paper-with-me

Papers

Improving Energy Conserving Descent for Machine Learning: Theory and Practice

2023-06-01 · 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. The method is based on the novel ECD framework of optimization as physical evolution of a suitable chaotic energy-conserving dynamical system, enabling analytic control of the distribution of results - dominated at low loss - even for generic high-dimensional problems with no symmetries. Compared to previous realizations of this idea, we exploit the theoretical control to improve both the dynamics and chaos-inducing elements, enhancing performance while simplifying the hyper-parameter tuning of the optimization algorithm targeted to different classes of problems. We empirically compare with popular optimization methods such as SGD, Adam and AdamW on a wide range of machine learning problems, finding competitive or improved performance compared to the best among them on each task. We identify limitations in our analysis pointing to possibilities for additional improvements.

📄 PDF Abstract BibTeX arXiv:2306.00352

Code (1)

gbdl/ecdsep 공식 구현 pytorch

Tasks

Learning Theory

Methods 이 논문이 사용한 방법론

Adam 설명 없음
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…
AdamW AdamW is a stochastic optimization method that modifies the typical implementation of weight decay in Adam, by decoupling [weight…

Similar Papers 제목 키워드 기반

Classical and Quantum Speedups for Non-Convex Optimization via Energy Conserving Descent

2026-04-14 · Yihang Sun, Huaijin Wang, Patrick Hayden, Jose Blanchet arxiv

The Energy Conserving Descent (ECD) algorithm was recently proposed (De Luca & Silverstein, 2022) as a global non-convex optimization method. Unlike gradient descent, appropriately configured ECD dynamics escape strict l…

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

2022-01-26 · 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. The prototype is a disc…

Benchmarking Energy-Conserving Neural Networks for Learning Dynamics from Data

2020-12-03 · Yaofeng Desmond Zhong, Biswadip Dey, Amit Chakraborty

The last few years have witnessed an increased interest in incorporating physics-informed inductive bias in deep learning frameworks. In particular, a growing volume of literature has been exploring ways to enforce energ…

BenchmarkingInductive BiasTime SeriesTime Series Analysis

Stabilization of Energy-Conserving Gaits for Point-Foot Planar Bipeds

2022-10-26 · Aakash Khandelwal, Nilay Kant, Ranjan Mukherjee

The problem of designing and stabilizing impact-free, energy-conserving gaits is considered for underactuated, point-foot planar bipeds. Virtual holonomic constraints are used to design energy-conserving gaits. A desired…

Pseudo-Hamiltonian Neural Networks with State-Dependent External Forces

2022-06-06 · Sølve Eidnes, Alexander J. Stasik, Camilla Sterud, Eivind Bøhn 외

Hybrid machine learning based on Hamiltonian formulations has recently been successfully demonstrated for simple mechanical systems, both energy conserving and not energy conserving. We introduce a pseudo-Hamiltonian for…

Hybrid Machine Learning