Recommendation algorithms that select the most relevant item for sequentially arriving users or queries have become vital for navigating the internet and its many online platforms.

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 adaptation, in particular, domain adaptation under posterior drift.

We study learning problems on correlated stochastic block models with two balanced communities.

Specifically, LocCa employs two tasks, bounding box prediction and location-dependent captioning, conditioned on the image pixel input.