cs.LGFeb 7, 2026

Efficient Adaptive Data Analysis over Dense Distributions

Authors: Joon Suk Huh

Organizations: Computer Science Department, University of Wisconsin–Madison

Abstract

Modern data workflows are inherently adaptive, repeatedly querying the same dataset to refine and validate sequential decisions, but such adaptivity can lead to overfitting and invalid statistical inference. Adaptive Data Analysis (ADA) mechanisms address this challenge; however, there is a fundamental tension between computational efficiency and sample complexity. For TT rounds of adaptive analysis, computationally efficient algorithms typically incur suboptimal O(T)O(\sqrt{T}) sample complexity, whereas for arbitrary distributions, algorithms with O(log⁡T)O(\log T) sample complexity are computationally intractable under standard cryptographic assumptions. In this work, we shed light on this trade-off by identifying a natural class of data distributions under which both computational efficiency and logarithmic sample complexity in TT are achievable. We propose a computationally efficient ADA mechanism that attains O(log⁡T)O(\log T) sample complexity, optimal in its dependence on TT, when the data distribution is dense with respect to a known prior. This setting includes, in particular, feature-label data distributions arising in distribution-specific learning. As a consequence, our mechanism also yields a sample-efficient (i.e., O(log⁡T)O(\log T) samples) statistical query oracle in the distribution-specific setting. Moreover, although our algorithm is not based on differential privacy, it satisfies a relaxed privacy notion known as Predicate Singling Out (PSO) security (Cohen and Nissim 2020) whenever the number of its possible update transcripts is polynomial in the sample size. Our results thus reveal an inherent connection between adaptive data analysis and privacy beyond differential privacy.

Explore similar work

CardsList
  1. Is Randomness Necessary for Adaptive Data Analysis?

    Jul 8, 2026Edith Cohen, Haim Kaplan, Yishay Mansour +2adaptive data analysis

  2. Efficient and Optimal Learning of Discrete Distributions with Person-Level Privacy

    Oct 22, 2026Gautam Kamath, Mahbod Majid, Ankur Moitra +2Robust StatisticsDifferential Privacy