We introduce a novel framework for optimization based on energy-conserving Hamiltonian dynamics in a strongly mixing (chaotic) regime and establish its key properties analytically and numerically. The prototype is a discretization of Born-Infeld dynamics, with a squared relativistic speed limit depending on the objective function. This class of frictionless, energy-conserving optimizers proceeds unobstructed until slowing naturally near the minimal loss, which dominates the phase space volume of the system. Building from studies of chaotic systems such as dynamical billiards, we formulate a specific algorithm with good performance on machine learning and PDE-solving tasks, including generalization. It cannot stop at a high local minimum, an advantage in non-convex loss functions, and proceeds faster than GD+momentum in shallow valleys.

De Luca, G., Silverstein, E. (2022). Born-Infeld (BI) for AI: Energy-Conserving Descent (ECD) for Optimization. In 39th International Conference on Machine Learning, ICML 2022 (pp.4918-4936). ML Research Press.

Born-Infeld (BI) for AI: Energy-Conserving Descent (ECD) for Optimization

De Luca, GB;
2022

Abstract

We introduce a novel framework for optimization based on energy-conserving Hamiltonian dynamics in a strongly mixing (chaotic) regime and establish its key properties analytically and numerically. The prototype is a discretization of Born-Infeld dynamics, with a squared relativistic speed limit depending on the objective function. This class of frictionless, energy-conserving optimizers proceeds unobstructed until slowing naturally near the minimal loss, which dominates the phase space volume of the system. Building from studies of chaotic systems such as dynamical billiards, we formulate a specific algorithm with good performance on machine learning and PDE-solving tasks, including generalization. It cannot stop at a high local minimum, an advantage in non-convex loss functions, and proceeds faster than GD+momentum in shallow valleys.
paper
Energy conservation; Hamiltonians; Machine learning; Optimization
English
39th International Conference on Machine Learning (ICML) - JUL 17-23, 2022
2022
Chaudhuri, K; Jegelka, S; Song, L; Szepesvari, C; Niu, G; Sabato, S
39th International Conference on Machine Learning, ICML 2022
2022
162
4918
4936
https://proceedings.mlr.press/v162/de-luca22a.html
open
De Luca, G., Silverstein, E. (2022). Born-Infeld (BI) for AI: Energy-Conserving Descent (ECD) for Optimization. In 39th International Conference on Machine Learning, ICML 2022 (pp.4918-4936). ML Research Press.
File in questo prodotto:
File Dimensione Formato  
De Luca-2022-Proceedings of Machine Learning Research-VoR.pdf

accesso aperto

Tipologia di allegato: Publisher’s Version (Version of Record, VoR)
Licenza: Creative Commons
Dimensione 4.5 MB
Formato Adobe PDF
4.5 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/10281/488900
Citazioni
  • Scopus 0
  • ???jsp.display-item.citation.isi??? 0
Social impact