Preventing False Discovery in Interactive Data Analysis is Hard

TL;DR

This paper proves that, assuming standard hardness conjectures, no efficient algorithm can accurately answer a super-polynomial number of adaptively chosen statistical queries, highlighting a computational barrier to preventing false discoveries in data analysis.

Contribution

It establishes a computational intractability result for answering many adaptive statistical queries, revealing an inherent difficulty in preventing false discoveries.

Findings

No efficient algorithm can answer n^{3+o(1)} adaptive queries accurately

Answering exponentially many non-adaptive queries is computationally feasible

The result demonstrates a fundamental computational barrier in statistical validity

Abstract

We show that, under a standard hardness assumption, there is no computationally efficient algorithm that given $n$ samples from an unknown distribution can give valid answers to $n^{3+o(1)}$ adaptively chosen statistical queries. A statistical query asks for the expectation of a predicate over the underlying distribution, and an answer to a statistical query is valid if it is "close" to the correct expectation over the distribution. Our result stands in stark contrast to the well known fact that exponentially many statistical queries can be answered validly and efficiently if the queries are chosen non-adaptively (no query may depend on the answers to previous queries). Moreover, a recent work by Dwork et al. shows how to accurately answer exponentially many adaptively chosen statistical queries via a computationally inefficient algorithm; and how to answer a quadratic number of adaptive queries via a computationally efficient algorithm. The latter result implies that our result is tight up to a linear factor in $n.$ Conceptually, our result demonstrates that achieving statistical validity alone can be a source of computational intractability in adaptive settings. For example, in the modern large collaborative research environment, data analysts typically choose a particular approach based on previous findings. False discovery occurs if a research finding is supported by the data but not by the underlying distribution. While the study of preventing false discovery in Statistics is decades old, to the best of our knowledge our result is the first to demonstrate a computational barrier. In particular, our result suggests that the perceived difficulty of preventing false discovery in today's collaborative research environment may be inherent.