Sample-compressible distribution families are shown to be PAC-learnable under additive noise and adversarial corruption, given new stability and low-frequency assumptions.
Near-optimal sample complexity bounds for robust learning of gaussian mixtures via compression schemes
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
stat.ML 1years
2025 1verdicts
REJECT 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Robust Learnability of Sample-Compressible Distributions under Noisy or Adversarial Perturbations
Sample-compressible distribution families are shown to be PAC-learnable under additive noise and adversarial corruption, given new stability and low-frequency assumptions.