Natalia Ares — accepted AI-conference papers

2026

A Physics-Inspired Optimizer: Velocity Regularized Adam

Pranav Vaidhyanathan, Lucas Schorling, Natalia Ares, Michael A Osborne

ICLR 2026poster

We introduce Velocity-Regularized Adam (VRAdam), a physics-inspired optimizer for training deep neural networks that draws on ideas from quartic terms for kinetic energy with its stabilizing effects on various system dynamics. Previous algorithms, including the ubiquitous Adam, operate at the so-ca…

Cited by 0 Source ↗Scholar ↗

2024

Looping in the Human: Collaborative and Explainable Bayesian Optimization

Masaki Adachi, Brady Planden, David Howey, Michael A. Osborne, Sebastian Orbell, Natalia Ares +2

AISTATS 2024poster

Like many optimizers, Bayesian optimization often falls short of gaining user trust due to opacity. While attempts have been made to develop human-centric optimizers, they typically assume user knowledge is well-specified and error-free, employing users mainly as supervisors of the optimization proc…

Cited by 19 Source ↗PDF ↗code ↗Scholar ↗