paper-with-me

Papers

Stochastic Approximation Beyond Gradient for Signal Processing and Machine Learning

2023-02-22 · Aymeric Dieuleveut, Gersende Fort, Eric Moulines, Hoi-To Wai

Stochastic Approximation (SA) is a classical algorithm that has had since the early days a huge impact on signal processing, and nowadays on machine learning, due to the necessity to deal with a large amount of data observed with uncertainties. An exemplar special case of SA pertains to the popular stochastic (sub)gradient algorithm which is the working horse behind many important applications. A lesser-known fact is that the SA scheme also extends to non-stochastic-gradient algorithms such as compressed stochastic gradient, stochastic expectation-maximization, and a number of reinforcement learning algorithms. The aim of this article is to overview and introduce the non-stochastic-gradient perspectives of SA to the signal processing and machine learning audiences through presenting a design guideline of SA algorithms backed by theories. Our central theme is to propose a general framework that unifies existing theories of SA, including its non-asymptotic and asymptotic convergence results, and demonstrate their applications on popular non-stochastic-gradient algorithms. We build our analysis framework based on classes of Lyapunov functions that satisfy a variety of mild conditions. We draw connections between non-stochastic-gradient algorithms and scenarios when the Lyapunov function is smooth, convex, or strongly convex. Using the said framework, we illustrate the convergence properties of the non-stochastic-gradient algorithms using concrete examples. Extensions to the emerging variance reduction techniques for improved sample complexity will also be discussed.

📄 PDF Abstract BibTeX arXiv:2302.11147

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Practical Precoding via Asynchronous Stochastic Successive Convex Approximation

2020-10-03 · Basil M. Idrees, Javed Akhtar, Ketan Rajawat

We consider stochastic optimization of a smooth non-convex loss function with a convex non-smooth regularizer. In the online setting, where a single sample of the stochastic gradient of the loss is available at every ite…

Stochastic Optimization

Computing the Variance of Shuffling Stochastic Gradient Algorithms via Power Spectral Density Analysis

2022-06-01 · Carles Domingo-Enrich

When solving finite-sum minimization problems, two common alternatives to stochastic gradient descent (SGD) with theoretical benefits are random reshuffling (SGD-RR) and shuffle-once (SGD-SO), in which functions are samp…

Formalization of a Stochastic Approximation Theorem

2022-02-12 · Koundinya Vajjha, Barry Trager, Avraham Shinnar, Vasily Pestun

Stochastic approximation algorithms are iterative procedures which are used to approximate a target value in an environment where the target is unknown and direct observations are corrupted by noise. These algorithms are…

Big Batch SGD: Automated Inference using Adaptive Batch Sizes

2016-10-18 · Soham De, Abhay Yadav, David Jacobs, Tom Goldstein

Classical stochastic gradient methods for optimization rely on noisy gradient approximations that become progressively less accurate as iterates approach a solution. The large noise and small signal in the resulting grad…

Differentiable Signal Processing With Black-Box Audio Effects

2021-05-11 · Marco A. Martínez Ramírez, Oliver Wang, Paris Smaragdis, Nicholas J. Bryan

We present a data-driven approach to automate audio signal processing by incorporating stateful third-party, audio effects as layers within a deep neural network. We then train a deep encoder to analyze input audio and c…

Audio Signal Processing