works on
hardy-space analyticity 1kramers-kronig relations 1memory kernel 1non-unitary exchange statistics 1open quantum systems 1paraparticles 1

From the 1 of 9 linked papers with an AI index.

collaborators
Showing cs.LGShow all

1 paper · 1 filter

cs.LG2026

The Predictive-Causal Gap: An Impossibility Theorem and Large-Scale Neural Evidence

Kejun Liu

We report a systematic failure mode in predictive representation learning. Across 2695 neural network configurations trained to predict linear-Gaussian dynamics, the optimal encode…