A deep neural network estimator using a continuous hinge-type surrogate loss achieves minimax-optimal boundary recovery rates up to logs for piecewise smooth boundaries in unlabeled noisy images.
An approach to large-scale quasi-Bayesian inference with spike-and-slab priors.arXiv preprint arXiv:1803.10282
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Early-stopped aggregation performs adaptive model selection and aggregation by halting at simpler models via an early-stopping criterion, achieving optimal contraction rates with reduced computation in variational Bayes and penalized estimation.
citing papers explorer
-
Rate-optimal neural boundary detection from unlabeled noisy images
A deep neural network estimator using a continuous hinge-type surrogate loss achieves minimax-optimal boundary recovery rates up to logs for piecewise smooth boundaries in unlabeled noisy images.
-
Early-stopped aggregation: Adaptive inference with computational efficiency
Early-stopped aggregation performs adaptive model selection and aggregation by halting at simpler models via an early-stopping criterion, achieving optimal contraction rates with reduced computation in variational Bayes and penalized estimation.