Proposes pointwise Riemannian Dimension from feature eigenvalues to derive tighter, representation-aware generalization bounds for deep networks in the nonlinear regime.
Foundations and Trends
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
PAC-Bayes framework derives high-probability performance bounds for learned controllers on unknown stochastic linear discrete-time systems and provides efficient algorithms for finite and infinite controller spaces.
citing papers explorer
-
Pointwise Generalization in Deep Neural Networks
Proposes pointwise Riemannian Dimension from feature eigenvalues to derive tighter, representation-aware generalization bounds for deep networks in the nonlinear regime.
-
A PAC-Bayes Approach for Controlling Unknown Linear Discrete-time Systems
PAC-Bayes framework derives high-probability performance bounds for learned controllers on unknown stochastic linear discrete-time systems and provides efficient algorithms for finite and infinite controller spaces.