Ananda Theertha Suresh

Block Verification Accelerates Speculative Decoding ICLR 2025 Concept Forgetting via Label Annealing UAI 2025 Efficient and Asymptotically Unbiased Constrained Decoding for Large Language Models AISTATS 2025 General Staircase Mechanisms for Optimal Differential Privacy AISTATS 2025 InfAlign: Inference-aware language model alignment ICML 2025 Rate of Model Collapse in Recursive Training AISTATS 2025 Theoretical guarantees on the best-of-n alignment policy ICML 2025 Accelerating Blockwise Parallel Language Models with Draft Refinement NeurIPS 2024 Mean Estimation in the Add-Remove Model of Differential Privacy ICML 2024 The importance of feature preprocessing for differentially private linear optimization ICLR 2024 Algorithms for bounding contribution for histogram estimation under user-level privacy ICML 2023 Federated Heavy Hitter Recovery under Linear Sketching ICML 2023 Principled Approaches for Private Adaptation from a Public Source AISTATS 2023 SpecTr: Fast Speculative Decoding via Optimal Transport NeurIPS 2023 Subset-Based Instance Optimality in Private Estimation ICML 2023 Correlated Quantization for Distributed Mean Estimation and Optimization ICML 2022 Differentially Private Learning with Margin Guarantees NeurIPS 2022 On the benefits of maximum likelihood estimation for Regression and Forecasting ICLR 2022 Open Problem: Better Differentially Private Learning Algorithms with Margin Guarantees COLT 2022 Robust Estimation for Random Graphs COLT 2022 The Fundamental Price of Secure Aggregation in Differentially Private Federated Learning ICML 2022 A Discriminative Technique for Multiple-Source Adaptation ICML 2021 A Theory of Multiple-Source Adaptation with Limited Target Labeled Data AISTATS 2021 Boosting with Multiple Sources NeurIPS 2021 Breaking the centralized barrier for cross-device federated learning NeurIPS 2021 Communication-Efficient Agnostic Federated Averaging Interspeech 2021 Learning with User-Level Privacy NeurIPS 2021 Relative Deviation Margin Bounds ICML 2021 Remember What You Want to Forget: Algorithms for Machine Unlearning NeurIPS 2021 Robust hypothesis testing and distribution estimation in Hellinger distance AISTATS 2021 Shuffled Model of Differential Privacy in Federated Learning AISTATS 2021 Wyner-Ziv Estimators: Efficient Distributed Mean Estimation with Side-Information AISTATS 2021 FedBoost: A Communication-Efficient Algorithm for Federated Learning ICML 2020 Learning discrete distributions: user vs item-level privacy NeurIPS 2020 Optimal multiclass overfitting by sequence reconstruction from Hamming queries ALT 2020 SCAFFOLD: Stochastic Controlled Averaging for Federated Learning ICML 2020 Agnostic Federated Learning ICML 2019 Differentially Private Anonymized Histograms NeurIPS 2019 Federated Learning of N-Gram Language Models CoNLL 2019 Sampled Softmax with Random Fourier Features NeurIPS 2019 cpSGD: Communication-efficient and differentially-private distributed SGD NeurIPS 2018 Data Amplification: A Unified and Competitive Approach to Property Estimation NeurIPS 2018 Maximum Selection and Sorting with Adversarial Comparators JMLR 2018 A Unified Maximum Likelihood Approach for Estimating Symmetric Properties of Discrete Distributions ICML 2017 Distributed Mean Estimation with Limited Communication ICML 2017 Maximum Selection and Ranking under Noisy Comparisons ICML 2017 Model-Powered Conditional Independence Test NeurIPS 2017 Multiscale Quantization for Fast Similarity Search NeurIPS 2017 Sample complexity of population recovery COLT 2017 Orthogonal Random Features NeurIPS 2016 Competitive Distribution Estimation: Why is Good-Turing Good NeurIPS 2015 Faster Algorithms for Testing under Conditional Sampling COLT 2015 On Learning Distributions from their Samples COLT 2015 Near-Optimal-Sample Estimators for Spherical Gaussian Mixtures NeurIPS 2014 Optimal Probability Estimation with Applications to Prediction and Classification COLT 2013