Kamalika Chaudhuri

Associate Professor
Computer Science and Engineering
University of California, San Diego
Office: EBU3B 4110
email: kamalika at cs dot ucsd dot edu
phone: 858-822-7703


I am giving a talk at the Nasa Formal Methods Workshop on AI Safety (May 2020).[Slides]
I am giving a Distinguished Lecture at Duke University, Department of Biostatistics (Feb 2020).
I am a Program Co-Chair for ICML 2019. In ICML 2019, for the first time in a major machine learning conference, we carried out a new code-at-submit-time experiment; see how it went here.
Slides for my tutorial on Nearest Neighbors and Adversarial Examples at the Simons Deep Learning Bootcamp now available. Video here.
I am giving a talk at the Simons Foundation Symposium on new directions in privacy-preserving data analysis.
Slides and video for my talk at the Mathematical Frontiers Webinar on the Mathematics of Differential Privacy are now up here.
I am the Program Co-Chair of AISTATS 2019.
Slides for my NIPS 2017 Tutorial with Anand Sarwate on Differentially Private Machine Learning are online.
More News



My research is on machine learning. I am interested in the foundations of trustworthy machine learning, which includes problems such as learning from sensitive data while preserving privacy, learning under sampling bias, and in the presence of an adversary. I am also broadly interested in a number of topics in learning theory, such as non-parametric methods, online learning, and active learning.

Here is a survey I wrote on machine learning with privacy. Here is an overview I wrote in 2008 about learning mixture models. Here is a press article on Biomedical Computation Review that talks about some of my work on privacy-preserving machine learning.

Here are the slides from a recent tutorial I gave with Annd Sarwate on differentially private machine learning. Here are the slides from a recent tutorial on non-parametric methods and adversarial examples.



Current

Joseph Geumlek

Yizhen Wang

Robi Bhattacharjee

Jacob Imola

Zhifeng Kong

Casey Meehan

Mary Anne Smart

Zhi Wang

Yaoyuan Yang

Alumni

Songbai Yan (PhD Student --> Google)

Shuang Song (PhD Student --> Google Brain)

Chicheng Zhang (PhD Student --> Postdoc at Microsoft Research, New York City --> University of Arizona)

Shengyang Shi (Undergraduate Student)

Siyang Wang (Undergraduate Student)

Edward Wong (MS Student)

Charles Packer (Undergraduate Student)

Judy Zhou (Undergraduate Student)

Ruiqing Qiu (Undergraduate Student)

Mingshan Wang (Undergraduate Student)

Sumithra Velupillai (Visiting Scholar)

Enrico Tanuwidjaja (Undergraduate Student)

Trung Thanh Lam (Undergraduate Student)

Hesler Rodriguez (Undergraduate Student)

Bowen Shu (Undergraduate Student)



CSE 151: Introduction to AI: A Statistical Approach
CSE 202: Graduate Algorithms
CSE 291: Machine Learning Theory
CSE 291: Advanced Topics in Learning Theory
CSE 291: Advanced Optimization
CSE 291: Topics in Online Learning and Bandit Problems


This is what Wordle thinks of my publication titles.

Adversarial Robustness through Local Lipschitzness
Yao-Yuan Yang, Cyrus Rashtchian, Hongyang Zhang, Ruslan Salakhutdinov and Kamalika Chaudhuri, Arxiv Pre-print, 2020.

When are Non-Parametric Methods Robust?
Robi Bhattacharjee and Kamalika Chaudhuri, Arxiv Pre-print, 2020.

Approximate Data Deletion from Machine Learning Models: Algorithms and Evaluation
Zachary Izzo, Mary Anne Smart, Kamalika Chaudhuri and James Zou, Arxiv Pre-print, 2020.

An Investigation of Data Poisoning Defenses for Online Learning
Yizhen Wang, Somesh Jha and Kamalika Chaudhuri, Arxiv Pre-print, 2019.

The Inductive Bias of Restricted f-GANs
Shuang Liu and Kamalika Chaudhuri, Arxiv Pre-print, 2018.

Differentially Private Continual Release of Graph Statistics
Shuang Song, Sanjay Mehta, Staal Vinterbo, Susan Little and Kamalika Chaudhuri, Arxiv Pre-print, 2018. [Code]

Data Poisoning Attacks Against Online Learning
Yizhen Wang and Kamalika Chaudhuri, Arxiv Pre-print, 2018.

