paper-with-me

홈 › Papers

Weak error analysis for stochastic gradient descent optimization algorithms

2020-07-03 · Aritz Bercher, Lukas Gonon, Arnulf Jentzen, Diyora Salimova

Stochastic gradient descent (SGD) type optimization schemes are fundamental ingredients in a large number of machine learning based algorithms. In particular, SGD type optimization schemes are frequently employed in applications involving natural language processing, object and face recognition, fraud detection, computational advertisement, and numerical approximations of partial differential equations. In mathematical convergence results for SGD type optimization schemes there are usually two types of error criteria studied in the scientific literature, that is, the error in the strong sense and the error with respect to the objective function. In applications one is often not only interested in the size of the error with respect to the objective function but also in the size of the error with respect to a test function which is possibly different from the objective function. The analysis of the size of this error is the subject of this article. In particular, the main result of this article proves under suitable assumptions that the size of this error decays at the same speed as in the special case where the test function coincides with the objective function.

📄 PDF Abstract BibTeX arXiv:2007.02723

Code (0)

등록된 구현이 없습니다.

Tasks

Face RecognitionFraud Detection

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…
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

Uniform-in-Time Weak Error Analysis for Stochastic Gradient Descent Algorithms via Diffusion Approximation

2019-02-02 · Yuanyuan Feng, Tingran Gao, Lei LI, Jian-Guo Liu 외

Diffusion approximation provides weak approximation for stochastic gradient descent algorithms in a finite time horizon. In this paper, we introduce new tools motivated by the backward error analysis of numerical stochas…

Stochastic Optimization

Analysis of Stochastic Gradient Descent in Continuous Time

2020-04-15 · Jonas Latz

Stochastic gradient descent is an optimisation method that combines classical gradient descent with random subsampling within the target functional. In this work, we introduce the stochastic gradient process as a continu…

Stochastic Gradient Descent with Exponential Convergence Rates of Expected Classification Errors

2018-06-14 · Atsushi Nitanda, Taiji Suzuki

We consider stochastic gradient descent and its averaging variant for binary classification problems in a reproducing kernel Hilbert space. In the traditional analysis using a consistency property of loss functions, it i…

Binary ClassificationClassificationGeneral Classification

Tight Analyses for Non-Smooth Stochastic Gradient Descent

2018-12-13 · Nicholas J. A. Harvey, Christopher Liaw, Yaniv Plan, Sikander Randhawa

Consider the problem of minimizing functions that are Lipschitz and strongly convex, but not necessarily differentiable. We prove that after $T$ steps of stochastic gradient descent, the error of the final iterate is $O(…

A Tight Convergence Analysis for Stochastic Gradient Descent with Delayed Updates

2018-06-26 · Yossi Arjevani, Ohad Shamir, Nathan Srebro

We provide tight finite-time convergence bounds for gradient descent and stochastic gradient descent on quadratic functions, when the gradients are delayed and reflect iterates from $\tau$ rounds ago. First, we show that…

Distributed Optimization