paper-with-me

Papers

AdaSub: Stochastic Optimization Using Second-Order Information in Low-Dimensional Subspaces

2023-10-30 · João Victor Galvão da Mata, Martin S. Andersen

We introduce AdaSub, a stochastic optimization algorithm that computes a search direction based on second-order information in a low-dimensional subspace that is defined adaptively based on available current and past information. Compared to first-order methods, second-order methods exhibit better convergence characteristics, but the need to compute the Hessian matrix at each iteration results in excessive computational expenses, making them impractical. To address this issue, our approach enables the management of computational expenses and algorithm efficiency by enabling the selection of the subspace dimension for the search. Our code is freely available on GitHub, and our preliminary numerical results demonstrate that AdaSub surpasses popular stochastic optimizers in terms of time and number of iterations required to reach a given accuracy.

📄 PDF Abstract BibTeX arXiv:2310.20060

Code (1)

jvictormata/adasub 공식 구현 pytorch

Tasks

ManagementSecond-order methodsStochastic Optimization

Similar Papers 제목 키워드 기반

Fast and Precise: Adjusting Planning Horizon with Adaptive Subgoal Search

2022-06-01 · Michał Zawalski, Michał Tyrolski, Konrad Czechowski, Tomasz Odrzygóźdź 외

Complex reasoning problems contain states that vary in the computational cost required to determine a good action plan. Taking advantage of this property, we propose Adaptive Subgoal Search (AdaSubS), a search method tha…

Rubik's CubeSokoban

Second-Order Stochastic Optimization for Machine Learning in Linear Time

2016-02-12 · Naman Agarwal, Brian Bullins, Elad Hazan

First-order stochastic methods are the state-of-the-art in large-scale machine learning optimization owing to efficient per-iteration complexity. Second-order methods, while able to provide faster convergence, have been …

BIG-bench Machine LearningSecond-order methodsStochastic Optimization

Fast Black-box Variational Inference through Stochastic Trust-Region Optimization

2017-06-07 · NeurIPS 2017 12 · Jeffrey Regier, Michael. I. Jordan, Jon Mcauliffe

We introduce TrustVI, a fast second-order algorithm for black-box variational inference based on trust-region optimization and the reparameterization trick. At each iteration, TrustVI proposes and assesses a step based o…

Variational Inference

Information-Theoretic Trust Regions for Stochastic Gradient-Based Optimization

2023-10-31 · Philipp Dahlinger, Philipp Becker, Maximilian Hüttenrauch, Gerhard Neumann

Stochastic gradient-based optimization is crucial to optimize neural networks. While popular approaches heuristically adapt the step size and direction by rescaling gradients, a more principled approach to improve optimi…

Second-Order Information in Non-Convex Stochastic Optimization: Power and Limitations

2020-06-24 · Yossi Arjevani, Yair Carmon, John C. Duchi, Dylan J. Foster 외

We design an algorithm which finds an $\epsilon$-approximate stationary point (with $\|\nabla F(x)\|\le \epsilon$) using $O(\epsilon^{-3})$ stochastic gradient and Hessian-vector products, matching guarantees that were p…

Second-order methodsStochastic Optimization