
Model Extraction and Active Learning
Machine learning is being increasingly used by individuals, research ins...
11/05/2018 ∙ by Varun Chandrasekaran, et al. ∙ 14 ∙ shareread it

Rényi Differential Privacy Mechanisms for Posterior Sampling
Using a recently proposed privacy definition of Rényi Differential Priva...
10/02/2017 ∙ by Joseph Geumlek, et al. ∙ 0 ∙ shareread it

Composition Properties of Inferential Privacy for TimeSeries Data
With the proliferation of mobile devices and the internet of things, dev...
07/10/2017 ∙ by Shuang Song, et al. ∙ 0 ∙ shareread it

Analyzing the Robustness of Nearest Neighbors to Adversarial Examples
Motivated by applications such as autonomous vehicles, testtime attacks...
06/13/2017 ∙ by Yizhen Wang, et al. ∙ 0 ∙ shareread it

Approximation and Convergence Properties of Generative Adversarial Learning
Generative adversarial networks (GAN) approximate a target data distribu...
05/24/2017 ∙ by Shuang Liu, et al. ∙ 0 ∙ shareread it

Variational Bayes In Private Settings (VIPS)
We provide a general framework for privacypreserving variational Bayes ...
11/01/2016 ∙ by Mijung Park, et al. ∙ 0 ∙ shareread it

Active Learning from Imperfect Labelers
We study active learning where the labeler can not only return incorrect...
10/30/2016 ∙ by Songbai Yan, et al. ∙ 0 ∙ shareread it

Private Topic Modeling
We develop a privatised stochastic variational inference method for Late...
09/14/2016 ∙ by Mijung Park, et al. ∙ 0 ∙ shareread it

Bolton Differential Privacy for Scalable Stochastic Gradient Descentbased Analytics
While significant progress has been made separately on analytics systems...
06/15/2016 ∙ by Xi Wu, et al. ∙ 0 ∙ shareread it

DPEM: Differentially Private Expectation Maximization
The iterative nature of the expectation maximization (EM) algorithm pres...
05/23/2016 ∙ by Mijung Park, et al. ∙ 0 ∙ shareread it

On the Theory and Practice of PrivacyPreserving Bayesian Data Analysis
Bayesian inference has great promise for the privacypreserving analysis...
03/23/2016 ∙ by James Foulds, et al. ∙ 0 ∙ shareread it

Pufferfish Privacy Mechanisms for Correlated Data
Many modern databases include personal and sensitive correlated data, su...
03/13/2016 ∙ by Shuang Song, et al. ∙ 0 ∙ shareread it

Active Learning from Weak and Strong Labelers
An active learner is given a hypothesis class, a large set of unlabeled ...
10/09/2015 ∙ by Chicheng Zhang, et al. ∙ 0 ∙ shareread it

Convergence Rates of Active Learning for Maximum Likelihood Estimation
An active learner is given a class of models, a large set of unlabeled e...
06/08/2015 ∙ by Kamalika Chaudhuri, et al. ∙ 0 ∙ shareread it

Spectral Learning of Large Structured HMMs for Comparative Epigenomics
We develop a latent variable model and an efficient spectral algorithm m...
06/04/2015 ∙ by Chicheng Zhang, et al. ∙ 0 ∙ shareread it

Crowdsourcing Feature Discovery via Adaptively Chosen Comparisons
We introduce an unsupervised approach to efficiently discover the underl...
03/31/2015 ∙ by James Y. Zou, et al. ∙ 0 ∙ shareread it

Beyond Disagreementbased Agnostic Active Learning
We study agnostic active learning, where the goal is to learn a classifi...
07/10/2014 ∙ by Chicheng Zhang, et al. ∙ 0 ∙ shareread it

Rates of Convergence for Nearest Neighbor Classification
Nearest neighbor methods are a popular class of nonparametric estimators...
06/30/2014 ∙ by Kamalika Chaudhuri, et al. ∙ 0 ∙ shareread it

