Proves that Rademacher complexity of depth-d compositional trees over finite operator vocabulary is controlled by (K b L)^{d} / sqrt(n) under Lipschitz conditions on operators.
PAC - B ayesian Supervised Classification: The Thermodynamics of Statistical Learning , volume 56 of Lecture Notes---Monograph Series
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4verdicts
UNVERDICTED 4representative citing papers
S²R² improves robustness of LoRA-tuned LLMs to prompt perturbations by penalizing semantic-segment drift while preserving clean performance and cross-dataset transfer.
A single algebraic mixed-coincidence identity is proved that recovers Sanov decompositions, Chernoff information, PAC-Bayes bounds, and Renyi variational formulas as special cases while generalizing them to any number of priors.
Derives smoothness-based PAC-Bayes derandomization bounds for deterministic predictors using Rademacher complexity of the Jensen gap class, yielding Jacobian/Hessian flatness terms and a practical regularizer tested on CIFAR-10.
citing papers explorer
-
Sample Complexity of Scientific Discovery: PAC Learnability of Compositional Function Trees
Proves that Rademacher complexity of depth-d compositional trees over finite operator vocabulary is controlled by (K b L)^{d} / sqrt(n) under Lipschitz conditions on operators.
-
Where Do Prompt Perturbations Break Generation? A Segment-Level View of Robustness in LoRA-Tuned Language Models
S²R² improves robustness of LoRA-tuned LLMs to prompt perturbations by penalizing semantic-segment drift while preserving clean performance and cross-dataset transfer.
-
Information from coincidences
A single algebraic mixed-coincidence identity is proved that recovers Sanov decompositions, Chernoff information, PAC-Bayes bounds, and Renyi variational formulas as special cases while generalizing them to any number of priors.
-
Smoothness-Based Derandomization of PAC-Bayes Bounds
Derives smoothness-based PAC-Bayes derandomization bounds for deterministic predictors using Rademacher complexity of the Jensen gap class, yielding Jacobian/Hessian flatness terms and a practical regularizer tested on CIFAR-10.