Learning Mixtures of Gaussians using the k-means Algorithm
Kamalika Chaudhuri, Sanjoy Dasgupta and Andrea Vattani, Arxiv Pre-print, 2009

A Non-Parametric Test to Detect Data-Copying in Generative Models
Casey Meehan, Kamalika Chaudhuri and Sanjoy Dasgupta, Artificial Intelligence and Statistics (AISTATS), 2020.

The Expressive Power of a Class of Normalizing Flow Models
Zhifeng Kong and Kamalika Chaudhuri, Artificial Intelligence and Statistics (AISTATS), 2020.

Robustness for Non-Parametric Methods: A Generic Attack and Defense
Yao-Yuan Yang, Cyrus Rashtchian, Yizhen Wang and Kamalika Chaudhuri, Artificial Intelligence and Statistics (AISTATS), 2020.

Variational Bayes in Private Settings (VIPS)
Mijung Park, James Foulds, Kamalika Chaudhuri and Max Welling, Journal of AI Research (JAIR), Accepted, 2020.

Model Extraction and Active Learning
Varun Chandrasekaran, Kamalika Chaudhuri, Irene Giacomelli, Somesh Jha and Songbai Yan, Usenix Security, 2020.

Capacity Bounded Differential Privacy
Kamalika Chaudhuri, Jacob Imola and Ashwin Machanavajjhala, Neural Information Processing Systems (NeuRIPS), 2019.

The Label Complexity of Active Learning from Observational Data
Songbai Yan, Kamalika Chaudhuri and Tara Javidi, Neural Information Processing Systems (NeuRIPS), 2019.

Profile-Based Privacy for Locally Private Computations
Joseph Geumlek and Kamalika Chaudhuri, International Symposium on Information Theory (ISIT), 2019.

Active Learning from Logged Data
Songbai Yan, Kamalika Chaudhuri and Tara Javidi, International Conference on Machine Learning (ICML), 2018. [Code]

Analyzing the Robustness of Nearest Neighbors to Adversarial Examples
Yizhen Wang, Somesh Jha and Kamalika Chaudhuri, International Conference on Machine Learning (ICML), 2018. [Code]

Renyi Differential Privacy Mechanisms for Posterior Sampling
Joseph Geumlek, Shuang Song and Kamalika Chaudhuri, Neural Information Processing Systems (NIPS), 2017

Approximation and Convergence Properties of Generative Adversarial Learning
Shuang Liu, Olivier Bousquet and Kamalika Chaudhuri, Neural Information Processing Systems (NIPS), 2017

Composition Properties of Inferential Privacy for Time-Series Data
Shuang Song and Kamalika Chaudhuri, Allerton Conference on Communication, Control and Computing, 2017

Learning to Blame: Localizing Novice Type Errors with Data-Driven Diagnosis
Eric Seidel, Huma Sibghat, Kamalika Chaudhuri, Westley Weimer and Ranjit Jhala, Object-Oriented Programming, Systems, Languages and Applications (OOPSLA), 2017

Active Heteroscedastic Regression
Kamalika Chaudhuri, Prateek Jain and Nagarajan Natarajan, International Conference on Machine Learning (ICML), 2017

Bolt-On Differential Privacy for Stochastic Gradient Descent-based Analytics
Xi Wu, Fengan Li, Arun Kumar, Kamalika Chaudhuri, Somesh Jha and Jeff Naughton, ACM SIGMOD International Conference on Management of Data (SIGMOD), 2017

Pufferfish Privacy Mechanisms for Correlated Data
Shuang Song, Yizhen Wang and Kamalika Chaudhuri, ACM SIGMOD International Conference on Management of Data (SIGMOD), 2017

Practical Privacy for Expectation Maximization
Mijung Park, James Foulds, Kamalika Chaudhuri and Max Welling, International Conference on Artificial Intelligence and Statistics (AISTATS), 2017

Private Topic Modeling
Mijung Park, James Foulds, Kamalika Chaudhuri and Max Welling, NIPS Workshop on Private Multi-party Machine Learning, 2016

Active Learning from Imperfect Labelers
Songbai Yan, Kamalika Chaudhuri and Tara Javidi, Neural Information Processing Systems (NIPS) 2016

On the Theory and Practice of Privacy-preserving Bayesian Data Analysis
James Foulds, Joseph Geumlek, Max Welling and Kamalika Chaudhuri, Uncertainty in Artificial Intelligence (UAI) 2016

