Contrastive pair presentations yield exact identifiability characterizations via a geometric refinement of Angluin's condition, a new contrastive closure dimension for generation, mutual incomparability with text identification, and a single algorithm that tolerates any finite corruption budget.
Forty-first International Conference on Machine Learning , year=
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4representative citing papers
Perturbing prefixes to semantic neighbors during training creates a hierarchical noise model that improves language model predictions on token sequences outside the training corpus support.
pFLAlign uses two gradient alignment mechanisms derived from PAC-Bayesian analysis to reduce variance in local training and distortion in aggregation, yielding state-of-the-art personalization in federated learning.
citing papers explorer
-
Contrastive Identification and Generation in the Limit
Contrastive pair presentations yield exact identifiability characterizations via a geometric refinement of Angluin's condition, a new contrastive closure dimension for generation, mutual incomparability with text identification, and a single algorithm that tolerates any finite corruption budget.
-
Perturbation is All You Need for Extrapolating Language Models
Perturbing prefixes to semantic neighbors during training creates a hierarchical noise model that improves language model predictions on token sequences outside the training corpus support.
-
Personalized Federated Learning for Gradient Alignment
pFLAlign uses two gradient alignment mechanisms derived from PAC-Bayesian analysis to reduce variance in local training and distortion in aggregation, yielding state-of-the-art personalization in federated learning.
- Simply Stabilizing the Loop via Fully Looped Transformer