A data-driven variational discretization of Onsager's principle learns uncertain free-energy and dissipation functionals from observations while guaranteeing provable energy stability for arbitrarily long simulations.
Schiff, and Y
5 Pith papers cite this work, alongside 9 external citations. Polarity classification is still indexing.
5
Pith papers citing it
9
external citations · external index
verdicts
UNVERDICTED 5representative citing papers
AI weather models may simulate the atmosphere via particle positions in latent space whose updates follow gradient flow on a learned free energy functional rather than conventional physical equations.
A single-network implicit neural optimal transport method that solves the c-transform via proximal fixed-point iteration for stable, non-adversarial training.
MGP uses a MERGE-based Markovian process from linguistic minimalism to discover and combine atomic building blocks into exact symbolic regression models, avoiding bloat when a suitable lexicon is provided.
A new differentiable layer with convex parameter space universally approximates generalized convex functions and their gradients, enabling single-level reformulations of bilevel problems in optimal transport and multi-good auctions.
citing papers explorer
-
Flexible and Stable Dynamics Discovery with Onsager's Variational Principle
A data-driven variational discretization of Onsager's principle learns uncertain free-energy and dissipation functionals from observations while guaranteeing provable energy stability for arbitrarily long simulations.
-
The physics of AI weather models
AI weather models may simulate the atmosphere via particle positions in latent space whose updates follow gradient flow on a learned free energy functional rather than conventional physical equations.
-
Implicit Neural Optimal Transport via Fixed-Point Optimization
A single-network implicit neural optimal transport method that solves the c-transform via proximal fixed-point iteration for stable, non-adversarial training.
-
Minimalist Genetic Programming
MGP uses a MERGE-based Markovian process from linguistic minimalism to discover and combine atomic building blocks into exact symbolic regression models, avoiding bloat when a suitable lexicon is provided.
-
Universal Representation of Generalized Convex Functions and their Gradients
A new differentiable layer with convex parameter space universally approximates generalized convex functions and their gradients, enabling single-level reformulations of bilevel problems in optimal transport and multi-good auctions.