Differentially Private Empirical Risk Minimization
Privacypreserving machine learning algorithms are crucial for the incre...
12/01/2009 ∙ by Kamalika Chaudhuri, et al. ∙ 0 ∙ shareread it

NearOptimal Algorithms for DifferentiallyPrivate Principal Components
Principal components analysis (PCA) is a standard tool for identifying g...
07/12/2012 ∙ by Kamalika Chaudhuri, et al. ∙ 0 ∙ shareread it

Convergence Rates for Differentially Private Statistical Estimation
Differential privacy is a cryptographicallymotivated definition of priv...
06/27/2012 ∙ by Kamalika Chaudhuri, et al. ∙ 0 ∙ shareread it

An Online Learningbased Framework for Tracking
We study the tracking problem, namely, estimating the hidden state of an...
03/15/2012 ∙ by Kamalika Chaudhuri, et al. ∙ 0 ∙ shareread it

Spectral Methods for Learning Multivariate Latent Tree Structure
This work considers the problem of learning the structure of multivariat...
07/07/2011 ∙ by Kamalika Chaudhuri, et al. ∙ 0 ∙ shareread it

Tracking using explanationbased modeling
We study the tracking problem, namely, estimating the hidden state of an...
03/16/2009 ∙ by Kamalika Chaudhuri, et al. ∙ 0 ∙ shareread it

Spectral Learning of Binomial HMMs for DNA Methylation Data
We consider learning parameters of Binomial Hidden Markov Models, which ...
02/07/2018 ∙ by Chicheng Zhang, et al. ∙ 0 ∙ shareread it

Active Learning with Logged Data
We consider active learning with logged data, where labeled examples are...
02/25/2018 ∙ by Songbai Yan, et al. ∙ 0 ∙ shareread it

Learning to Blame: Localizing Novice Type Errors with DataDriven Diagnosis
Localizing type errors is challenging in languages with global type infe...
08/25/2017 ∙ by Eric L. Seidel, et al. ∙ 0 ∙ shareread it

Data Poisoning Attacks against Online Learning
We consider data poisoning attacks, a class of adversarial attacks on ma...
08/27/2018 ∙ by Yizhen Wang, et al. ∙ 0 ∙ shareread it

Differentially Private Continual Release of Graph Statistics
Motivated by understanding the dynamics of sensitive social networks ove...
09/07/2018 ∙ by Shuang Song, et al. ∙ 0 ∙ shareread it

The Inductive Bias of Restricted fGANs
Generative adversarial networks are a novel method for statistical infer...
09/12/2018 ∙ by Shuang Liu, et al. ∙ 0 ∙ shareread it

The Label Complexity of Active Learning from Observational Data
Counterfactual learning from observational data involves learning a clas...
05/29/2019 ∙ by Songbai Yan, et al. ∙ 0 ∙ shareread it

An Investigation of Data Poisoning Defenses for Online Learning
We consider data poisoning attacks, where an adversary can modify a smal...
05/28/2019 ∙ by Yizhen Wang, et al. ∙ 0 ∙ shareread it

Adversarial Examples for NonParametric Methods: Attacks, Defenses and Large Sample Limits
Adversarial examples have received a great deal of recent attention beca...
06/07/2019 ∙ by YaoYuan Yang, et al. ∙ 0 ∙ shareread it

Capacity Bounded Differential Privacy
Differential privacy, a notion of algorithmic stability, is a gold stand...
07/03/2019 ∙ by Kamalika Chaudhuri, et al. ∙ 0 ∙ shareread it
Kamalika Chaudhuri
is this you? claim profile
Assistant Professor at University of California at San Diego, Postdoc at University of California at San Diego from 20072010, Intern at Microsoft 2006, Intern at IBM 2005, Intern at HewlettPackard 2004, Intern at INRIA 2001