Kamalika Chaudhuri’s research interests are in machine-learning, a subfield that lies at the intersection of statistics and computer science. She is interested in three aspects of machine-learning -- unsupervised learning, online learning and privacy-preserving machine learning. In unsupervised learning, the goal is to extract information from unlabeled data to assist various learning tasks. In online learning, data arrives one at a time, and the challenge is to make good predictions on the face of changing data and models. Privacy-preserving machine learning addresses the problem of learning a good predictor from the data, while ensuring the privacy of individuals in the training data set.