paper-with-me

홈 › Papers

Momentum via Primal Averaging: Theoretical Insights and Learning Rate Schedules for Non-Convex Optimization

2020-10-01 · Aaron Defazio

Momentum methods are now used pervasively within the machine learning community for training non-convex models such as deep neural networks. Empirically, they out perform traditional stochastic gradient descent (SGD) approaches. In this work we develop a Lyapunov analysis of SGD with momentum (SGD+M), by utilizing a equivalent rewriting of the method known as the stochastic primal averaging (SPA) form. This analysis is much tighter than previous theory in the non-convex case, and due to this we are able to give precise insights into when SGD+M may out-perform SGD, and what hyper-parameter schedules will work and why.

📄 PDF Abstract BibTeX arXiv:2010.00406

Code (1)

facebookresearch/madgrad 공식 구현 pytorch

Tasks

BIG-bench Machine LearningSingle Particle Analysis

Methods 이 논문이 사용한 방법론

SGD with Momentum 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…

Similar Papers 제목 키워드 기반

Gradient Descent Averaging and Primal-dual Averaging for Strongly Convex Optimization

2020-12-29 · Wei Tao, Wei Li, Zhisong Pan, Qing Tao

Averaging scheme has attracted extensive attention in deep learning as well as traditional machine learning. It achieves theoretically optimal convergence and also improves the empirical model performance. However, there…

Smoothing DiLoCo with Primal Averaging for Faster Training of LLMs

2025-12-18 · Aaron Defazio, Konstantin Mishchenko, Parameswaran Raman, Hao-Jun Michael Shi 외 arxiv

We propose Generalized Primal Averaging (GPA), an extension of Nesterov's method that unifies and generalizes recent averaging-based optimizers like single-worker DiLoCo and Schedule-Free, within a non-distributed settin…

Federated Composite Optimization

2020-11-17 · Honglin Yuan, Manzil Zaheer, Sashank Reddi

Federated Learning (FL) is a distributed learning paradigm that scales on-device learning collaboratively and privately. Standard FL algorithms such as FedAvg are primarily geared towards smooth unconstrained settings. I…

Federated Learning

Accelerated Dual-Averaging Primal-Dual Method for Composite Convex Minimization

2020-01-15 · Conghui Tan, Yuqiu Qian, Shiqian Ma, Tong Zhang

Dual averaging-type methods are widely used in industrial machine learning applications due to their ability to promoting solution structure (e.g., sparsity) efficiently. In this paper, we propose a novel accelerated dua…

BIG-bench Machine Learning

On Principled Local Optimization Methods for Federated Learning

2024-01-24 · Honglin Yuan

Federated Learning (FL), a distributed learning paradigm that scales on-device learning collaboratively, has emerged as a promising approach for decentralized AI applications. Local optimization methods such as Federated…

Federated Learning