paper-with-me

홈 › Papers

Tight Dimension Independent Lower Bound on the Expected Convergence Rate for Diminishing Step Sizes in SGD

2018-10-10 · NeurIPS 2019 12 · Phuong Ha Nguyen, Lam M. Nguyen, Marten van Dijk

We study the convergence of Stochastic Gradient Descent (SGD) for strongly convex objective functions. We prove for all $t$ a lower bound on the expected convergence rate after the $t$-th SGD iteration; the lower bound is over all possible sequences of diminishing step sizes. It implies that recently proposed sequences of step sizes at ICML 2018 and ICML 2019 are {\em universally} close to optimal in that the expected convergence rate after {\em each} iteration is within a factor $32$ of our lower bound. This factor is independent of dimension $d$. We offer a framework for comparing with lower bounds in state-of-the-art literature and when applied to SGD for strongly convex objective functions our lower bound is a significant factor $775\cdot d$ larger compared to existing work.

📄 PDF Abstract BibTeX arXiv:1810.04723

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

Tight Regret Bounds for Noisy Optimization of a Brownian Motion

2020-01-25 · Zexin Wang, Vincent Y. F. Tan, Jonathan Scarlett

We consider the problem of Bayesian optimization of a one-dimensional Brownian motion in which the $T$ adaptively chosen observations are corrupted by Gaussian noise. We show that as the smallest possible expected cumula…

Bayesian OptimizationTwo-sample testing

Distribution-Dependent Sample Complexity of Large Margin Learning

2012-04-05 · Sivan Sabato, Nathan Srebro, Naftali Tishby

We obtain a tight distribution-specific characterization of the sample complexity of large-margin classification with L2 regularization: We introduce the margin-adapted dimension, which is a simple function of the second…

Active LearningGeneral ClassificationL2 Regularization

Expected Worst Case Regret via Stochastic Sequential Covering

2022-09-09 · Changlong Wu, Mohsen Heidari, Ananth Grama, Wojciech Szpankowski

We study the problem of sequential prediction and online minimax regret with stochastically generated features under a general loss function. We introduce a notion of expected worst case minimax regret that generalizes a…

Tight lower bounds for Differentially Private ERM

2021-09-29 · Daogao Liu, Zhou Lu

We consider the lower bounds of differentially private ERM for general convex functions. For approximate-DP, the well-known upper bound of DP-ERM is $O(\frac{\sqrt{p\log(1/\delta)}}{\epsilon n})$, which is believed to be…

Tight Lower Bound on the Probability of a Binomial Exceeding its Expectation

2013-06-06 · Spencer Greenberg, Mehryar Mohri

We give the proof of a tight lower bound on the probability that a binomial random variable exceeds its expected value. The inequality plays an important role in a variety of contexts, including the analysis of relative …

Generalization BoundsLearning Theory