Presents the first formal Subjective Logic framework for uncertainty-aware assessment of dataset-level trustworthiness properties such as bias, evaluated on a traffic sign recognition dataset in centralized and federated settings.
The Optimal Sample Complexity of PAC Learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
This work establishes a new upper bound on the number of samples sufficient for PAC learning in the realizable case. The bound matches known lower bounds up to numerical constant factors. This solves a long-standing open problem on the sample complexity of PAC learning. The technique and analysis build on a recent breakthrough by Hans Simon.
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Assessing Trustworthiness of AI Training Dataset using Subjective Logic -- A Use Case on Bias
Presents the first formal Subjective Logic framework for uncertainty-aware assessment of dataset-level trustworthiness properties such as bias, evaluated on a traffic sign recognition dataset in centralized and federated settings.