REVIEW 3 cited by
Born-Infeld (BI) for AI: Energy-Conserving Descent (ECD) for Optimization
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
We introduce a novel framework for optimization based on energy-conserving Hamiltonian dynamics in a strongly mixing (chaotic) regime and establish its key properties analytically and numerically. The prototype is a discretization of Born-Infeld dynamics, with a squared relativistic speed limit depending on the objective function. This class of frictionless, energy-conserving optimizers proceeds unobstructed until slowing naturally near the minimal loss, which dominates the phase space volume of the system. Building from studies of chaotic systems such as dynamical billiards, we formulate a specific algorithm with good performance on machine learning and PDE-solving tasks, including generalization. It cannot stop at a high local minimum, an advantage in non-convex loss functions, and proceeds faster than GD+momentum in shallow valleys.
Forward citations
Cited by 3 Pith papers
-
The Optimiser Hidden in Plain Sight: Training with the Loss Landscape's Induced Metric
A geometrically derived optimizer that rescales gradients by 1/(1+ξ||∇L||²) is competitive with AdamW and Muon, with one RMS-based variant showing slight average improvement.
-
Pre-Strings Lectures on Artificial Intelligence
Lecture notes define neural-network field theory and survey how it recovers known QFT/string results plus applied AI techniques for string problems.
-
Machine Learning Gravity Compactifications on Negatively Curved Manifolds
A neural network is trained to solve the Einstein equations on a Dehn-filled hyperbolic three-manifold, cutting the equation residual to about a percent and serving as a proof-of-concept for machine-learning gravity c...
Discussion (0). Continue with ORCID to comment.