HOME-3: High-Order Momentum Estimator with Third-Power Gradient for Convex and Smooth Nonconvex Optimization
Preprint
Abstract
Momentum-based gradients are essential for optimizing advanced machine learning models, as they not only accelerate convergence but also advance optimizers to escape stationary points. While most state-of-the-art momentum techniques utilize lower-order gradients, such as the squared first-order gradient, there has been limited exploration of higher-order gradients, particularly those raised to powers greater than two. In this work, we introduce the concept of high-order momentum, where momentum is constructed using higher-power gradients, with a focus on the third-power of the first-order gradient as a representative case. Our research offers both theoretical and empirical support for this approach. Theoretically, we demonstrate that incorporating third-power gradients can improve the convergence bounds of gradient-based optimizers for both convex and smooth nonconvex problems. Empirically, we validate these findings through extensive experiments across convex, smooth nonconvex, and nonsmooth nonconvex optimization tasks. Across all cases, high-order momentum consistently outperforms conventional low-order momentum methods, showcasing superior performance in various optimization problems.Keywords
All Related Versions
This publication has 17 references indexed in Scilit:
- Dictionary learning for integrative, multimodal and scalable single-cell analysisNature Biotechnology, 2023
- On the Parallelization Upper Bound for Asynchronous Stochastic Gradients Descent in Non-convex OptimizationJournal of Optimization Theory and Applications, 2022
- Proximal stochastic recursive momentum algorithm for nonsmooth nonconvex optimization problemsOptimization, 2022
- Approximation properties of Gaussian-binary restricted Boltzmann machines and Gaussian-binary deep belief networksNeural Networks, 2022
- Distributed Stochastic Consensus Optimization With Momentum for Nonconvex Nonsmooth ProblemsIEEE Transactions on Signal Processing, 2021
- Momentum and stochastic momentum for stochastic gradient, Newton, proximal point and subspace descent methodsComputational Optimization and Applications, 2020
- Low-rank and sparse matrices fitting algorithm for low-rank representationComputers & Mathematics with Applications, 2020
- A Deep Matrix Factorization Method for Learning Attribute RepresentationsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- Robust Stochastic Approximation Approach to Stochastic ProgrammingSIAM Journal on Optimization, 2009
- Generalized gradients of Lipschitz functionalsAdvances in Mathematics, 1981