Home Research-feed Channel Rankings GCT THU AI TR Open Data Must Reading

views: 1511

Kunal Talwar

Scientist

Google

Sign in to view more

Show Academic Trajectory

Ego Network

D-Core

Research Interests

Author Statistics

Experience

Education

Bio

I am a Theoretical Computer Scientist, working in the areas of Differential Privacy, Machine Learning, Algorithms, and Data Structures. I am a Research Scientist at Apple. I got my PhD from UC Berkeley in 2004 and was at Microsoft Research 2004-2014, and at Google Brain 2015-2019.

Papers153 papers

Sort

By YearBy Citation

Online Learning over a Finite Action Set with Limited Switching

Jason M. Altschuler,Kunal Talwar

Mathematics of Operations Research, (2020)

Bibtex

Hiding Among the Clones: A Simple and Nearly Optimal Analysis of Privacy Amplification by Shuffling

Vitaly Feldman, Audra McMillan,Kunal Talwar

Bibtex

Encode, Shuffle, Analyze Privacy Revisited: Formalizations and Empirical Evaluation

Erlingsson Úlfar,Feldman Vitaly,Mironov Ilya,Raghunathan Ananth, Song Shuang,Talwar Kunal, Thakurta Abhradeep

Cited by10Bibtex

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

Gavin Brown, Mark Bun,Vitaly Feldman, Adam Smith,Kunal Talwar

Bibtex

Stochastic Optimization with Laggard Data Pipelines

Naman Agarwal,Rohan Anil,Tomer Koren,Kunal Talwar, Cyril Zhang

NeurIPS, (2020)

EIBibtex

Exploring the Memorization-Generalization Continuum in Deep Learning

Jiang Ziheng, Zhang Chiyuan,Talwar Kunal, Mozer Michael C.

Bibtex

Stability of Stochastic Gradient Descent on Nonsmooth Convex Losses

Bassily Raef,Feldman Vitaly,Guzmán Cristóbal,Talwar Kunal

NeurIPS, (2020)

EIBibtex

Private Stochastic Convex Optimization: Optimal Rates in Linear Time

Feldman Vitaly,Koren Tomer,Talwar Kunal

STOC '20: 52nd Annual ACM SIGACT Symposium on Theory of Computing Chicago IL ..., pp.439-449, (2020)

Cited by5EIBibtex

Computational Separations between Sampling and Optimization

ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 32 (NIPS 2019), (2019): 14997-15007

Cited by2EIBibtex

Semi-Cyclic Stochastic Gradient Descent

Hubert Eichner,Tomer Koren,H. Brendan McMahan,Nathan Srebro,Kunal Talwar

arXiv: Learning, (2019)

Cited by23EIBibtex

Better Algorithms for Stochastic Bandits with Adversarial Corruptions

Anupam Gupta,Tomer Koren,Kunal Talwar

COLT, (2019): 1562-1578

Cited by12EIBibtex

From Local to Central Differential Privacy

Vitaly Feldman,Ilya Mironov,Ananth Raghunathan,Kunal Talwar,Abhradeep Thakurta

symposium on discrete algorithms, (2019)

Bibtex

Amplification by Shuffling: From Local to Central Differential Privacy via Anonymity

Úlfar Erlingsson,Vitaly Feldman,Ilya Mironov,Ananth Raghunathan,Kunal Talwar,Abhradeep Thakurta

SODA '19: Symposium on Discrete Algorithms San Diego California January, 2019, (2019): 2468-2479

Cited by74EIBibtex

Private Selection from Private Candidates

Jingcheng Liu,Kunal Talwar

Proceedings of the 51st Annual ACM SIGACT Symposium on Theory of Computing, (2019): 298-309

Cited by12EIBibtex

Private Stochastic Convex Optimization with Optimal Rates

Raef Bassily,Vitaly Feldman,Kunal Talwar,Abhradeep Guha Thakurta

ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 32 (NIPS 2019), (2019): 11279-11288

Cited by17EIBibtex

R\'enyi Differential Privacy of the Sampled Gaussian Mechanism

Mironov Ilya,Talwar Kunal, Zhang Li

Cited by9Bibtex

Learning Differentially Private Recurrent Language Models

H. Brendan McMahan,Daniel Ramage,Kunal Talwar,Li Zhang

international conference on learning representations, (2018)

Cited by182EIBibtex

Online learning over a finite action set with limited switching

Jason Altschuler,Kunal Talwar

COLT, (2018): 1569-1573

Cited by5EIBibtex

Online Linear Quadratic Control

Alon Cohen,Avinatan Hassidim,Tomer Koren,Nevena Lazic,Yishay Mansour,Kunal Talwar

ICML, (2018): 1028-1037

Cited by33EIBibtex

Privacy Amplification by Iteration

Vitaly Feldman,Ilya Mironov,Kunal Talwar,Abhradeep Thakurta

2018 IEEE 59TH ANNUAL SYMPOSIUM ON FOUNDATIONS OF COMPUTER SCIENCE (FOCS), (2018): 521.0-532

Cited by41EIBibtex

View All

Base Info Papers Patents Projects