SGD, approximations of Newton's method, natural gradient descent, and Adam are proven compatible with evolutionary dynamics when augmented with DLS noise, turning them into valid in silico simulations of asexual Darwinian evolution.
Proceedings of the 35th International Conference on Machine Learning , pages =
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 3verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
SOAP and SOAP-Muon optimizers deliver faster convergence and higher final accuracy than Adam for NequIP and Allegro MLIPs, with the largest gains under partial force supervision.
Adam's adaptive preconditioning and first-moment averaging improve high-probability tracking error in noise-dominated nonstationary regimes but can increase it under strong drift, where SGD achieves a smaller floor, with explicit beta-dependent bounds.
citing papers explorer
-
Direct From Darwin: Deriving Advanced Optimizers From Evolutionary First Principles
SGD, approximations of Newton's method, natural gradient descent, and Adam are proven compatible with evolutionary dynamics when augmented with DLS noise, turning them into valid in silico simulations of asexual Darwinian evolution.
-
Beyond Adam: SOAP and Muon for Faster, Label-Efficient Training of Machine Learning Interatomic Potentials
SOAP and SOAP-Muon optimizers deliver faster convergence and higher final accuracy than Adam for NequIP and Allegro MLIPs, with the largest gains under partial force supervision.
-
Adapt or Forget: Provable Tradeoffs Between Adam and SGD in Nonstationary Optimization
Adam's adaptive preconditioning and first-moment averaging improve high-probability tracking error in noise-dominated nonstationary regimes but can increase it under strong drift, where SGD achieves a smaller floor, with explicit beta-dependent bounds.