Generalization bounds: Perspectives from information theory and PAC-Bayes
A fundamental question in theoretical machine learning is generalization. Over the past
decades, the PAC-Bayesian approach has been established as a flexible framework to …
decades, the PAC-Bayesian approach has been established as a flexible framework to …
Single Trajectory Conformal Prediction
B Lee, N Matni - arxiv preprint arxiv:2406.01570, 2024 - arxiv.org
We study the performance of risk-controlling prediction sets (RCPS), an empirical risk
minimization-based formulation of conformal prediction, with a single trajectory of temporally …
minimization-based formulation of conformal prediction, with a single trajectory of temporally …
Formal verification and control with conformal prediction
In this survey, we design formal verification and control algorithms for autonomous systems
with practical safety guarantees using conformal prediction (CP), a statistical tool for …
with practical safety guarantees using conformal prediction (CP), a statistical tool for …
Generalization and informativeness of conformal prediction
The safe integration of machine learning modules in decision-making processes hinges on
their ability to quantify uncertainty. A popular technique to achieve this goal is conformal …
their ability to quantify uncertainty. A popular technique to achieve this goal is conformal …
Bridging model heterogeneity in federated learning via uncertainty-based asymmetrical reciprocity learning
This paper presents FedType, a simple yet pioneering framework designed to fill research
gaps in heterogeneous model aggregation within federated learning (FL). FedType …
gaps in heterogeneous model aggregation within federated learning (FL). FedType …
PAC-Bayes Analysis for Recalibration in Classification
Nonparametric estimation with binning is widely employed in the calibration error evaluation
and the recalibration of machine learning models. Recently, theoretical analyses of the bias …
and the recalibration of machine learning models. Recently, theoretical analyses of the bias …