Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Adam Smith

When is Memorization of Irrelevant Training Data Necessary for High-Accuracy Learning?


Dec 11, 2020
Gavin Brown, Mark Bun, Vitaly Feldman, Adam Smith, Kunal Talwar


  Access Paper or Ask Questions

Empirical Risk Minimization in the Non-interactive Local Model of Differential Privacy


Nov 11, 2020
Di Wang, Marco Gaboardi, Adam Smith, Jinhui Xu

* Appeared at Journal of Machine Learning Research. The journal version of arXiv:1802.04085, fixed a bug in arXiv:1812.06825 

  Access Paper or Ask Questions

Differentially Private Simple Linear Regression


Jul 10, 2020
Daniel Alabi, Audra McMillan, Jayshree Sarathy, Adam Smith, Salil Vadhan

* 20 pages, 18 figures 

  Access Paper or Ask Questions

Guaranteed Validity for Empirical Approaches to Adaptive Data Analysis


Jun 21, 2019
Ryan Rogers, Aaron Roth, Adam Smith, Nathan Srebro, Om Thakkar, Blake Woodworth


  Access Paper or Ask Questions

Differentially Private Empirical Risk Minimization in Non-interactive Local Model via Polynomial of Inner Product Approximation


Dec 17, 2018
Di Wang, Adam Smith, Jinhui Xu

* To appear in Algorithmic Learning Theory 2019 (ALT 2019), draft version 

  Access Paper or Ask Questions

The Structure of Optimal Private Tests for Simple Hypotheses


Nov 27, 2018
Clément L. Canonne, Gautam Kamath, Audra McMillan, Adam Smith, Jonathan Ullman


  Access Paper or Ask Questions

From Soft Classifiers to Hard Decisions: How fair can we be?


Oct 03, 2018
Ran Canetti, Aloni Cohen, Nishanth Dikkala, Govind Ramnarayan, Sarah Scheffler, Adam Smith


  Access Paper or Ask Questions

The Limits of Post-Selection Generalization


Jun 15, 2018
Kobbi Nissim, Adam Smith, Thomas Steinke, Uri Stemmer, Jonathan Ullman


  Access Paper or Ask Questions

Evolving Mario Levels in the Latent Space of a Deep Convolutional Generative Adversarial Network


May 02, 2018
Vanessa Volz, Jacob Schrum, Jialin Liu, Simon M. Lucas, Adam Smith, Sebastian Risi

* 8 pages, GECCO2018 

  Access Paper or Ask Questions

Information, Privacy and Stability in Adaptive Data Analysis


Jun 02, 2017
Adam Smith

* 15 pages, first drafted February 2017. A version of this survey appears in the Information Theory Society Newsletter 

  Access Paper or Ask Questions

Stability selection for component-wise gradient boosting in multiple dimensions


Nov 30, 2016
Janek Thomas, Andreas Mayr, Bernd Bischl, Matthias Schmid, Adam Smith, Benjamin Hofner

* 16 pages 

  Access Paper or Ask Questions

Max-Information, Differential Privacy, and Post-Selection Hypothesis Testing


Sep 09, 2016
Ryan Rogers, Aaron Roth, Adam Smith, Om Thakkar


  Access Paper or Ask Questions

When is Nontrivial Estimation Possible for Graphons and Stochastic Block Models?


Apr 07, 2016
Audra McMillan, Adam Smith

* 11 pages 

  Access Paper or Ask Questions

More General Queries and Less Generalization Error in Adaptive Data Analysis


Nov 10, 2015
Raef Bassily, Adam Smith, Thomas Steinke, Jonathan Ullman

* This paper was merged with another manuscript and is now subsumed by arXiv:1511.02513 

  Access Paper or Ask Questions

Algorithmic Stability for Adaptive Data Analysis


Nov 08, 2015
Raef Bassily, Kobbi Nissim, Adam Smith, Thomas Steinke, Uri Stemmer, Jonathan Ullman

* This work unifies and subsumes the two arXiv manuscripts arXiv:1503.04843 and arXiv:1504.05800 

  Access Paper or Ask Questions

Local, Private, Efficient Protocols for Succinct Histograms


Apr 18, 2015
Raef Bassily, Adam Smith


  Access Paper or Ask Questions

Differentially Private Empirical Risk Minimization: Efficient Algorithms and Tight Error Bounds


Oct 17, 2014
Raef Bassily, Adam Smith, Abhradeep Thakurta


  Access Paper or Ask Questions

The Power of Linear Reconstruction Attacks


Oct 08, 2012
Shiva Prasad Kasiviswanathan, Mark Rudelson, Adam Smith

* 30 pages, to appear in ACM-SIAM Symposium on Discrete Algorithms (SODA 2013) 

  Access Paper or Ask Questions

What Can We Learn Privately?


Feb 19, 2010
Shiva Prasad Kasiviswanathan, Homin K. Lee, Kobbi Nissim, Sofya Raskhodnikova, Adam Smith

* SIAM Journal of Computing 40(3) (2011) 793-826 
* 35 pages, 2 figures 

  Access Paper or Ask Questions