Theory Seminar: Guy Blanc

This week’s speaker is Guy Blanc, from Stanford Univeristy. As usual, the talk will take place in Room 401B, 3401 Walnut Street on Friday 12-1 PM. Talk details are below.

Title: Subsampling Suffices for Adaptive Data Analysis

Abstract: Ensuring that analyses performed on a dataset are representative of the entire population is one of the central problems in statistics. Most classical techniques assume that the dataset is independent of the analyst’s query and break down in the common setting where a dataset is reused for multiple, adaptively chosen, queries. This problem of adaptive data analysis was formalized in the seminal works of Dwork et al. (STOC, 2015) and Hardt and Ullman (FOCS, 2014).

We identify a remarkably simple set of assumptions under which the queries will continue to be representative even when chosen adaptively: The only requirements are that each query takes as input a random subsample and outputs few bits. This result shows that the noise inherent in subsampling is sufficient to guarantee that query responses generalize. The simplicity of this subsampling-based framework allows it to model a variety of real-world scenarios not covered by prior work. We furthermore demonstrate the utility of this framework by designing a state of the art and extremely simple mechanism for answering statistical queries.