Preserving Statistical Validity in Adaptive Data Analysis

DOI10.1145/2746539.2746580zbMath1321.68401arXiv1411.2664OpenAlexW1982723861MaRDI QIDQ2941495

Moritz Hardt, Aaron Roth, Toniann Pitassi, Vitaly Feldman, Omer Reingold, Cynthia Dwork

Publication date: 21 August 2015

Published in: Proceedings of the forty-seventh annual ACM symposium on Theory of Computing (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1411.2664

zbMATH Keywords

statistical estimationdifferential privacygeneralization boundsoverfittingfalse discoveryadaptive data analysis

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Cryptography (94A60)

Related Items

Private Sequential Learning ⋮ Separating adaptive streaming from oblivious streaming using the bounded storage model ⋮ On the Power of Learning from k-Wise Queries ⋮ Lower Bounds for Parallel and Randomized Convex Optimization ⋮ Fingerprinting Codes and the Price of Approximate Differential Privacy ⋮ Rejoinder ⋮ Scalable methods for Bayesian selective inference ⋮ Comment ⋮ Comment ⋮ On differential privacy and adaptive data analysis with bounded space ⋮ Unnamed Item ⋮ Post-selection inference via algorithmic stability ⋮ Learning privately with labeled and unlabeled examples ⋮ Preserving Randomness for Adaptive Algorithms ⋮ Perturbation of convex risk minimization and its application in differential private learning algorithms ⋮ Unnamed Item ⋮ Online rules for control of false discovery rate and false discovery exceedance ⋮ Selective inference with a randomized response ⋮ Test Data Reuse for the Evaluation of Continuously Evolving Classification Algorithms Using the Area under the Receiver Operating Characteristic Curve ⋮ Algorithmic Stability for Adaptive Data Analysis ⋮ Structure and Sensitivity in Differential Privacy: Comparing K-Norm Mechanisms ⋮ The Complexity of Differential Privacy

Uses Software

• Graphs

Cites Work

• Unnamed Item
• Ramsey partitions and proximity data structures
• On sparse spanners of weighted graphs
• Scale-oblivious metric fragmentation and the nonlinear Dvoretzky theorem
• On Approximate Distance Labels and Routing Schemes with Affine Stretch
• Distance Oracles for Unweighted Graphs: Breaking the Quadratic Barrier with Constant Additive Error
• Approximate distance oracles
• Fast Algorithms for Constructing t-Spanners and Paths with Stretch t
• Near-Linear Time Construction of Sparse Neighborhood Covers
• Shortest-path queries in static networks
• Approximate distance oracles with constant query time
• Automata, Languages and Programming

This page was built for publication: Preserving Statistical Validity in Adaptive Data Analysis