paper-with-me

홈 › Papers

Dynamics of Stochastic Momentum Methods on Large-scale, Quadratic Models

2021-06-07 · NeurIPS 2021 12 · Courtney Paquette, Elliot Paquette

We analyze a class of stochastic gradient algorithms with momentum on a high-dimensional random least squares problem. Our framework, inspired by random matrix theory, provides an exact (deterministic) characterization for the sequence of loss values produced by these algorithms which is expressed only in terms of the eigenvalues of the Hessian. This leads to simple expressions for nearly-optimal hyperparameters, a description of the limiting neighborhood, and average-case complexity. As a consequence, we show that (small-batch) stochastic heavy-ball momentum with a fixed momentum parameter provides no actual performance improvement over SGD when step sizes are adjusted correctly. For contrast, in the non-strongly convex setting, it is possible to get a large improvement over SGD using momentum. By introducing hyperparameters that depend on the number of samples, we propose a new algorithm sDANA (stochastic dimension adjusted Nesterov acceleration) which obtains an asymptotically optimal average-case complexity while remaining linearly convergent in the strongly convex setting without adjusting parameters.

📄 PDF Abstract BibTeX arXiv:2106.03696

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

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

Perfect Parallelization in Mini-Batch SGD with Classical Momentum Acceleration

2026-05-18 · Sachin Garg, Michał Dereziński arxiv

Accelerating stochastic gradient methods with classical momentum schemes, such as Polyak's heavy ball, has proven highly successful in training large-scale machine learning models, particularly when combined with the har…

Dynamics of Stochastic Momentum with Sparse Updates in High Dimensions

2026-05-27 · Katie Everett, Elliot Paquette arxiv

Existing theory of momentum assumes that gradients arrive at every parameter at a roughly constant rate, an assumption violated in practice by heavy-tailed data distributions and modern architectures. We theoretically an…

Last-iterate convergence analysis of stochastic momentum methods for neural networks

2022-05-30 · Dongpo Xu, Jinlan Liu, Yinghua Lu, Jun Kong 외

The stochastic momentum method is a commonly used acceleration technique for solving large-scale stochastic optimization problems in artificial neural networks. Current convergence results of stochastic momentum methods …

Stochastic Optimization

Trajectory of Mini-Batch Momentum: Batch Size Saturation and Convergence in High Dimensions

2022-06-02 · Kiwon Lee, Andrew N. Cheng, Courtney Paquette, Elliot Paquette

We analyze the dynamics of large batch stochastic gradient descent with momentum (SGD+M) on the least squares problem when both the number of samples and dimensions are large. In this setting, we show that the dynamics o…

mL-BFGS: A Momentum-based L-BFGS for Distributed Large-Scale Neural Network Optimization

2023-07-25 · Yue Niu, Zalan Fabian, Sunwoo Lee, Mahdi Soltanolkotabi 외

Quasi-Newton methods still face significant challenges in training large-scale neural networks due to additional compute costs in the Hessian related computations and instability issues in stochastic training. A well-kno…

Stochastic Optimization