Neural LoFi models deep learning as layer-wise spectral filtering that selects maximal low-degree correlations, yielding a tractable surrogate for hierarchical representation learning beyond the lazy regime.
Asymp- totics of non-convex generalized linear models in high-dimensions: A proof of the replica formula
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 5verdicts
UNVERDICTED 5roles
background 2polarities
background 2representative citing papers
Linear associative memories store up to p_c log p_c / d^2 = 1/2 associations, with optimal weights pushing correct scores just above the extreme value of competing outputs.
Characterizes training error and test-training relation for an IAMP algorithm in multi-index ERM under high-d asymptotics, expecting optimality among polynomial-time methods based on prior related models.
Quadratic two-layer networks exhibit data-dependent power-law generalization scaling with distinct regimes in width and sample size, including an interpolation transition whose location depends on target spectrum.
This review synthesizes representative advances in high-dimensional statistics, highlights common themes and open problems, and points to key entry works.
citing papers explorer
-
Factual recall in linear associative memories: sharp asymptotics and mechanistic insights
Linear associative memories store up to p_c log p_c / d^2 = 1/2 associations, with optimal weights pushing correct scores just above the extreme value of competing outputs.