Risk-controlled post-processing yields a threshold-structured policy that follows the baseline except where an oracle fallback sharply reduces conditional violation risk, achieving O(log n/n) expected excess risk in i.i.d. settings and exact risk control under exchangeability.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
Proves node subsampling asymptotically approximates joint distribution of network moments under sparse graphon, enabling two-sample tests for unmatchable networks with unequal densities.
Unified framework relaxes spectral constraints and provides parameter-free guarantees linking practical algorithms to MLE for latent space network models.
citing papers explorer
-
Risk-Controlled Post-Processing of Decision Policies
Risk-controlled post-processing yields a threshold-structured policy that follows the baseline except where an oracle fallback sharply reduces conditional violation risk, achieving O(log n/n) expected excess risk in i.i.d. settings and exact risk control under exchangeability.
-
Multivariate Inference of Network Moments by Subsampling
Proves node subsampling asymptotically approximates joint distribution of network moments under sparse graphon, enabling two-sample tests for unmatchable networks with unequal densities.
-
Bridging Theory and Practice: Statistical Inference for Latent Space Models of Networks
Unified framework relaxes spectral constraints and provides parameter-free guarantees linking practical algorithms to MLE for latent space network models.