REVIEW 2 cited by
Learning to Benchmark: Determining Best Achievable Misclassification Error from Training Data
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
abstract
We address the problem of learning to benchmark the best achievable classifier performance. In this problem the objective is to establish statistically consistent estimates of the Bayes misclassification error rate without having to learn a Bayes-optimal classifier. Our learning to benchmark framework improves on previous work on learning bounds on Bayes misclassification rate since it learns the {\it exact} Bayes error rate instead of a bound on error rate. We propose a benchmark learner based on an ensemble of $\epsilon$-ball estimators and Chebyshev approximation. Under a smoothness assumption on the class densities we show that our estimator achieves an optimal (parametric) mean squared error (MSE) rate of $O(N^{-1})$, where $N$ is the number of samples. Experiments on both simulated and real datasets establish that our proposed benchmark learning algorithm produces estimates of the Bayes error that are more accurate than previous approaches for learning bounds on Bayes error probability.
Forward citations
Cited by 2 Pith papers
-
Bounding Neyman-Pearson Region with $f$-Divergences
Every f-divergence yields a constraint on the achievable error region of a binary test, the hockey-stick family makes these constraints exactly tight, and any Neyman-Pearson boundary can be realized by a specially con...
-
Universal Training of Neural Networks to Achieve Bayes Optimal Classification Accuracy
BOLT, a loss derived from an f-divergence bound on Bayes error, matches or slightly beats cross-entropy on MNIST, Fashion-MNIST, CIFAR-10, and IMDb.
Discussion (0). Continue with ORCID to comment.