paper-with-me

홈 › Papers

Optimization on manifolds: A symplectic approach

2021-07-23 · Guilherme França, Alessandro Barp, Mark Girolami, Michael I. Jordan

Optimization tasks are crucial in statistical machine learning. Recently, there has been great interest in leveraging tools from dynamical systems to derive accelerated and robust optimization methods via suitable discretizations of continuous-time systems. However, these ideas have mostly been limited to Euclidean spaces and unconstrained settings, or to Riemannian gradient flows. In this work, we propose a dissipative extension of Dirac's theory of constrained Hamiltonian systems as a general framework for solving optimization problems over smooth manifolds, including problems with nonlinear constraints. We develop geometric/symplectic numerical integrators on manifolds that are "rate-matching," i.e., preserve the continuous-time rates of convergence. In particular, we introduce a dissipative RATTLE integrator able to achieve optimal convergence rate locally. Our class of (accelerated) algorithms are not only simple and efficient but also applicable to a broad range of contexts.

📄 PDF Abstract BibTeX arXiv:2107.11231

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Symplectic model reduction of Hamiltonian systems using data-driven quadratic manifolds

2023-05-24 · Harsh Sharma, Hongliang Mu, Patrick Buchfink, Rudy Geelen 외

This work presents two novel approaches for the symplectic model reduction of high-dimensional Hamiltonian systems using data-driven quadratic manifolds. Classical symplectic model reduction approaches employ linear symp…

Learning symplectic model reduction based on a approximation theorem of symplectic embeddings

2026-06-03 · Liyi Feng, Yifa Tang, Yulin Xie, Ruili Zhang 외 arxiv

High-dimensional Hamiltonian systems play a central role in many scientific and engineering disciplines, with dynamics evolving on symplectic manifolds. Although deep learning provides powerful tools for constructing low…

Generalizing Adam to Manifolds for Efficiently Training Transformers

2023-05-26 · Benedikt Brantner

One of the primary reasons behind the success of neural networks has been the emergence of an array of new, highly-successful optimizers, perhaps most importantly the Adam optimizer. It is widely used for training neural…

Physical Intuition

Riemannian coordinate descent algorithms on matrix manifolds

2024-06-04 · Andi Han, Pratik Jawanpuria, Bamdev Mishra

Many machine learning applications are naturally formulated as optimization problems on Riemannian manifolds. The main idea behind Riemannian optimization is to maintain the feasibility of the variables while moving alon…

Riemannian optimization

Symmetry Preservation in Hamiltonian Systems: Simulation and Learning

2023-08-30 · Miguel Vaquero, Jorge Cortés, David Martín de Diego

This work presents a general geometric framework for simulating and learning the dynamics of Hamiltonian systems that are invariant under a Lie group of transformations. This means that a group of symmetries is known to …