Derives upper and lower generalization bounds for the student relative to the teacher using a new distillation divergence, plus a loss-sharpness-aware bound and a bias-variance-rank decomposition in the linear Gaussian case.
In: Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
An autoencoder with minimal latent entropy loss enables fully unsupervised video anomaly detection by concentrating normal latent embeddings and producing poor reconstructions for anomalies.
An MPNN models football players as graph nodes and passes as weighted edges to predict receivers from tracking and event data, claiming competitive accuracy plus metrics for likelihood, threat, and creativity.
citing papers explorer
-
Evaluating passing decision-making in professional football: An enhanced MPNN approach to Receiver Selection
An MPNN models football players as graph nodes and passes as weighted edges to predict receivers from tracking and event data, claiming competitive accuracy plus metrics for likelihood, threat, and creativity.