Proposes pointwise Riemannian Dimension from feature eigenvalues to derive tighter, representation-aware generalization bounds for deep networks in the nonlinear regime.
A Note on the PAC Bayesian Theorem
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
abstract
We prove general exponential moment inequalities for averages of [0,1]-valued iid random variables and use them to tighten the PAC Bayesian Theorem. The logarithmic dependence on the sample count in the enumerator of the PAC Bayesian bound is halved.
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
PAC-Bayesian bounds are derived for quadratic closed-loop control via SLS parameterization, yielding Chernoff certificates for posteriors over responses, a mean-response deployment result, and a data-driven learning algorithm.
Introduces a fairness layer for deep learning models that guarantees output parity and an online primal-dual algorithm for aggregate fairness guarantees in streaming predictions with small batch sizes.
Federated learning trains private local randomised predictors whose aggregation yields a global predictor with nonvacuous PAC-Bayesian generalisation bounds and near-centralized accuracy.
Establishes a complete non-asymptotic theory of rational commitment thresholds for BMA over BDTs with Dirichlet-Multinomial leaves and Catalan-exponential tree-size priors.
Learning a margin-based confidence ranker for LLM judges improves agreement-target success in cascaded selective evaluation compared to heuristic confidence scores.
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.
-
PAC-Bayesian Certificates for Quadratic Closed-Loop Control
PAC-Bayesian bounds are derived for quadratic closed-loop control via SLS parameterization, yielding Chernoff certificates for posteriors over responses, a mean-response deployment result, and a data-driven learning algorithm.
-
Differentiable Optimization Layers for Guaranteed Fairness in Deep Learning
Introduces a fairness layer for deep learning models that guarantees output parity and an online primal-dual algorithm for aggregate fairness guarantees in streaming predictions with small batch sizes.
-
Federated Learning with Nonvacuous Generalisation Bounds
Federated learning trains private local randomised predictors whose aggregation yields a global predictor with nonvacuous PAC-Bayesian generalisation bounds and near-centralized accuracy.
-
Sample Complexity and Decision-Theoretic Guarantees for Bayesian Model Averaging over Decision Trees with Catalan-Exponential Priors
Establishes a complete non-asymptotic theory of rational commitment thresholds for BMA over BDTs with Dirichlet-Multinomial leaves and Catalan-exponential tree-size priors.
-
Margin-Adaptive Confidence Ranking for Reliable LLM Judgement
Learning a margin-based confidence ranker for LLM judges improves agreement-target success in cascaded selective evaluation compared to heuristic confidence scores.