paper-with-me

Papers

Optimal Convergence for Distributed Learning with Stochastic Gradient Methods and Spectral Algorithms

2018-01-22 · Junhong Lin, Volkan Cevher

We study generalization properties of distributed algorithms in the setting of nonparametric regression over a reproducing kernel Hilbert space (RKHS). We first investigate distributed stochastic gradient methods (SGM), with mini-batches and multi-passes over the data. We show that optimal generalization error bounds can be retained for distributed SGM provided that the partition level is not too large. We then extend our results to spectral-regularization algorithms (SRA), including kernel ridge regression (KRR), kernel principal component analysis, and gradient methods. Our results are superior to the state-of-the-art theory. Particularly, our results show that distributed SGM has a smaller theoretical computational complexity, compared with distributed KRR and classic SGM. Moreover, even for non-distributed SRA, they provide the first optimal, capacity-dependent convergence rates, considering the case that the regression function may not be in the RKHS.

📄 PDF Abstract BibTeX arXiv:1801.07226

Code (0)

등록된 구현이 없습니다.

Tasks

regression

Similar Papers 제목 키워드 기반

High-Probability Convergence for Composite and Distributed Stochastic Minimization and Variational Inequalities with Heavy-Tailed Noise

2023-10-03 · Eduard Gorbunov, Abdurakhmon Sadiev, Marina Danilova, Samuel Horváth 외

High-probability analysis of stochastic first-order optimization methods under mild assumptions on the noise has been gaining a lot of attention in recent years. Typically, gradient clipping is one of the key algorithmic…

Distributed Optimization

Asynchronous Distributed Semi-Stochastic Gradient Optimization

2015-08-07 · Ruiliang Zhang, Shuai Zheng, James T. Kwok

With the recent proliferation of large-scale learning problems,there have been a lot of interest on distributed machine learning algorithms, particularly those that are based on stochastic gradient descent (SGD) and its …

Cloud Computing

Distributed Delayed Stochastic Optimization

2011-12-01 · NeurIPS 2011 12 · Alekh Agarwal, John C. Duchi

We analyze the convergence of gradient-based optimization algorithms whose updates depend on delayed stochastic gradient information. The main application of our results is to the development of distributed minimizatio…

Distributed OptimizationStochastic Optimization

Without-Replacement Sampling for Stochastic Gradient Methods: Convergence Results and Application to Distributed Optimization

2016-03-02 · NeurIPS 2016 · Ohad Shamir

Stochastic gradient methods for machine learning and optimization problems are usually analyzed assuming data points are sampled \emph{with} replacement. In practice, however, sampling \emph{without} replacement is very …

Distributed OptimizationLearning TheoryStochastic OptimizationTransductive Learning

From PowerSGD to PowerSGD+: Low-Rank Gradient Compression for Distributed Optimization with Convergence Guarantees

2025-09-14 · Shengping Xie, Chuyan Chen, Kun Yuan arxiv

Low-rank gradient compression methods, such as PowerSGD, have gained attention in communication-efficient distributed optimization. However, the convergence guarantees of PowerSGD remain unclear, particularly in stochast…

Distributed Optimization