Generalization in the Face of Adaptivity: A Bayesian Perspective

• URL: http://arxiv.org/abs/2106.10761v3
• Date: Wed, 3 Apr 2024 19:39:10 GMT
• Title: Generalization in the Face of Adaptivity: A Bayesian Perspective
• Authors: Moshe Shenfeld, Katrina Ligett,
• Abstract summary: Repeated use of a data sample via adaptively chosen queries can rapidly lead to overfitting. It turns out that simple noise unbounded addition algorithms suffice to prevent this issue. We show that the harm of adaptivity results from the covariance between the new query and a Bayes factor-based measure of how much information about the data sample was encoded in the responses given to past queries.
• Score: 3.0202264016476623
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Repeated use of a data sample via adaptively chosen queries can rapidly lead to overfitting, wherein the empirical evaluation of queries on the sample significantly deviates from their mean with respect to the underlying data distribution. It turns out that simple noise addition algorithms suffice to prevent this issue, and differential privacy-based analysis of these algorithms shows that they can handle an asymptotically optimal number of queries. However, differential privacy's worst-case nature entails scaling such noise to the range of the queries even for highly-concentrated queries, or introducing more complex algorithms. In this paper, we prove that straightforward noise-addition algorithms already provide variance-dependent guarantees that also extend to unbounded queries. This improvement stems from a novel characterization that illuminates the core problem of adaptive data analysis. We show that the harm of adaptivity results from the covariance between the new query and a Bayes factor-based measure of how much information about the data sample was encoded in the responses given to past queries. We then leverage this characterization to introduce a new data-dependent stability notion that can bound this covariance.

Related papers

• pEBR: A Probabilistic Approach to Embedding Based Retrieval [4.8338111302871525]
  Embedding retrieval aims to learn a shared semantic representation space for both queries and items. In current industrial practice, retrieval systems typically retrieve a fixed number of items for different queries.
  arXiv  Detail & Related papers  (2024-10-25T07:14:12Z)
• Error Feedback under $(L_0,L_1)$-Smoothness: Normalization and Momentum [56.37522020675243]
  We provide the first proof of convergence for normalized error feedback algorithms across a wide range of machine learning problems. We show that due to their larger allowable stepsizes, our new normalized error feedback algorithms outperform their non-normalized counterparts on various tasks.
  arXiv  Detail & Related papers  (2024-10-22T10:19:27Z)
• Benchmarking Private Population Data Release Mechanisms: Synthetic Data vs. TopDown [50.40020716418472]
  This study conducts a comparison between the TopDown algorithm and private synthetic data generation to determine how accuracy is affected by query complexity. Our results show that for in-distribution queries, the TopDown algorithm achieves significantly better privacy-fidelity tradeoffs than any of the synthetic data methods we evaluated.
  arXiv  Detail & Related papers  (2024-01-31T17:38:34Z)
• Best Arm Identification with Fixed Budget: A Large Deviation Perspective [54.305323903582845]
  We present sred, a truly adaptive algorithm that can reject arms in it any round based on the observed empirical gaps between the rewards of various arms. In particular, we present sred, a truly adaptive algorithm that can reject arms in it any round based on the observed empirical gaps between the rewards of various arms.
  arXiv  Detail & Related papers  (2023-12-19T13:17:43Z)
• Tackling Diverse Minorities in Imbalanced Classification [80.78227787608714]
  Imbalanced datasets are commonly observed in various real-world applications, presenting significant challenges in training classifiers. We propose generating synthetic samples iteratively by mixing data samples from both minority and majority classes. We demonstrate the effectiveness of our proposed framework through extensive experiments conducted on seven publicly available benchmark datasets.
  arXiv  Detail & Related papers  (2023-08-28T18:48:34Z)
• Non-Stochastic CDF Estimation Using Threshold Queries [3.6576781735746513]
  We tackle the problem of estimating an empirical distribution in a setting with two challenges. First, the algorithm does not directly observe the data; instead, it only asks a limited number of threshold queries about each sample. Second, the data are not assumed to be independent and identically distributed; instead, we allow for an arbitrary process generating the samples.
  arXiv  Detail & Related papers  (2023-01-13T18:00:57Z)
• Conformal Frequency Estimation using Discrete Sketched Data with Coverage for Distinct Queries [35.67445122503686]
  This paper develops conformal inference methods to construct a confidence interval for the frequency of a queried object in a very large discrete data set. We show our methods have improved empirical performance compared to existing frequentist and Bayesian alternatives in simulations.
  arXiv  Detail & Related papers  (2022-11-09T00:05:29Z)
• Partial Identification with Noisy Covariates: A Robust Optimization Approach [94.10051154390237]
  Causal inference from observational datasets often relies on measuring and adjusting for covariates. We show that this robust optimization approach can extend a wide range of causal adjustment methods to perform partial identification. Across synthetic and real datasets, we find that this approach provides ATE bounds with a higher coverage probability than existing methods.
  arXiv  Detail & Related papers  (2022-02-22T04:24:26Z)
• Differentially Private Query Release Through Adaptive Projection [19.449593001368193]
  We propose, implement, and evaluate a new algorithm for releasing answers to very large numbers of statistical queries like $k$-way marginals. Our algorithm makes adaptive use of a continuous relaxation of the Projection Mechanism, which answers queries on the private dataset using simple perturbation. We find that our method outperforms existing algorithms in many cases, especially when the privacy budget is small or the query class is large.
  arXiv  Detail & Related papers  (2021-03-11T12:43:18Z)
• Oblivious Data for Fairness with Kernels [1.599072005190786]
  We investigate the problem of algorithmic fairness in the case where sensitive and non-sensitive features are available. Our key ingredient for generating such oblivious features is a Hilbert-space-valued conditional expectation. We propose a plug-in approach and demonstrate how the estimation errors can be controlled.
  arXiv  Detail & Related papers  (2020-02-07T16:59:24Z)
• The Simulator: Understanding Adaptive Sampling in the Moderate-Confidence Regime [52.38455827779212]
  We propose a novel technique for analyzing adaptive sampling called the em Simulator. We prove the first instance-based lower bounds the top-k problem which incorporate the appropriate log-factors. Our new analysis inspires a simple and near-optimal for the best-arm and top-k identification, the first em practical of its kind for the latter problem.
  arXiv  Detail & Related papers  (2017-02-16T23:42:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.