Kunal Talwar

Publication Activity (10 Years)

Years Active: 2001-2023
Publications (10 Years): 103

Top Venues

CoRR

NeurIPS

ICML

STOC

Publications

Martin Pelikan, Sheikh Shams Azam, Vitaly Feldman, Jan "Honza" Silovsky, Kunal Talwar, Tatiana Likhomanenko
Federated Learning with Differential Privacy for End-to-End Speech Recognition. CoRR (2023)
Vitaly Feldman, Audra McMillan, Kunal Talwar
Stronger Privacy Amplification by Shuffling for Renyi and Approximate Differential Privacy. SODA (2023)
Hilal Asi, Vitaly Feldman, Tomer Koren, Kunal Talwar
Private Online Prediction from Experts: Separations and Faster Rates. COLT (2023)
Rachel Cummings, Vitaly Feldman, Audra McMillan, Kunal Talwar
Mean Estimation with User-level Privacy under Data Heterogeneity. CoRR (2023)
Kunal Talwar, Shan Wang, Audra McMillan, Vojta Jina, Vitaly Feldman, Bailey Basile, Áine Cahill, Yi Sheng Chan, Mike Chatzidakis, Junye Chen, Oliver Chick, Mona Chitnis, Suman Ganta, Yusuf Goren, Filip Granqvist, Kristine Guo, Frederic Jacobs, Omid Javidbakht, Albert Liu, Richard Low, Dan Mascenik, Steve Myers, David Park, Wonhee Park, Gianni Parsa, Tommy Pauly, Christian Priebe, Rehan Rishi, Guy Rothblum, Michael Scaria, Linmao Song, Congzheng Song, Karl Tarbe, Sebastian Vogt, Luke Winstrom, Shundong Zhou
Samplable Anonymous Aggregation for Private Federated Data Analysis. CoRR (2023)
Guy N. Rothblum, Eran Omri, Junye Chen, Kunal Talwar
PINE: Efficient Norm-Bound Verification for Secret-Shared Vectors. CoRR (2023)
Jason M. Altschuler, Kunal Talwar
Resolving the Mixing Time of the Langevin Algorithm to its Stationary Distribution for Log-Concave Sampling. COLT (2023)
Hilal Asi, Vitaly Feldman, Jelani Nelson, Huy L. Nguyen, Kunal Talwar
Fast Optimal Locally Private Mean Estimation via Random Projections. NeurIPS (2023)
Hilal Asi, Vitaly Feldman, Tomer Koren, Kunal Talwar
Near-Optimal Algorithms for Private Online Optimization in the Realizable Regime. ICML (2023)
Karan N. Chadha, Junye Chen, John C. Duchi, Vitaly Feldman, Hanieh Hashemi, Omid Javidbakht, Audra McMillan, Kunal Talwar
Differentially Private Heavy Hitter Detection using Federated Analytics. CoRR (2023)
Hilal Asi, Vitaly Feldman, Tomer Koren, Kunal Talwar
Near-Optimal Algorithms for Private Online Optimization in the Realizable Regime. CoRR (2023)
Hilal Asi, Vitaly Feldman, Jelani Nelson, Huy L. Nguyen, Kunal Talwar
Fast Optimal Locally Private Mean Estimation via Random Projections. CoRR (2023)
Vitaly Feldman, Audra McMillan, Kunal Talwar
Hiding Among the Clones: A Simple and Nearly Optimal Analysis of Privacy Amplification by Shuffling. FOCS (2022)
Jason M. Altschuler, Kunal Talwar
Privacy of Noisy Stochastic Gradient Descent: More Iterations without More Privacy Loss. NeurIPS (2022)
Hilal Asi, Vitaly Feldman, Kunal Talwar
Optimal Algorithms for Mean Estimation under Local Differential Privacy. CoRR (2022)
Congzheng Song, Filip Granqvist, Kunal Talwar
FLAIR: Federated Learning Annotated Image Repository. NeurIPS (2022)
Vitaly Feldman, Jelani Nelson, Huy Le Nguyen, Kunal Talwar
