Improving Energy Conserving Descent for Machine Learning: Theory and Practice

1 code implementation • 1 Jun 2023 • G. Bruno De Luca, Alice Gatti, Eva Silverstein

We develop the theory of Energy Conserving Descent (ECD) and introduce ECDSep, a gradient-based optimization algorithm able to tackle convex and non-convex optimization problems.

Learning Theory

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

1 code implementation • 26 Jan 2022 • G. Bruno De Luca, Eva Silverstein

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.