{"record":{"author":{"account_ref":null,"orcid":null},"builds_on":[],"content_schema":"pubphys.content.topic/1","content_sha256":"b2d215727d57da36a95f942fb523cb6edc53d497d1d8cc54de53b5efc3815564","created":"2026-10-03T07:17:53Z","files":[],"origin":{"assisted_by":[],"kind":"seed"},"parents":[],"salt":"2b03118c8568c8f8ff2ad4d13f75a6ee16d49c78c3a589b33a290164de09ae2e","schema":"pubphys.record/2","site":"pubphys.com","target":null,"type":"topic"},"content":{"external_id":"stat.learning-inference","field":"stat","n":"1","review_cite":"L. Zdeborova and F. Krzakala, Statistical physics of inference: thresholds and algorithms, Advances in Physics 65, 2016","review_link":"https://doi.org/10.1080/00018732.2016.1211393","review_verified":"true","summary":"Methods from the physics of disordered systems explain how well large learning machines and statistical estimators can work, and when a hidden signal is present in data but no fast algorithm can find it. The same tools describe memory networks that store and recall patterns.","title":"Statistical physics of learning and inference","topic_ref":null,"why":"It gives quantitative laws for how machine learning improves with size and data, and separates limits set by information from limits set by computation."},"attested":{"attestation":{"batch":null,"client_id":null,"id_token_sha256":null,"kind":"platform"},"record_hash":"e915a7e12556cfb0adf583a894af7480127cf4267dc4e2458650f4872a864ed1","schema":"pubphys.attested/1"},"envelope":{"attested_hash":"7b75aed5d8da1f0f66017e06ae99cf166486c9e07bac8f6ce9714b26954b98f2","platform_signature":{"key_id":"c6afc19b31429869751f06879c75cd64ea92654423d15b44be775bf1310a60da","sig":"pWPOziO5_pTWCgBUUyB_i_iD6ikrI3OEXYeuimFg2BM902pgksemHh0zkHBkK67MQywKPNII5tugORuonyDzAg"},"schema":"pubphys.envelope/1"},"record_hash":"e915a7e12556cfb0adf583a894af7480127cf4267dc4e2458650f4872a864ed1","leaf_index":355}