paper-with-me

홈 › Papers

FOSI: Hybrid First and Second Order Optimization

2023-02-16 · Hadar Sivan, Moshe Gabel, Assaf Schuster

Popular machine learning approaches forgo second-order information due to the difficulty of computing curvature in high dimensions. We present FOSI, a novel meta-algorithm that improves the performance of any base first-order optimizer by efficiently incorporating second-order information during the optimization process. In each iteration, FOSI implicitly splits the function into two quadratic functions defined on orthogonal subspaces, then uses a second-order method to minimize the first, and the base optimizer to minimize the other. We formally analyze FOSI's convergence and the conditions under which it improves a base optimizer. Our empirical evaluation demonstrates that FOSI improves the convergence rate and optimization time of first-order methods such as Heavy-Ball and Adam, and outperforms second-order methods (K-FAC and L-BFGS).

📄 PDF Abstract BibTeX arXiv:2302.08484

Code (1)

hsivan/fosi 공식 구현 jax

Tasks

Audio ClassificationLanguage ModellingSecond-order methodsTransfer Learning

Methods 이 논문이 사용한 방법론

BASE 설명 없음
SGD Stochastic Gradient Descent is an iterative optimization technique that uses minibatches of data to form an expectation of the gradient, rather than the full gradient using…
Adam 설명 없음

Similar Papers 제목 키워드 기반

Accelerating Deep Neural Network Training via Distributed Hybrid Order Optimization

2025-05-02 · Shunxian Gu, Chaoqun You, Bangbang Ren, Lailong Luo 외

Scaling deep neural network (DNN) training to more devices can reduce time-to-solution. However, it is impractical for users with limited computing resources. FOSI, as a hybrid order optimizer, converges faster than conv…

Universal Controllers with Differentiable Physics for Online System Identification

2021-09-29 · Michelle Guo, Wenhao Yu, Daniel Ho, Jiajun Wu 외

Creating robots that can handle changing or unknown environments is a critical step towards real-world robot applications. Existing methods tackle this problem by training controllers robust to large ranges of environmen…

Domain Adaptation

Fuzzy hyperparameters update in a second order optimization

2024-03-08 · Abdelaziz Bensadok, Muhammad Zeeshan Babar

This research will present a hybrid approach to accelerate convergence in a second order optimization. An online finite difference approximation of the diagonal Hessian matrix will be introduced, along with fuzzy inferen…

Hybrid Decentralized Optimization: Leveraging Both First- and Zeroth-Order Optimizers for Faster Convergence

2022-10-14 · Shayan Talaei, Matin Ansaripour, Giorgi Nadiradze, Dan Alistarh

Distributed optimization is the standard way of speeding up machine learning training, and most of the research in the area focuses on distributed first-order, gradient-based methods. Yet, there are settings where some c…

Distributed Optimization

From Kinematics to Dynamics: Learning to Refine Hybrid Plans for Physically Feasible Execution

2026-04-14 · Lidor Erez, Shahaf S. Shperberg, Ayal Taitler arxiv

In many robotic tasks, agents must traverse a sequence of spatial regions to complete a mission. Such problems are inherently mixed discrete-continuous: a high-level action sequence and a physically feasible continuous t…

Reinforcement Learning