Robust Streaming, Sampling, and a Perspective on Online Learning
This work aims to enlighten the study of statistical learning and robust streaming by clarifying technical connections, potentially motivating new research directions, but it appears to be a survey and unification effort rather than a novel breakthrough.
The paper provides an overview of statistical learning and robust streaming techniques, culminating in rigorous results that prove relationships between these areas, while unifying disjoint theorems in a shared framework to clarify deep connections.
In this work we present an overview of statistical learning, followed by a survey of robust streaming techniques and challenges, culminating in several rigorous results proving the relationship that we motivate and hint at throughout the journey. Furthermore, we unify often disjoint theorems in a shared framework and notation to clarify the deep connections that are discovered. We hope that by approaching these results from a shared perspective, already aware of the technical connections that exist, we can enlighten the study of both fields and perhaps motivate new and previously unconsidered directions of research.