paper-with-me

Papers

YellowFin and the Art of Momentum Tuning

2017-06-12 · ICLR 2018 1 · Jian Zhang, Ioannis Mitliagkas

Hyperparameter tuning is one of the most time-consuming workloads in deep learning. State-of-the-art optimizers, such as AdaGrad, RMSProp and Adam, reduce this labor by adaptively tuning an individual learning rate for each variable. Recently researchers have shown renewed interest in simpler methods like momentum SGD as they may yield better test metrics. Motivated by this trend, we ask: can simple adaptive methods based on SGD perform as well or better? We revisit the momentum SGD algorithm and show that hand-tuning a single learning rate and momentum makes it competitive with Adam. We then analyze its robustness to learning rate misspecification and objective curvature variation. Based on these insights, we design YellowFin, an automatic tuner for momentum and learning rate in SGD. YellowFin optionally uses a negative-feedback loop to compensate for the momentum dynamics in asynchronous settings on the fly. We empirically show that YellowFin can converge in fewer iterations than Adam on ResNets and LSTMs for image recognition, language modeling and constituency parsing, with a speedup of up to 3.28x in synchronous and up to 2.69x in asynchronous settings.

📄 PDF Abstract BibTeX arXiv:1706.03471

Code (2)

JianGoForIt/YellowFin tf
JianGoForIt/YellowFin_Pytorch pytorch

Tasks

Constituency ParsingLanguage ModelingLanguage Modelling

Methods 이 논문이 사용한 방법론

AdaGrad AdaGrad is a stochastic optimization method that adapts the learning rate to the parameters. It performs smaller updates for parameters associated with frequently occurring…
YellowFin YellowFin is a learning rate and momentum tuner motivated by robustness properties and analysis of quadratic objectives. It stems from a known but obscure fact: the momentum…
RMSProp RMSProp is an unpublished adaptive learning rate optimizer proposed by Geoff Hinton. The motivation…
Adam 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

Training Deep Neural Networks with Adaptive Momentum Inspired by the Quadratic Optimization

2021-10-18 · Tao Sun, Huaming Ling, Zuoqiang Shi, Dongsheng Li 외

Heavy ball momentum is crucial in accelerating (stochastic) gradient-based optimization algorithms for machine learning. Existing heavy ball momentum is usually weighted by a uniform hyperparameter, which relies on exces…

BIG-bench Machine Learningimage-classificationImage ClassificationLanguage Modeling+3

Greedy Alignment Principle for Optimizer Selection

2025-12-06 · Jaerin Lee, Kyoung Mu Lee arxiv

Recent works have shown that gradient-update alignment is a powerful signal for modulating optimizer updates, often leading to faster training. We promote this update-wise heuristic as a mathematically grounded principle…

Image Classification

Convergence and Stability of the Stochastic Proximal Point Algorithm with Momentum

2021-11-11 · Junhyung Lyle Kim, Panos Toulis, Anastasios Kyrillidis

Stochastic gradient descent with momentum (SGDM) is the dominant algorithm in many optimization scenarios, including convex optimization instances and non-convex neural network training. Yet, in the stochastic setting, m…

Amortized Nesterov's Momentum: Robust and Lightweight Momentum for Deep Learning

2019-09-25 · Kaiwen Zhou, Yanghua Jin, Qinghua Ding, James Cheng

Stochastic Gradient Descent (SGD) with Nesterov's momentum is a widely used optimizer in deep learning, which is observed to have excellent generalization performance. However, due to the large stochasticity, SGD with Ne…

Deep Learning

MoMo: Momentum Models for Adaptive Learning Rates

2023-05-12 · Fabian Schaipp, Ruben Ohana, Michael Eickenberg, Aaron Defazio 외

Training a modern machine learning architecture on a new task requires extensive learning-rate tuning, which comes at a high computational cost. Here we develop new Polyak-type adaptive learning rates that can be used on…

Recommendation SystemsStochastic Optimization