The Extended Littlestone's Dimension for Learning with Mistakes and Abstentions
Chicheng Zhang and Kamalika Chaudhuri, Conference on Learning Theory (COLT) 2016

Spectral Learning of Large Structured HMMs for Comparative Epigenomics
Chicheng Zhang, Jimin Song, Kamalika Chaudhuri and Kevin Chen, Neural Information Processing Systems (NIPS) 2015 [Code]

Active Learning from Weak and Strong Labelers
Chicheng Zhang and Kamalika Chaudhuri, Neural Information Processing Systems (NIPS) 2015

Convergence Rates of Active Learning for Maximum Likelihood Estimation
Kamalika Chaudhuri, Sham Kakade, Praneeth Netrapalli and Sujay Sanghavi, Neural Information Processing Systems (NIPS) 2015

Active Learning from Noisy and Abstention Feedback
Songbai Yan, Kamalika Chaudhuri and Tara Javidi, Allerton Conference on Communication, Control and Computing, 2015.

Crowdsourcing Feature Discovery via Adaptively Chosen Comparisons
James Y. Zou, Kamalika Chaudhuri and Adam Tauman Kalai, Conference on Human Computation and Crowdsourcing (HCOMP) 2015

Noisy Bayesian Active Learning
Mohammad Naghshvar, Tara Javidi and Kamalika Chaudhuri, IEEE Transactions of Information Theory, 2015

Learning from Data with Heterogenous Noise using SGD
Shuang Song, Kamalika Chaudhuri and Anand D. Sarwate, International Conference on Artificial Intelligence and Statistics (AISTATS) 2015

The Large Margin Mechanism for Differentially Private Maximization
Kamalika Chaudhuri, Daniel Hsu and Shuang Song, Neural Information Processing Systems (NIPS) 2014

Beyond Disagreement-Based Agnostic Active Learning
Chicheng Zhang and Kamalika Chaudhuri, Neural Information Processing Systems (NIPS) 2014

Rates of Convergence for Nearest Neighbor Classification
Kamalika Chaudhuri and Sanjoy Dasgupta, Neural Information Processing Systems (NIPS) 2014

Consistent Procedures for Cluster Tree Estimation and Pruning
Kamalika Chaudhuri, Sanjoy Dasgupta, Samory Kpotufe and Ulrike Von Luxburg, IEEE Transactions of Information Theory, 2014

Improved Algorithms for Confidence-Rated Prediction with Error Guarantees
Kamalika Chaudhuri and Chicheng Zhang, NIPS Workshop on Learning Faster From Easy Data, NIPS 2013

A Stability-based Validation Procedure for Differentially Private Machine Learning
Kamalika Chaudhuri and Staal Vinterbo, Neural Information Processing Systems (NIPS), 2013

Stochastic Gradient Descent with Differentially Private Updates
Shuang Song, Kamalika Chaudhuri and Anand Sarwate, GlobalSIP Conference, 2013

Signal Processing and Machine Learning with Differential Privacy: Theory, Algorithms and Challenges
Anand Sarwate and Kamalika Chaudhuri, IEEE Signal Processing Magazine, 2013

Near-Optimal Algorithms for Differentially Private Principal Components
Kamalika Chaudhuri, Anand Sarwate and Kaushik Sinha, Neural Information Processing Systems (NIPS), 2012

Convergence Rates for Differentially Private Statistical Estimation
Kamalika Chaudhuri and Daniel Hsu, International Conference on Machine Learning (ICML), 2012

Spectral Clustering of Graphs with General Degrees in the Extended Planted Partition Model
Kamalika Chaudhuri, Fan Chung and Alexander Tsiatas, Conference on Learning Theory (COLT), 2012

Spectral Methods for Learning Multivariate Latent Tree Structure
Animashree Anandkumar, Kamalika Chaudhuri, Daniel Hsu, Sham Kakade, Le Song and Tong Zhang, Neural Information Processing Systems (NIPS), 2011.

Sample Complexity Bounds for Differentially Private Learning
Kamalika Chaudhuri and Daniel Hsu, Conference on Learning Theory (COLT), 2011

Differentially Private ERM
Kamalika Chaudhuri, Claire Monteleoni, and Anand Sarwate, Journal of Machine Learning Research (JMLR), 2011. A previous version appeared in Neural Information Processing Systems (NIPS), 2008.

