Atsutoshi Kumagai

Do We Really Need Permutations? Impact of Model Width on Linear Mode Connectivity

Deep Positive-Unlabeled Anomaly Detection for Contaminated Unlabeled Data

Analysis of Linear Mode Connectivity via Permutation-Based Weight Matching: With Insights into Other Permutation Search Methods

Positive-unlabeled AUC Maximization under Covariate Shift

Test-time Adaptation for Regression by Subspace Alignment

Linear Mode Connectivity between Multiple Models modulo Permutation Symmetries

Positive-Unlabeled Diffusion Models for Preventing Sensitive Data Generation

Meta-learning Representations for Learning from Multiple Annotators

Deep Positive-Unlabeled Anomaly Detection for Contaminated Unlabeled Data