Kamalika Chaudhuri

Beyond Discrepancy: A Closer Look at the Theory of Distribution Shift ALT 2026 ExpProof : Operationalizing Explanations for Confidential Models with ZKPs ICML 2025 Auditing $f$-differential privacy in one run ICML 2025 Measuring Dejavu Memorization Efficiently NIPS 2024 On Differentially Private U Statistics NIPS 2024 Distribution Learning with Valid Outputs Beyond the Worst-Case NIPS 2024 Differentially Private Representation Learning via Image Captioning ICML 2024 Effective pruning of web-scale datasets based on complexity of concept clusters ICLR 2024 ViP: A Differentially Private Foundation Model for Computer Vision ICML 2024 FairProof : Confidential and Certifiable Fairness for Neural Networks ICML 2024 Déjà Vu Memorization in Vision–Language Models NIPS 2024 Do SSL Models Have Déjà Vu? A Case of Unintended Memorization in Self-supervised Learning NIPS 2023 A Two-Stage Active Learning Algorithm for k-Nearest Neighbors ICML 2023 Privacy-Aware Compression for Federated Learning Through Numerical Mechanism Design ICML 2023 Why does Throwing Away Data Improve Worst-Group Error? ICML 2023 Data-Copying in Generative Models: A Formal Framework ICML 2023 Robust Empirical Risk Minimization with Tolerance ALT 2023 Agnostic Multi-Group Active Learning NIPS 2023 Privacy Implications of Shuffling ICLR 2022 Sentence-level Privacy for Document Embeddings ACL 2022 Privacy Amplification by Subsampling in Time Domain AISTATS 2022 Privacy Amplification via Shuffling for Linear Contextual Bandits ALT 2022 Bounding Training Data Reconstruction in Private (Deep) Learning ICML 2022 Thompson Sampling for Robust Transfer in Multi-Task Bandits ICML 2022 Privacy-aware compression for federated data analysis UAI 2022 Location Trace Privacy Under Conditional Priors AISTATS 2021 Revisiting Model-Agnostic Private Learning: Faster Rates and Active Learning JMLR 2021 Connecting Interpretability and Robustness in Decision Trees through Separation ICML 2021 Understanding Instance-based Interpretability of Variational Auto-Encoders NIPS 2021 Consistent Non-Parametric Methods for Maximizing Robustness NIPS 2021 Sample Complexity of Robust Linear Classification on Separated Data ICML 2021 Revisiting Model-Agnostic Private Learning: Faster Rates and Active Learning AISTATS 2021 Multitask Bandit Learning Through Heterogeneous Feedback Aggregation AISTATS 2021 Approximate Data Deletion from Machine Learning Models AISTATS 2021 Variational Bayes in Private Settings (VIPS) (Extended Abstract) IJCAI 2020 Robustness for Non-Parametric Classification: A Generic Attack and Defense AISTATS 2020 A Three Sample Hypothesis Test for Evaluating Generative Models AISTATS 2020 The Expressive Power of a Class of Normalizing Flow Models AISTATS 2020 A Closer Look at Accuracy vs. Robustness NIPS 2020 When are Non-Parametric Methods Robust? ICML 2020 Capacity Bounded Differential Privacy NIPS 2019 The Label Complexity of Active Learning from Observational Data NIPS 2019 Active Learning with Logged Data ICML 2018 Analyzing the Robustness of Nearest Neighbors to Adversarial Examples ICML 2018 Approximation and Convergence Properties of Generative Adversarial Learning NIPS 2017 Active Heteroscedastic Regression ICML 2017 Renyi Differential Privacy Mechanisms for Posterior Sampling NIPS 2017 Active Learning from Imperfect Labelers NIPS 2016 The Extended Littlestone’s Dimension for Learning with Mistakes and Abstentions COLT 2016 Active Learning from Weak and Strong Labelers NIPS 2015 Learning from Data with Heterogeneous Noise using SGD AISTATS 2015 Spectral Learning of Large Structured HMMs for Comparative Epigenomics NIPS 2015 Convergence Rates of Active Learning for Maximum Likelihood Estimation NIPS 2015 The Large Margin Mechanism for Differentially Private Maximization NIPS 2014 Rates of Convergence for Nearest Neighbor Classification NIPS 2014 Beyond Disagreement-Based Agnostic Active Learning NIPS 2014 A Stability-based Validation Procedure for Differentially Private Machine Learning NIPS 2013 A Near-Optimal Algorithm for Differentially-Private Principal Components JMLR 2013 Near-optimal Differentially Private Principal Components NIPS 2012 Spectral Clustering of Graphs with General Degrees in the Extended Planted Partition Model COLT 2012 Sample Complexity Bounds for Differentially Private Learning COLT 2011 Spectral Methods for Learning Multivariate Latent Tree Structure NIPS 2011 Differentially Private Empirical Risk Minimization JMLR 2011 Rates of convergence for the cluster tree NIPS 2010 A Parameter-free Hedging Algorithm NIPS 2009 Privacy-preserving logistic regression NIPS 2008