Private Frequency Estimation via Projective Geometry. CoRR (2022)
Vitaly Feldman, Jelani Nelson, Huy L. Nguyen, Kunal Talwar
Private frequency estimation via projective geometry. ICML (2022)
Congzheng Song, Filip Granqvist, Kunal Talwar
FLAIR: Federated Learning Annotated Image Repository. CoRR (2022)
Rachel Cummings, Vitaly Feldman, Audra McMillan, Kunal Talwar
Mean Estimation with User-level Privacy under Data Heterogeneity. NeurIPS (2022)
Hilal Asi, Vitaly Feldman, Tomer Koren, Kunal Talwar
Private Online Prediction from Experts: Separations and Faster Rates. CoRR (2022)
Lorenzo Orecchia, Konstantinos Ameranis, Charalampos E. Tsourakakis, Kunal Talwar
Practical Almost-Linear-Time Approximation Algorithms for Hybrid and Overlapping Graph Clustering. ICML (2022)
Jason M. Altschuler, Kunal Talwar
Concentration of the Langevin Algorithm's Stationary Distribution. CoRR (2022)
Jason M. Altschuler, Kunal Talwar
Privacy of Noisy Stochastic Gradient Descent: More Iterations without More Privacy Loss. CoRR (2022)
Kunal Talwar
Differential Secrecy for Distributed Data and Applications to Robust Differentially Secure Vector Summation. FORC (2022)
Hilal Asi, Vitaly Feldman, Kunal Talwar
Optimal Algorithms for Mean Estimation under Local Differential Privacy. ICML (2022)
John C. Duchi, Vitaly Feldman, Lunjia Hu, Kunal Talwar
Subspace Recovery from Heterogeneous Data with Non-isotropic Noise. NeurIPS (2022)
Audra McMillan, Omid Javidbakht, Kunal Talwar, Elliot Briggs, Mike Chatzidakis, Junye Chen, John C. Duchi, Vitaly Feldman, Yusuf Goren, Michael Hesse, Vojta Jina, Anil Katti, Albert Liu, Cheney Lyford, Joey Meyer, Alex Palmer, David Park, Wonhee Park, Gianni Parsa, Paul Pelzl, Rehan Rishi, Congzheng Song, Shan Wang, Shundong Zhou
Private Federated Statistics in an Interactive Setting. CoRR (2022)
John Duchi, Vitaly Feldman, Lunjia Hu, Kunal Talwar
Subspace Recovery from Heterogeneous Data with Non-isotropic Noise. CoRR (2022)
Kunal Talwar
Differential Secrecy for Distributed Data and Applications to Robust Differentially Secure Vector Summation. CoRR (2022)
Vitaly Feldman, Audra McMillan, Kunal Talwar
Stronger Privacy Amplification by Shuffling for Rényi and Approximate Differential Privacy. CoRR (2022)
Hilal Asi, John C. Duchi, Alireza Fallah, Omid Javidbakht, Kunal Talwar
Private Adaptive Gradient Methods for Convex Optimization. ICML (2021)
Vitaly Feldman, Audra McMillan, Kunal Talwar
Hiding Among the Clones: A Simple and Nearly Optimal Analysis of Privacy Amplification by Shuffling. FOCS (2021)
Vitaly Feldman, Kunal Talwar
Lossless Compression of Efficient Private Local Randomizers. CoRR (2021)
Hilal Asi, John C. Duchi, Alireza Fallah, Omid Javidbakht, Kunal Talwar
Private Adaptive Gradient Methods for Convex Optimization. CoRR (2021)
Gavin Brown, Mark Bun, Vitaly Feldman, Adam D. Smith, Kunal Talwar
When is memorization of irrelevant training data necessary for high-accuracy learning? STOC (2021)
Ziheng Jiang, Chiyuan Zhang, Kunal Talwar, Michael C. Mozer
Characterizing Structural Regularities of Labeled Data in Overparameterized Models. ICML (2021)
