Martingale Neural Operator uses Doob-Meyer factorization to output mean and low-rank covariance for stochastic PDE terminal laws, achieving large Wasserstein reductions versus diffusion baselines on tested SPDEs.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Grokking delay arises from attention performing delayed Bayesian inference over task structure after MLP memorization drives loss to zero; a KL structural intervention bypasses the inverse-weight-decay scaling.
citing papers explorer
-
Martingale Neural Operators: Learning Stochastic Marginals via Doob-Meyer Factorization
Martingale Neural Operator uses Doob-Meyer factorization to output mean and low-rank covariance for stochastic PDE terminal laws, achieving large Wasserstein reductions versus diffusion baselines on tested SPDEs.
-
Grokking as Structural Inference: Transformers Need Bayesian Lottery Tickets
Grokking delay arises from attention performing delayed Bayesian inference over task structure after MLP memorization drives loss to zero; a KL structural intervention bypasses the inverse-weight-decay scaling.