Hamiltonian Descent Algorithms for Optimization: Accelerated Rates via Randomized Integration Time

NeurIPSSpotlight2025

Authors
Qiang Fu, Andre Wibisono
Venue
NeurIPS 2025
Track
Spotlight

TL;DR

We study the Hamiltonian flow for optimization (HF-opt), which simulates the Hamiltonian dynamics for some integration time and resets the velocity to $0$ to decrease the objective function; this is t…

Opening excerpt from the authors’ abstract. source

Read the paper

Topics

optimization

← All NeurIPS 2025 Spotlight papers · Browse the whole archive