V
Vitaly Feldman
Researcher at Google
Publications - 175
Citations - 6308
Vitaly Feldman is an academic researcher from Google. The author has contributed to research in topics: Convex optimization & Upper and lower bounds. The author has an hindex of 37, co-authored 165 publications receiving 4808 citations. Previous affiliations of Vitaly Feldman include Harvard University & IBM.
Papers
More filters
Journal ArticleDOI
The reusable holdout: Preserving validity in adaptive data analysis
TL;DR: A new approach for addressing the challenges of adaptivity based on insights from privacy-preserving data analysis is demonstrated, and how to safely reuse a holdout data set many times to validate the results of adaptively chosen analyses is shown.
Proceedings ArticleDOI
Cognitive computing building block: A versatile and efficient digital neuron model for neurosynaptic cores
Andrew S. Cassidy,Paul A. Merolla,John V. Arthur,Steve K. Esser,Bryan L. Jackson,Rodrigo Alvarez-Icaza,Pallab Datta,Jun Sawada,Theodore M. Wong,Vitaly Feldman,Arnon Amir,Daniel D Ben Dayan Rubin,Filipp Akopyan,Emmett McQuinn,William P. Risk,Dharmendra S. Modha +15 more
TL;DR: A simple, digital, reconfigurable, versatile spiking neuron model that supports one-to-one equivalence between hardware and simulation and is implementable using only 1272 ASIC gates is developed.
Posted Content
Preserving Statistical Validity in Adaptive Data Analysis
TL;DR: It is shown that, surprisingly, there is a way to estimate an exponential in n number of expectations accurately even if the functions are chosen adaptively, and this gives an exponential improvement over standard empirical estimators that are limited to a linear number of estimates.
Posted Content
Amplification by Shuffling: From Local to Central Differential Privacy via Anonymity
Úlfar Erlingsson,Vitaly Feldman,Ilya Mironov,Ananth Raghunathan,Kunal Talwar,Abhradeep Thakurta +5 more
TL;DR: It is shown, via a new and general privacy amplification technique, that any permutation-invariant algorithm satisfying e-local differential privacy will satisfy [MATH HERE]-central differential privacy.
Proceedings ArticleDOI
Preserving Statistical Validity in Adaptive Data Analysis
TL;DR: In this paper, the authors investigate the question of estimating the expectations of m adaptively chosen functions on an unknown distribution given n random samples, and show that there is a way to estimate an exponential in n number of expectations accurately even if the functions are chosen adaptively.