Jason M. Altschuler, Kunal Talwar
Online Learning over a Finite Action Set with Limited Switching. Math. Oper. Res. 46 (1) (2021)
Vitaly Feldman, Kunal Talwar
Lossless Compression of Efficient Private Local Randomizers. ICML (2021)
Hilal Asi, Vitaly Feldman, Tomer Koren, Kunal Talwar
Geometry. CoRR (2021)
Hilal Asi, Vitaly Feldman, Tomer Koren, Kunal Talwar
Private Stochastic Convex Optimization: Optimal Rates in L1 Geometry. ICML (2021)
Vitaly Feldman, Tomer Koren, Kunal Talwar
Private Stochastic Convex Optimization: Optimal Rates in Linear Time. CoRR (2020)
Vitaly Feldman, Audra McMillan, Kunal Talwar
Hiding Among the Clones: A Simple and Nearly Optimal Analysis of Privacy Amplification by Shuffling. CoRR (2020)
Gavin Brown, Mark Bun, Vitaly Feldman, Adam D. Smith, Kunal Talwar
When is Memorization of Irrelevant Training Data Necessary for High-Accuracy Learning? CoRR (2020)
Arun Ganesh, Kunal Talwar
Faster Differentially Private Samplers via Rényi Divergence Analysis of Discretized Langevin MCMC. CoRR (2020)
Kunal Talwar
On the Error Resistance of Hinge-Loss Minimization. NeurIPS (2020)
Vitaly Feldman, Tomer Koren, Kunal Talwar
Private stochastic convex optimization: optimal rates in linear time. STOC (2020)
Arun Ganesh, Kunal Talwar
Faster Differentially Private Samplers via Rényi Divergence Analysis of Discretized Langevin MCMC. NeurIPS (2020)
Raef Bassily, Vitaly Feldman, Cristóbal Guzmán, Kunal Talwar
Stability of Stochastic Gradient Descent on Nonsmooth Convex Losses. NeurIPS (2020)
Naman Agarwal, Rohan Anil, Tomer Koren, Kunal Talwar, Cyril Zhang
Stochastic Optimization with Laggard Data Pipelines. CoRR (2020)
Úlfar Erlingsson, Vitaly Feldman, Ilya Mironov, Ananth Raghunathan, Shuang Song, Kunal Talwar, Abhradeep Thakurta
Encode, Shuffle, Analyze Privacy Revisited: Formalizations and Empirical Evaluation. CoRR (2020)
Ziheng Jiang, Chiyuan Zhang, Kunal Talwar, Michael C. Mozer
Exploring the Memorization-Generalization Continuum in Deep Learning. CoRR (2020)
Kunal Talwar
On the Error Resistance of Hinge Loss Minimization. CoRR (2020)
Naman Agarwal, Rohan Anil, Tomer Koren, Kunal Talwar, Cyril Zhang
Stochastic Optimization with Laggard Data Pipelines. NeurIPS (2020)
Raef Bassily, Vitaly Feldman, Cristóbal Guzmán, Kunal Talwar
Stability of Stochastic Gradient Descent on Nonsmooth Convex Losses. CoRR (2020)
Raef Bassily, Vitaly Feldman, Kunal Talwar, Abhradeep Thakurta
Private Stochastic Convex Optimization with Optimal Rates. CoRR (2019)
Hubert Eichner, Tomer Koren, H. Brendan McMahan, Nathan Srebro, Kunal Talwar
Semi-Cyclic Stochastic Gradient Descent. CoRR (2019)
Kunal Talwar
Computational Separations between Sampling and Optimization. CoRR (2019)
Ilya Mironov, Kunal Talwar, Li Zhang
Rényi Differential Privacy of the Sampled Gaussian Mechanism. CoRR (2019)
Raef Bassily, Vitaly Feldman, Kunal Talwar, Abhradeep Guha Thakurta
Private Stochastic Convex Optimization with Optimal Rates. NeurIPS (2019)
Hubert Eichner, Tomer Koren, Brendan McMahan, Nathan Srebro, Kunal Talwar
Semi-Cyclic Stochastic Gradient Descent. ICML (2019)
