In many scientific applications, we observe a system in different conditions in which its components may change, rather than in isolation.

Multi-distribution or collaborative learning involves learning a single predictor that works well across multiple data distributions, using samples from each during training.

Can a physicist make only a finite number of errors in the eternal quest to uncover the law of nature? This millennium-old philosophical problem, known as inductive inference, lies at the heart of epistemology.

The goal is to train a good instance classifier.

In this paper, we study the same problem in the Massart noise model that we now define.

Algorithmic stability is a major theme in learning theory, where seminal results have firmly established its close relationship with generalization. Recent research has further highlighted the intricate interplay between stability and additional properties of interest beyond statistical generalization.

For learning Boolean concept classes, we show that the entangled and separable sample complexity are polynomially related .