Publications (34)
Vertex Sparsifiers: New Results from Old Techniques
Matthias Englert, Anupam Gupta, Robert Krauthgamer +3
TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
MartÃn Abadi, Ashish Agarwal, Paul Barham +37
Changing Bases: Multistage Optimization for Matroids and Matchings
Anupam Gupta, Kunal Talwar, Udi Wieder
Sketching and Neural Networks
Amit Daniely, Nevena Lazic, Yoram Singer +1
On the Protection of Private Information in Machine Learning Systems: Two Recent Approaches
MartÃn Abadi, Ãlfar Erlingsson, Ian Goodfellow +5
Approximating Hereditary Discrepancy via Small Width Ellipsoids
Aleksandar Nikolov, Kunal Talwar
Private Empirical Risk Minimization Beyond the Worst Case: The Effect of the Constraint Set Geometry
Kunal Talwar, Abhradeep Thakurta, Li Zhang
Factorization Norms and Hereditary Discrepancy
Jiri Matousek, Aleksandar Nikolov, Kunal Talwar
How to Complete a Doubling Metric
Anupam Gupta, Kunal Talwar
The Geometry of Differential Privacy: the Sparse and Approximate Cases
Aleksandar Nikolov, Kunal Talwar, Li Zhang
Smooth Boolean functions are easy: efficient algorithms for low-sensitivity functions
Parikshit Gopalan, Noam Nisan, Rocco A. Servedio +2
Constrained Non-Monotone Submodular Maximization: Offline and Secretary Algorithms
Anupam Gupta, Aaron Roth, Grant Schoenebeck +1
Learning Differentially Private Recurrent Language Models
H. Brendan McMahan, Daniel Ramage, Kunal Talwar +1
On Privacy-Preserving Histograms
Shuchi Chawla, Cynthia Dwork, Frank McSherry +1
Semi-Cyclic Stochastic Gradient Descent
Hubert Eichner, Tomer Koren, H. Brendan McMahan +2
Privacy Amplification by Iteration
Vitaly Feldman, Ilya Mironov, Kunal Talwar +1
Differentially Private Combinatorial Optimization
Anupam Gupta, Katrina Ligett, Frank McSherry +2
Oblivious Stash Shuffle
Petros Maniatis, Ilya Mironov, Kunal Talwar
Sparsest Cut on Bounded Treewidth Graphs: Algorithms and Hardness Results
Anupam Gupta, Kunal Talwar, David Witmer
On the Geometry of Differential Privacy
Moritz Hardt, Kunal Talwar
Random Rates for 0-Extension and Low-Diameter Decompositions
Anupam Gupta, Kunal Talwar
Lower Bounds on Near Neighbor Search via Metric Expansion
Rina Panigrahy, Kunal Talwar, Udi Wieder
Better Algorithms for Stochastic Bandits with Adversarial Corruptions
Anupam Gupta, Tomer Koren, Kunal Talwar
Private Selection from Private Candidates
Jingcheng Liu, Kunal Talwar
Scalable Private Learning with PATE
Nicolas Papernot, Shuang Song, Ilya Mironov +3
Deep Learning with Differential Privacy
MartÃn Abadi, Andy Chu, Ian Goodfellow +4
Adversarially Robust Generalization Requires More Data
Ludwig Schmidt, Shibani Santurkar, Dimitris Tsipras +2
Online Linear Quadratic Control
Alon Cohen, Avinatan Hassidim, Tomer Koren +3
Consistent Weighted Sampling Made Fast, Small, and Easy
Bernhard Haeupler, Mark Manasse, Kunal Talwar
Balanced Allocations: A Simple Proof for the Heavily Loaded Case
Kunal Talwar, Udi Wieder
Efficient Algorithms for Privately Releasing Marginals via Convex Relaxations
Cynthia Dwork, Aleksandar Nikolov, Kunal Talwar
LAST but not Least: Online Spanners for Buy-at-Bulk
Anupam Gupta, R. Ravi, Kunal Talwar +1
On The Hereditary Discrepancy of Homogeneous Arithmetic Progressions
Aleksandar Nikolov, Kunal Talwar
Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data
Nicolas Papernot, MartÃn Abadi, Ãlfar Erlingsson +2