Rates of Convergence for the Cluster Tree
Kamalika Chaudhuri and Sanjoy Dasgupta, Neural Inf. Processing Systems (NIPS), 2010.

An Online Learning-based Framework for Tracking
Kamalika Chaudhuri, Yoav Freund and Daniel Hsu, Uncertainty in Artificial Intelligence (UAI), 2010

A New Parameter-Free Hedging Algorithm
Kamalika Chaudhuri, Yoav Freund and Daniel Hsu, Neural Information Processing Systems (NIPS), 2009

Online Bipartite Matching with Augmentations
Kamalika Chaudhuri, Costis Daskalakis, Robert Kleinberg and Henry Lin, International Conf. on Computer Communications (INFOCOM), 2009

Multiview Clustering via Canonical Correlation Analysis
Kamalika Chaudhuri , Sham Kakade, Karen Livescu and Karthik Sridharan, International Conf. on Machine Learning (ICML), 2009. [Full proofs ]

A Network Coloring Game
Kamalika Chaudhuri, Fan Chung Graham, Mohammad S. Jamall, Workshop on Internet and Network Econimics (WINE), 2008.

Finding Metric Structure in Information-Theoretic Clustering
Kamalika Chaudhuri and Andrew McGregor, Conference on Learning Theory (COLT), 2008

Beyond Gaussians: Spectral Methods for Learning Mixtures of Heavy-Tailed Distributions
Kamalika Chaudhuri and Satish Rao, Conference on Learning Theory (COLT), 2008

Learning Mixtures of Product Distributions using Correlations and Independence
Kamalika Chaudhuri and Satish Rao, Conference on Learning Theory (COLT), 2008

Privacy, Accuracy, and Consistency Too: A Holistic Solution to Contingency Table Release
Boaz Barak, Kamalika Chaudhuri, Cynthia Dwork, Satyen Kale, Frank Mcsherry and Kunal Talwar, Principles of Database Systems (PODS), 2007

A Rigorous Analysis of Population Stratification with Limited Data
Kamalika Chaudhuri, Eran Halperin, Satish Rao and Shuheng Zhou, Symposium on Discrete Algorithms (SODA), 2007 [Slides]

Push-Relabel and an Improved Approximation Algorithm for the Bounded-degree MST Problem
Kamalika Chaudhuri, Satish Rao, Samantha Riesenfeld, and Kunal Talwar, International Conference on Automata, Languages, and Programming (ICALP), 2006.

When Random Sampling preserves Privacy
Kamalika Chaudhuri and Nina Mishra, International Cryptology Conference (CRYPTO), 2006

On the tandem duplication-random loss model of genome rearrangement
Kamalika Chaudhuri, Kevin Chen, Radu Mihaescu, and Satish Rao, Symposium of Discrete Algorithms (SODA), 2006

Server Allocation Algorithms for Tiered Systems
Kamalika Chaudhuri, Anshul Kothari, Rudi Pendavingh, Ram Swaminathan, Robert Tarjan, and Yunhong Zhou, International Computing and Combinatorics Conference (COCOON), 2005

What would Edmonds do? Augmenting Paths, Witnesses and Improved Approximations for Bounded-degree MSTs
Kamalika Chaudhuri, Satish Rao, Samantha Riesenfeld, and Kunal Talwar, Workshop on Approximation Algorithms for Combinatorial Optimization Problems (APPROX), 2005. [Slides]

Value-Maximizing Deadline Scheduling and its Application to Animation Rendering
Eric Anderson, Dirk Beyer, Kamalika Chaudhuri, Terrance Kelly, Norman Salazar, Ciprano Santos, Ram Swaminathan, Robert Tarjan, Janet Wiener, and Yunhong Zhou, Symposium on Parallelism in Algorithms and Architecture (SPAA), 2005

Selfish Caching in Distributed Systems: A Game Theoretic Analysis
Byung-Gon Chun, Kamalika Chaudhuri, Hoeteck Wee, Marco Barreno, Christos Papadimitriou, and John Kubiatowicz, Principles of Distributed Computing (PODC), 2004

Paths, Trees and Minimum Latency Tours
Kamalika Chaudhuri, Brighten Godfrey, Satish Rao, and Kunal Talwar, Foundations of Computer Science (FOCS), 2003. [Slides]

Learning Mixtures of Distributions
Kamalika Chaudhuri, Ph.D Dissertation,
UC Berkeley, 2007