Kunal Talwar

Adaptive Batch Size for Privately Finding Second-Order Stationary Points ICLR 2025 Faster Rates for Private Adversarial Bandits ICML 2025 Improved Sample Complexity for Private Nonsmooth Nonconvex Optimization ICML 2025 Local Pan-privacy for Federated Analytics ICML 2025 Instance-Optimal Private Density Estimation in the Wasserstein Distance NeurIPS 2024 Private and Personalized Frequency Estimation in a Federated Setting NeurIPS 2024 Private Online Learning via Lazy Algorithms NeurIPS 2024 Private Vector Mean Estimation in the Shuffle Model: Optimal Rates Require Many Messages ICML 2024 Fast Optimal Locally Private Mean Estimation via Random Projections NeurIPS 2023 Near-Optimal Algorithms for Private Online Optimization in the Realizable Regime ICML 2023 Private Online Prediction from Experts: Separations and Faster Rates COLT 2023 Resolving the Mixing Time of the Langevin Algorithm to its Stationary Distribution for Log-Concave Sampling COLT 2023 FLAIR: Federated Learning Annotated Image Repository NeurIPS 2022 Mean Estimation with User-level Privacy under Data Heterogeneity NeurIPS 2022 Optimal Algorithms for Mean Estimation under Local Differential Privacy ICML 2022 Practical Almost-Linear-Time Approximation Algorithms for Hybrid and Overlapping Graph Clustering ICML 2022 Privacy of Noisy Stochastic Gradient Descent: More Iterations without More Privacy Loss NeurIPS 2022 Private frequency estimation via projective geometry ICML 2022 Subspace Recovery from Heterogeneous Data with Non-isotropic Noise NeurIPS 2022 Characterizing Structural Regularities of Labeled Data in Overparameterized Models ICML 2021 Lossless Compression of Efficient Private Local Randomizers ICML 2021 Private Adaptive Gradient Methods for Convex Optimization ICML 2021 Private Stochastic Convex Optimization: Optimal Rates in L1 Geometry ICML 2021 Faster Differentially Private Samplers via Rényi Divergence Analysis of Discretized Langevin MCMC NeurIPS 2020 On the Error Resistance of Hinge-Loss Minimization NeurIPS 2020 Stability of Stochastic Gradient Descent on Nonsmooth Convex Losses NeurIPS 2020 Stochastic Optimization with Laggard Data Pipelines NeurIPS 2020 Better Algorithms for Stochastic Bandits with Adversarial Corruptions COLT 2019 Computational Separations between Sampling and Optimization NeurIPS 2019 Private Stochastic Convex Optimization with Optimal Rates NeurIPS 2019 Semi-Cyclic Stochastic Gradient Descent ICML 2019 Adversarially Robust Generalization Requires More Data NeurIPS 2018 Learning Differentially Private Recurrent Language Models ICLR 2018 Online learning over a finite action set with limited switching COLT 2018 Online Linear Quadratic Control ICML 2018 Scalable Private Learning with PATE ICLR 2018 Nearly Optimal Private LASSO NeurIPS 2015