Conformal Symplectic and Relativistic Optimization
From MaRDI portal
Publication:6315372
DOI10.1088/1742-5468/ABCAEEarXiv1903.04100MaRDI QIDQ6315372FDOQ6315372
Authors: G. S. França, Jeremias Sulam, Daniel P. Robinson, René Vidal 
Publication date: 10 March 2019
Abstract: Arguably, the two most popular accelerated or momentum-based optimization methods in machine learning are Nesterov's accelerated gradient and Polyaks's heavy ball, both corresponding to different discretizations of a particular second order differential equation with friction. Such connections with continuous-time dynamical systems have been instrumental in demystifying acceleration phenomena in optimization. Here we study structure-preserving discretizations for a certain class of dissipative (conformal) Hamiltonian systems, allowing us to analyze the symplectic structure of both Nesterov and heavy ball, besides providing several new insights into these methods. Moreover, we propose a new algorithm based on a dissipative relativistic system that normalizes the momentum and may result in more stable/faster optimization. Importantly, such a method generalizes both Nesterov and heavy ball, each being recovered as distinct limiting cases, and has potential advantages at no additional cost.
This page was built for publication: Conformal Symplectic and Relativistic Optimization
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6315372)
