paper-with-me

홈 › Papers

Deep Relaxation: partial differential equations for optimizing deep neural networks

2017-04-17 · Pratik Chaudhari, Adam Oberman, Stanley Osher, Stefano Soatto, Guillaume Carlier

In this paper we establish a connection between non-convex optimization methods for training deep neural networks and nonlinear partial differential equations (PDEs). Relaxation techniques arising in statistical physics which have already been used successfully in this context are reinterpreted as solutions of a viscous Hamilton-Jacobi PDE. Using a stochastic control interpretation allows we prove that the modified algorithm performs better in expectation that stochastic gradient descent. Well-known PDE regularity results allow us to analyze the geometry of the relaxed energy landscape, confirming empirical evidence. The PDE is derived from a stochastic homogenization problem, which arises in the implementation of the algorithm. The algorithms scale well in practice and can effectively tackle the high dimensionality of modern neural networks.

📄 PDF Abstract BibTeX arXiv:1704.04932

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Learning Relaxation for Multigrid

2022-07-25 · Dmitry Kuznichov

During the last decade, Neural Networks (NNs) have proved to be extremely effective tools in many fields of engineering, including autonomous vehicles, medical diagnosis and search engines, and even in art creation. Inde…

Autonomous VehiclesMedical Diagnosis

A deep learning algorithm for optimal investment strategies

2021-01-29 · Daeyung Gim, Hyungbin Park

This paper treats the Merton problem how to invest in safe assets and risky assets to maximize an investor's utility, given by investment opportunities modeled by a $d$-dimensional state process. The problem is represent…

Deep Learning

DEQGAN: Learning the Loss Function for PINNs with Generative Adversarial Networks

2022-09-15 · Blake Bullwinkel, Dylan Randle, Pavlos Protopapas, David Sondak

Solutions to differential equations are of significant scientific and engineering relevance. Physics-Informed Neural Networks (PINNs) have emerged as a promising method for solving differential equations, but they lack a…

Symbolic Discovery of Stochastic Differential Equations with Genetic Programming

2026-03-10 · Sigur de Vries, Sander W. Keemink, Marcel A. J. van Gerven arxiv

Automated scientific discovery aims to improve scientific understanding through machine learning. A central approach in this field is symbolic regression, which uses genetic programming or sparse regression to learn inte…

Enhanced Physics-Informed Neural Networks with Augmented Lagrangian Relaxation Method (AL-PINNs)

2022-04-29 · Hwijae Son, Sung Woong Cho, Hyung Ju Hwang

Physics-Informed Neural Networks (PINNs) have become a prominent application of deep learning in scientific computation, as they are powerful approximators of solutions to nonlinear partial differential equations (PDEs).…