My current research focuses on regression models in the context of the high-dimensional and semi-supervised setting. In such a setting, an important and challenging goal is to quantify how much variation in the response variable can be explained by the predictors, versus how much of the variation is left unexplained. My research aims to improve current methods of performing statistical inference by incorporating the additional information that is available in the unlabeled data.
Co-advised with David Azriel
Continue Reading Ilan Livne
I currently focus on method development of kernel machines on missing responses, missing covariates, and multiple instances of data where instances are arranged in bags. In survival analysis, I am working on hypothesis testing when the survival curves are crossing.
Co-advised with Jin Xu
. Continue Reading Titantian Liu
Working to estimate the uncertainty in a single prediction task, i.e., given an algorithm and a new sample, how confident can we be with its prediction? Continue Reading Oron Madmon
I am a Ph.D. candidate studying statistics and machine learning. Our research goal is to provide statistical inference for machine learning techniques such as kernel machines and deep learning. We will utilize Bayesian methods to quantify uncertainty, to select hyper-parameter values, and to bound the generalization error. Continue Reading Yael Travis-Lumer
Valentin Vancak, Ph.D. (2021)
Systematic Analysis of the Number Needed to Treat
Yotam Leibovici, M.Sc. (2020)
Improving Efficiency of Tests for Composite Null Hypotheses
Jonathan Yefe-Nof, Ph.D., (2020) Co-advised with Ya’acov Ritov
Challenges in statistical inference for complicated datasets structures
Yael Travis-Lumer, M.Sc. (2016)
Support Vector Machines for Current Status Data
Valentin Vancak, M.Sc. (2016)
Continuous Statistical Models: With or Without Truncation Parameters?
Afraa Araidy, M.Sc. (2014)
Fitting Models for Twins Data with Missing Data