Accelerating Optimization via Differentiable Stopping Time
NeurIPSSpotlight2025
TL;DR
A common approach for accelerating optimization algorithms is to minimize the loss achieved in a fixed time, which enables a differentiable framework with respect to the algorithm's hyperparameters…
Opening excerpt from the authors’ abstract. source
Read the paper
Topics
optimization
← All NeurIPS 2025 Spotlight papers · Browse the whole archive