Ittai Abraham, Cyril Gavoille, Anupam Gupta, Ofer Neiman, Kunal Talwar
Cops, Robbers, and Threatening Skeletons: Padded Decomposition for Minor-Free Graphs. SIAM J. Comput. 48 (3) (2019)
Úlfar Erlingsson, Vitaly Feldman, Ilya Mironov, Ananth Raghunathan, Kunal Talwar, Abhradeep Thakurta
Amplification by Shuffling: From Local to Central Differential Privacy via Anonymity. SODA (2019)
Kunal Talwar
Computational Separations between Sampling and Optimization. NeurIPS (2019)
Jingcheng Liu, Kunal Talwar
Private selection from private candidates. STOC (2019)
Anupam Gupta, Tomer Koren, Kunal Talwar
Better Algorithms for Stochastic Bandits with Adversarial Corruptions. CoRR (2019)
Anupam Gupta, Tomer Koren, Kunal Talwar
Better Algorithms for Stochastic Bandits with Adversarial Corruptions. COLT (2019)
Vitaly Feldman, Ilya Mironov, Kunal Talwar, Abhradeep Thakurta
Privacy Amplification by Iteration. FOCS (2018)
Jason Altschuler, Kunal Talwar
Online learning over a finite action set with limited switching. COLT (2018)
Ludwig Schmidt, Shibani Santurkar, Dimitris Tsipras, Kunal Talwar, Aleksander Madry
Adversarially Robust Generalization Requires More Data. NeurIPS (2018)
Alon Cohen, Avinatan Hassidim, Tomer Koren, Nevena Lazic, Yishay Mansour, Kunal Talwar
Online Linear Quadratic Control. CoRR (2018)
Alon Cohen, Avinatan Hassidim, Tomer Koren, Nevena Lazic, Yishay Mansour, Kunal Talwar
Online Linear Quadratic Control. ICML (2018)
Úlfar Erlingsson, Vitaly Feldman, Ilya Mironov, Ananth Raghunathan, Kunal Talwar, Abhradeep Thakurta
Amplification by Shuffling: From Local to Central Differential Privacy via Anonymity. CoRR (2018)
Jingcheng Liu, Kunal Talwar
Private Selection from Private Candidates. CoRR (2018)
Ludwig Schmidt, Shibani Santurkar, Dimitris Tsipras, Kunal Talwar, Aleksander Madry
Adversarially Robust Generalization Requires More Data. CoRR (2018)
Vitaly Feldman, Ilya Mironov, Kunal Talwar, Abhradeep Thakurta
Privacy Amplification by Iteration. CoRR (2018)
Nicolas Papernot, Shuang Song, Ilya Mironov, Ananth Raghunathan, Kunal Talwar, Úlfar Erlingsson
Scalable Private Learning with PATE. CoRR (2018)
H. Brendan McMahan, Daniel Ramage, Kunal Talwar, Li Zhang
Learning Differentially Private Recurrent Language Models. ICLR (Poster) (2018)
Jason Altschuler, Kunal Talwar
Online learning over a finite action set with limited switching. CoRR (2018)
Daniel Dadush, Aleksandar Nikolov, Kunal Talwar, Nicole Tomczak-Jaegermann
Balancing Vectors in Any Norm. FOCS (2018)
Nicolas Papernot, Shuang Song, Ilya Mironov, Ananth Raghunathan, Kunal Talwar, Úlfar Erlingsson
Scalable Private Learning with PATE. ICLR (2018)
Martín Abadi, Úlfar Erlingsson, Ian J. Goodfellow, H. Brendan McMahan, Ilya Mironov, Nicolas Papernot, Kunal Talwar, Li Zhang
On the Protection of Private Information in Machine Learning Systems: Two Recent Approches. CSF (2017)
Amit Daniely, Nevena Lazic, Yoram Singer, Kunal Talwar
Short and Deep: Sketching and Neural Networks. ICLR (Workshop) (2017)
Petros Maniatis, Ilya Mironov, Kunal Talwar
Oblivious Stash Shuffle. CoRR (2017)
