Semantic geometry emerges transiently early in next-token prediction training before collapsing to Neural Collapse symmetry in synthetic settings with latent semantic factors.
Beyond lipschitz: Sharp general$ ization and excess risk bounds for full$batch gd
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
verdicts
UNVERDICTED 4representative citing papers
High-probability generalization bounds for D-SGD are derived at the optimal rate O(1/sqrt(mn) log(1/δ)) via pointwise uniform stability across convex and non-convex settings.
Decentralized SGD and SGDA under Markovian sampling admit non-asymptotic generalization bounds that incorporate network topology, Markov mixing rates, and primal-dual dynamics.
A model-independent upper bound on generalization gap is established that depends solely on the Rényi entropy of the data-generating distribution for histogram-determined algorithms such as ERM.
citing papers explorer
-
Structure Before Collapse: Transient semantic geometry in next-token prediction
Semantic geometry emerges transiently early in next-token prediction training before collapsing to Neural Collapse symmetry in synthetic settings with latent semantic factors.
-
Unveiling High-Probability Generalization in Decentralized SGD
High-probability generalization bounds for D-SGD are derived at the optimal rate O(1/sqrt(mn) log(1/δ)) via pointwise uniform stability across convex and non-convex settings.
-
Stability and Generalization for Decentralized Markov SGD
Decentralized SGD and SGDA under Markovian sampling admit non-asymptotic generalization bounds that incorporate network topology, Markov mixing rates, and primal-dual dynamics.
-
Overfitting has a limitation: a model-independent generalization gap bound based on R\'enyi entropy
A model-independent upper bound on generalization gap is established that depends solely on the Rényi entropy of the data-generating distribution for histogram-determined algorithms such as ERM.