REVIEW 3 cited by
PAC Confidence Sets for Deep Neural Networks via Calibrated Prediction
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
We propose an algorithm combining calibrated prediction and generalization bounds from learning theory to construct confidence sets for deep neural networks with PAC guarantees---i.e., the confidence set for a given input contains the true label with high probability. We demonstrate how our approach can be used to construct PAC confidence sets on ResNet for ImageNet, a visual object tracking model, and a dynamics model for the half-cheetah reinforcement learning problem.
Forward citations
Cited by 3 Pith papers
-
How Many Iterations to Jailbreak? Dynamic Budget Allocation for Multi-Turn LLM Evaluation
DAPRO provides the first dynamic, theoretically guaranteed way to allocate interaction budgets across test cases for bounding time-to-event in multi-turn LLM evaluations, achieving tighter coverage than static conform...
-
Position: There Is No Free Bayesian Uncertainty Quantification
Bayesian updating is reframed as an optimization problem without inherent uncertainty quantification, and a PAC-style calibration step is proposed to give predictive intervals frequentist coverage.
-
Fundus Image-based Visual Acuity Assessment with PAC-Guarantees
A model predicts visual acuity from fundus images with PAC-guaranteed prediction intervals, achieving 71.49% coverage at a 70% target on a 0 to 10 scale.
Discussion (0). Continue with ORCID to comment.