paper-with-me

Papers

Dynamical mean-field theory for stochastic gradient descent in Gaussian mixture classification

2020-06-10 · NeurIPS 2020 12 · Francesca Mignacco, Florent Krzakala, Pierfrancesco Urbani, Lenka Zdeborová

We analyze in a closed form the learning dynamics of stochastic gradient descent (SGD) for a single-layer neural network classifying a high-dimensional Gaussian mixture where each cluster is assigned one of two labels. This problem provides a prototype of a non-convex loss landscape with interpolating regimes and a large generalization gap. We define a particular stochastic process for which SGD can be extended to a continuous-time limit that we call stochastic gradient flow. In the full-batch limit, we recover the standard gradient flow. We apply dynamical mean-field theory from statistical physics to track the dynamics of the algorithm in the high-dimensional limit via a self-consistent stochastic process. We explore the performance of the algorithm as a function of the control parameters shedding light on how it navigates the loss landscape.

📄 PDF Abstract BibTeX arXiv:2006.06098

Code (0)

등록된 구현이 없습니다.

Tasks

General Classification

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

Rigorous dynamical mean field theory for stochastic gradient descent methods

2022-10-12 · Cedric Gerbelot, Emanuele Troiani, Francesca Mignacco, Florent Krzakala 외

We prove closed-form equations for the exact high-dimensional asymptotics of a family of first order gradient-based methods, learning an estimator (e.g. M-estimator, shallow neural network, ...) from observations on Gaus…

High-Dimensional Limit of Stochastic Gradient Flow via Dynamical Mean-Field Theory

2026-02-06 · Sota Nishiyama, Masaaki Imaizumi arxiv

Modern machine learning models are typically trained via multi-pass stochastic gradient descent (SGD) with small batch sizes, and understanding their dynamics in high dimensions is of great interest. However, an analytic…

An optimization-based equilibrium measure describes non-equilibrium steady state dynamics: application to edge of chaos

2024-01-18 · Junbin Qiu, Haiping Huang

Understanding neural dynamics is a central topic in machine learning, non-linear physics and neuroscience. However, the dynamics is non-linear, stochastic and particularly non-gradient, i.e., the driving force can not be…

Stochasticity helps to navigate rough landscapes: comparing gradient-descent-based algorithms in the phase retrieval problem

2021-03-08 · Francesca Mignacco, Pierfrancesco Urbani, Lenka Zdeborová

In this paper we investigate how gradient-based algorithms such as gradient descent, (multi-pass) stochastic gradient descent, its persistent variant, and the Langevin algorithm navigate non-convex loss-landscapes and wh…

NavigateRetrieval

Stochastic Gradient Descent outperforms Gradient Descent in recovering a high-dimensional signal in a glassy energy landscape

2023-09-09 · Persia Jana Kamali, Pierfrancesco Urbani

Stochastic Gradient Descent (SGD) is an out-of-equilibrium algorithm used extensively to train artificial neural networks. However very little is known on to what extent SGD is crucial for to the success of this technolo…