paper-with-me

홈 › Papers

Does Momentum Help? A Sample Complexity Analysis

2021-10-29 · Swetha Ganesh, Rohan Deb, Gugan Thoppe, Amarjit Budhiraja

Stochastic Heavy Ball (SHB) and Nesterov's Accelerated Stochastic Gradient (ASG) are popular momentum methods in stochastic optimization. While benefits of such acceleration ideas in deterministic settings are well understood, their advantages in stochastic optimization is still unclear. In fact, in some specific instances, it is known that momentum does not help in the sample complexity sense. Our work shows that a similar outcome actually holds for the whole of quadratic optimization. Specifically, we obtain a lower bound on the sample complexity of SHB and ASG for this family and show that the same bound can be achieved by the vanilla SGD. We note that there exist results claiming the superiority of momentum based methods in quadratic optimization, but these are based on one-sided or flawed analyses.

📄 PDF Abstract BibTeX arXiv:2110.15547

Code (0)

등록된 구현이 없습니다.

Tasks

Stochastic Optimization

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

Accelerated Stochastic Power Iteration

2017-07-10 · Christopher De Sa, Bryan He, Ioannis Mitliagkas, Christopher Ré 외

Principal component analysis (PCA) is one of the most powerful tools in machine learning. The simplest method for PCA, the power iteration, requires $\mathcal O(1/\Delta)$ full-data passes to recover the principal compon…

Dimensionality Reduction

Riemannian stochastic recursive momentum method for non-convex optimization

2020-08-11 · Andi Han, Junbin Gao

We propose a stochastic recursive momentum method for Riemannian non-convex optimization that achieves a near-optimal complexity of $\tilde{\mathcal{O}}(\epsilon^{-3})$ to find $\epsilon$-approximate solution with one sa…

Riemannian optimization

MDPGT: Momentum-based Decentralized Policy Gradient Tracking

2021-12-06 · Zhanhong Jiang, Xian Yeow Lee, Sin Yong Tan, Kai Liang Tan 외

We propose a novel policy gradient method for multi-agent reinforcement learning, which leverages two different variance-reduction techniques and does not require large batches over iterations. Specifically, we propose a…

Multi-agent Reinforcement LearningPolicy Gradient Methodsreinforcement-learningReinforcement Learning+2

Adai: Separating the Effects of Adaptive Learning Rate and Momentum Inertia

2020-06-29 · Zeke Xie, Xinrui Wang, Huishuai Zhang, Issei Sato 외

Adaptive Momentum Estimation (Adam), which combines Adaptive Learning Rate and Momentum, is the most popular stochastic optimizer for accelerating the training of deep neural networks. However, empirically Adam often gen…

Adaptive Inertia: Disentangling the Effects of Adaptive Learning Rate and Momentum

2021-09-29 · Zeke Xie, Xinrui Wang, Huishuai Zhang, Issei Sato 외

Adaptive Momentum Estimation (Adam), which combines Adaptive Learning Rate and Momentum, would be the most popular stochastic optimizer for accelerating the training of deep neural networks. However, empirically Adam oft…