Anupam Gupta, R. Ravi, Kunal Talwar, Seeun William Umboh
LAST but not Least: Online Spanners for Buy-at-Bulk. SODA (2017)
Nicolas Papernot, Martín Abadi, Úlfar Erlingsson, Ian J. Goodfellow, Kunal Talwar
Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data. ICLR (2017)
H. Brendan McMahan, Daniel Ramage, Kunal Talwar, Li Zhang
Learning Differentially Private Language Models Without Losing Accuracy. CoRR (2017)
Martín Abadi, Úlfar Erlingsson, Ian J. Goodfellow, H. Brendan McMahan, Ilya Mironov, Nicolas Papernot, Kunal Talwar, Li Zhang
On the Protection of Private Information in Machine Learning Systems: Two Recent Approaches. CoRR (2017)
Anupam Gupta, R. Ravi, Kunal Talwar, Seeun William Umboh
LAST but not Least: Online Spanners for Buy-at-Bulk. CoRR (2016)
Aleksandar Nikolov, Kunal Talwar, Li Zhang
The Geometry of Differential Privacy: The Small Database and Approximate Cases. SIAM J. Comput. 45 (2) (2016)
Martín Abadi, Ashish Agarwal, Paul Barham, Eugene Brevdo, Zhifeng Chen, Craig Citro, Gregory S. Corrado, Andy Davis, Jeffrey Dean, Matthieu Devin, Sanjay Ghemawat, Ian J. Goodfellow, Andrew Harp, Geoffrey Irving, Michael Isard, Yangqing Jia, Rafal Józefowicz, Lukasz Kaiser, Manjunath Kudlur, Josh Levenberg, Dan Mané, Rajat Monga, Sherry Moore, Derek Gordon Murray, Chris Olah, Mike Schuster, Jonathon Shlens, Benoit Steiner, Ilya Sutskever, Kunal Talwar, Paul A. Tucker, Vincent Vanhoucke, Vijay Vasudevan, Fernanda B. Viégas, Oriol Vinyals, Pete Warden, Martin Wattenberg, Martin Wicke, Yuan Yu, Xiaoqiang Zheng
TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems. CoRR (2016)
Martín Abadi, Andy Chu, Ian J. Goodfellow, H. Brendan McMahan, Ilya Mironov, Kunal Talwar, Li Zhang
Deep Learning with Differential Privacy. CoRR (2016)
Amit Daniely, Nevena Lazic, Yoram Singer, Kunal Talwar
Sketching and Neural Networks. CoRR (2016)
Nicolas Papernot, Martín Abadi, Úlfar Erlingsson, Ian J. Goodfellow, Kunal Talwar
Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data. CoRR (2016)
Parikshit Gopalan, Noam Nisan, Rocco A. Servedio, Kunal Talwar, Avi Wigderson
Smooth Boolean Functions are Easy: Efficient Algorithms for Low-Sensitivity Functions. ITCS (2016)
Martín Abadi, Andy Chu, Ian J. Goodfellow, H. Brendan McMahan, Ilya Mironov, Kunal Talwar, Li Zhang
Deep Learning with Differential Privacy. CCS (2016)
Parikshit Gopalan, Noam Nisan, Rocco A. Servedio, Kunal Talwar, Avi Wigderson
Smooth Boolean functions are easy: efficient algorithms for low-sensitivity functions. CoRR (2015)
Parikshit Gopalan, Noam Nisan, Rocco A. Servedio, Kunal Talwar, Avi Wigderson
Smooth Boolean functions are easy: efficient algorithms for low-sensitivity functions. Electron. Colloquium Comput. Complex. 22 (2015)
Kunal Talwar, Abhradeep Thakurta, Li Zhang
Nearly Optimal Private LASSO. NIPS (2015)
Cynthia Dwork, Aleksandar Nikolov, Kunal Talwar
Efficient Algorithms for Privately Releasing Marginals via Convex Relaxations. Discret. Comput. Geom. 53 (3) (2015)

Kunal Talwar.css-eqlu8i{font-size:small;padding-left:4px;}

Publication Activity (10 Years)

Top Topics

Top Venues

Kunal Talwar