AI RESEARCH
Unlearnable phases of matter
arXiv CS.LG
•
ArXi:2602.11262v2 Announce Type: replace-cross We identify fundamental limitations in machine learning by nstrating that non-trivial mixed-state phases of matter are computationally hard to learn. Focusing on unsupervised learning of distributions, we show that autoregressive neural networks fail to learn global properties of distributions characterized by locally indistinguishable (LI) states. We nstrate that conditional mutual information (CMI) is a useful diagnostic for LI: we show that for classical distributions, long-range CMI of a state implies a spatially LI partner. By.