3 papers
cs.LG2026
Symmetry Reveals Layerwise Dynamics: How Transformers Perform In-Context Classification
Patrick Lutz, Themistoklis Haris, Arjun Chandra +2
Transformers can perform in-context classification from a few labeled examples, yet the inference-time algorithm remains opaque. We study multi-class linear classification in the h…
cs.LG2026
Domain Generalization Under Posterior Drift
Yilun Zhu, Naihao Deng, Naichen Shi +2
Domain generalization (DG) is the problem of generalizing from several distributions (or domains), for which labeled training data are available, to a new test domain for which no…
cs.LG2024
Label Noise: Ignorance Is Bliss
Yilun Zhu, Jianxin Zhang, Aditya Gangrade +1
We establish a new theoretical framework for learning under multi-class, instance-dependent label noise. This framework casts learning with label noise as a form of domain adaptati…