paper-with-me

홈 › Papers

A stochastic gradient descent algorithm with random search directions

2025-03-25 · Eméric Gbaguidi

Stochastic coordinate descent algorithms are efficient methods in which each iterate is obtained by fixing most coordinates at their values from the current iteration, and approximately minimizing the objective with respect to the remaining coordinates. However, this approach is usually restricted to canonical basis vectors of $\mathbb{R}^d$. In this paper, we develop a new class of stochastic gradient descent algorithms with random search directions which uses the directional derivative of the gradient estimate following more general random vectors. We establish the almost sure convergence of these algorithms with decreasing step. We further investigate their central limit theorem and pay particular attention to analyze the impact of the search distributions on the asymptotic covariance matrix. We also provide non-asymptotic $\mathbb{L}^p$ rates of convergence.

📄 PDF Abstract BibTeX arXiv:2503.19942

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음
Random Search Random Search replaces the exhaustive enumeration of all combinations by selecting them randomly. This can be simply applied to the discrete setting described above, but also…

Similar Papers 제목 키워드 기반

Accelerated Randomized Coordinate Descent Algorithms for Stochastic Optimization and Online Learning

2018-06-05 · Akshita Bhandari, Chandramani Singh

We propose accelerated randomized coordinate descent algorithms for stochastic optimization and online learning. Our algorithms have significantly less per-iteration complexity than the known accelerated gradient algorit…

Stochastic Optimization

Continual Backprop: Stochastic Gradient Descent with Persistent Randomness

2021-08-13 · Shibhansh Dohare, Richard S. Sutton, A. Rupam Mahmood

The Backprop algorithm for learning in neural networks utilizes two mechanisms: first, stochastic gradient descent and second, initialization with small random weights, where the latter is essential to the effectiveness …

Continual LearningReinforcement Learning (RL)

Overall error analysis for the training of deep neural networks via stochastic gradient descent with random initialisation

2020-03-03 · Arnulf Jentzen, Timo Welti

In spite of the accomplishments of deep learning based algorithms in numerous applications and very broad corresponding research interest, at the moment there is still no rigorous understanding of the reasons why such al…

Deep Learning

A block-random algorithm for learning on distributed, heterogeneous data

2019-02-28 · Prakash Mohan, Marc T. Henry de Frahan, Ryan King, Ray W. Grout

Most deep learning models are based on deep neural networks with multiple layers between input and output. The parameters defining these layers are initialized using random values and are "learned" from data, typically u…

Stochastic Backward Euler: An Implicit Gradient Descent Algorithm for $k$-means Clustering

2017-10-21 · Penghang Yin, Minh Pham, Adam Oberman, Stanley Osher

In this paper, we propose an implicit gradient descent algorithm for the classic $k$-means problem. The implicit gradient step or backward Euler is solved via stochastic fixed-point iteration, in which we randomly sample…

Clustering