paper-with-me

홈 › Papers

Adaptive Variance Reduction for Stochastic Optimization under Weaker Assumptions

2024-06-04 · Wei Jiang, Sifan Yang, Yibo Wang, Lijun Zhang

This paper explores adaptive variance reduction methods for stochastic optimization based on the STORM technique. Existing adaptive extensions of STORM rely on strong assumptions like bounded gradients and bounded function values, or suffer an additional $\mathcal{O}(\log T)$ term in the convergence rate. To address these limitations, we introduce a novel adaptive STORM method that achieves an optimal convergence rate of $\mathcal{O}(T^{-1/3})$ for non-convex functions with our newly designed learning rate strategy. Compared with existing approaches, our method requires weaker assumptions and attains the optimal convergence rate without the additional $\mathcal{O}(\log T)$ term. We also extend the proposed technique to stochastic compositional optimization, obtaining the same optimal rate of $\mathcal{O}(T^{-1/3})$. Furthermore, we investigate the non-convex finite-sum problem and develop another innovative adaptive variance reduction method that achieves an optimal convergence rate of $\mathcal{O}(n^{1/4} T^{-1/2} )$, where $n$ represents the number of component functions. Numerical experiments across various tasks validate the effectiveness of our method.

📄 PDF Abstract BibTeX arXiv:2406.01959

Code (0)

등록된 구현이 없습니다.

Tasks

Stochastic Optimization

Similar Papers 제목 키워드 기반

Kalman Gradient Descent: Adaptive Variance Reduction in Stochastic Optimization

2018-10-29 · James Vuckovic

We introduce Kalman Gradient Descent, a stochastic optimization algorithm that uses Kalman filtering to adaptively reduce gradient variance in stochastic gradient descent by filtering the gradient estimates. We present b…

BIG-bench Machine LearningStochastic OptimizationVariational Inference

Variance Reduction on General Adaptive Stochastic Mirror Descent

2020-12-26 · Wenjie Li, Zhanyu Wang, Yichen Zhang, Guang Cheng

In this work, we investigate the idea of variance reduction by studying its properties with general adaptive mirror descent algorithms in nonsmooth nonconvex finite-sum optimization problems. We propose a simple yet gene…

Online Variance Reduction with Mixtures

2019-03-29 · Zalán Borsos, Sebastian Curi, Kfir. Y. Levy, Andreas Krause

Adaptive importance sampling for stochastic optimization is a promising approach that offers improved convergence through variance reduction. In this work, we propose a new framework for variance reduction that enables t…

Stochastic Optimization

Variance reduction for Riemannian non-convex optimization with batch size adaptation

2020-07-03 · Andi Han, Junbin Gao

Variance reduction techniques are popular in accelerating gradient descent and stochastic gradient descent for optimization problems defined on both Euclidean space and Riemannian manifold. In this paper, we further impr…

Riemannian optimization

MARS: Unleashing the Power of Variance Reduction for Training Large Models

2024-11-15 · Huizhuo Yuan, Yifeng Liu, Shuang Wu, Xun Zhou 외

Training deep neural networks--and more recently, large models demands efficient and scalable optimizers. Adaptive gradient algorithms like Adam, AdamW, and their variants have been central to this task. Despite the deve…

Stochastic Optimization