Hei Ho , Brandon Amos , Kai Wang

In this work, we develop first-order (Hessian-free) and zero-order (derivative-free) implementations of the Cubically regularized Newton method for solving general non-convex optimization problems. For that, we employ finite difference…

Optimization and Control · Mathematics 2023-09-06 Nikita Doikov , Geovani Nunes Grapiglia

Trust-region (TR) and adaptive regularization using cubics (ARC) have proven to have some very appealing theoretical properties for non-convex optimization by concurrently computing function value, gradient, and Hessian matrix to obtain the…

Machine Learning · Computer Science 2023-10-19 Liu Liu , Xuanqing Liu , Cho-Jui Hsieh , Dacheng Tao

Meta-learning that uses implicit gradient have provided an exciting alternative to standard techniques which depend on the trajectory of the inner loop training. Implicit meta-learning (IML), however, require computing $2^{nd}$ order…

Machine Learning · Computer Science 2023-10-31 Fady Rezk

In the Bayesian approach to inverse problems, data are often informative, relative to the prior, only on a low-dimensional subspace of the parameter space. Significant computational savings can be achieved by using this subspace to…

Numerical Analysis · Mathematics 2015-07-07 Alessio Spantini , Antti Solonen , Tiangang Cui , James Martin , Luis Tenorio , Youssef Marzouk

Recently, Stochastic Variational Inference (SVI) has been increasingly attractive thanks to its ability to find good posterior approximations of probabilistic models. It optimizes the variational objective with stochastic optimization,…

Machine Learning · Computer Science 2022-03-16 Minta Liu , Suliang Bu

The multiplication of matrices is an important arithmetic operation in computational mathematics. In the context of hierarchical matrices, this operation can be realized by the multiplication of structured block-wise low-rank matrices,…

Numerical Analysis · Mathematics 2018-05-24 Jürgen Dölz , Helmut Harbrecht , Michael D. Multerer

We develop Policy Gradient with Second-Order Momentum (PG-SOM), a lightweight second-order optimisation scheme for reinforcement-learning policies. PG-SOM augments the classical REINFORCE update with two exponentially weighted statistics: a…

Machine Learning · Computer Science 2025-05-20 Tianyu Sun

Kronecker-factored Approximate Curvature (K-FAC) method is a high efficiency second order optimizer for the deep learning. Its training time is less than SGD(or other first-order method) with same accuracy in many large-scale problems. The…

Machine Learning · Computer Science 2021-01-05 Yingshi Chen

The problem of approximating the Pareto front of a multiobjective optimization problem can be reformulated as the problem of finding a set that maximizes the hypervolume indicator. This paper establishes the analytical expression of the…

Optimization and Control · Mathematics 2023-01-03 André H. Deutz , Michael T. M. Emmerich , Hao Wang

In this paper, we propose a second order optimization method to learn models where both the dimensionality of the parameter space and the number of training samples is high. In our method, we construct on each iteration a Krylov subspace…

Machine Learning · Statistics 2011-11-21 Oriol Vinyals , Daniel Povey

Given a matrix $X$, and two ranks $r_1$ and $r_2$, the Hadamard decomposition (HD) looks for two low-rank matrices, $X_1$ of rank $r_1$ and $X_2$ of rank $r_2$, both of the same size as $X$, such that $X\approx X_1\circ X_2$, where $\circ$…

Optimization and Control · Mathematics 2026-05-29 Nicolas Gillis , Subhayan Saha , Stefano Sicilia , Arnaud Vandaele