Enhancing Optimizer Stability: Momentum Adaptation of The NGN Step-size
Modern optimization algorithms that incorporate momentum and adaptive step-size offer improved performance in numerous challenging deep learning tasks. However, their effectiveness is often highly sensitive to the choice of hyperparameters, especially the step-size. Tuning these parameters is often difficult, resource-intensive, and time-consuming. Therefore, recent efforts have been directed toward enhancing the stability of optimizers across a wide range of hyperparameter choices [Schaipp et al., 2024]. In this paper, we introduce an algorithm that matches the performance of state-of-the-art optimizers while improving stability to the choice of the step-size hyperparameter through a novel adaptation of the NGN step-size method [Orvieto and Xiao, 2024]. Specifically, we propose a momentum-based version (NGN-M) that attains the standard convergence rate of $\mathcal{O}(1/\sqrt{K})$ under less restrictive assumptions, without the need for interpolation condition or assumptions of bounded stochastic gradients or iterates, in contrast to previous approaches. Additionally, we empirically demonstrate that the combination of the NGN step-size with momentum results in enhanced robustness to the choice of the step-size hyperparameter while delivering performance that is comparable to or surpasses other state-of-the-art optimizers.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Enhanced NIRMAL Optimizer With Damped Nesterov Acceleration: A Comparative Analysis
This study introduces the Enhanced NIRMAL (Novel Integrated Robust Multi-Adaptation Learning with Damped Nesterov Acceleration) optimizer, an improved version of the original NIRMAL optimizer. By incorporating an $(α, r)…
Image ClassificationAdaPlus: Integrating Nesterov Momentum and Precise Stepsize Adjustment on AdamW Basis
This paper proposes an efficient optimizer called AdaPlus which integrates Nesterov momentum and precise stepsize adjustment on AdamW basis. AdaPlus combines the advantages of AdamW, Nadam, and AdaBelief and, in particul…
image-classificationImage ClassificationLanguage ModelingLanguage ModellingAdam Improves Muon: Adaptive Moment Estimation with Orthogonalized Momentum
Efficient stochastic optimization typically integrates an update direction that performs well in the deterministic regime with a mechanism adapting to stochastic perturbations. While Adam uses adaptive moment estimates t…
Stochastic OptimizationMomentum Centering and Asynchronous Update for Adaptive Gradient Methods
We propose ACProp (Asynchronous-centering-Prop), an adaptive optimizer which combines centering of second momentum and asynchronous update (e.g. for $t$-th update, denominator uses information up to step $t-1$, while num…
image-classificationImage ClassificationL4: Practical loss-based stepsize adaptation for deep learning
We propose a stepsize adaptation scheme for stochastic gradient descent. It operates directly with the loss function and rescales the gradient in order to make fixed predicted progress on the loss. We demonstrate its cap…
Deep Learning