I am a PhD student in Applied Mathematics at UMD advised by Prof. Tom Goldstein and my research interests include interpretability and robustness of deep neural networks. Recently, I have started working in fairness in machine learning.
Prior to my PhD I received bachelor’s degree in mathematics from Higher School of Economics (Moscow) and master’s degree in computational biology from University College London (London).
PhD in Applied Mathematics, 2023
University of Maryland
MSc in Computational Biology, 2018
University College London
BSc in Mathematics, 2017
Higher School of Economics
In this project we aim to analyse unintended consequences of fairness constraints in facial recognition systems.
In this project we develop a tool to protect photos shared online from facial recognition systems.
Meta-learning algorithms produce feature extractors which achieve state-of-the-art performance on few-shot classification. While the literature is rich with meta-learning methods, little is known about why the resulting feature extractors perform so well. We develop a better understanding of the underlying mechanics of meta-learning and the difference between models trained using meta-learning and models which are trained classically. In doing so, we introduce and verify several hypotheses for why meta-learned models perform better. Furthermore, we develop a regularizer which boosts the performance of standard training routines for few-shot classification. In many cases, our routine outperforms meta-learning while simultaneously running an order of magnitude faster..
An accurate and simple risk prediction model that would facilitate earlier detection of pancreatic adenocarcinoma (PDAC) is not available at present. In this study, we compare different algorithms of risk prediction in order to select the best one for constructing a biomarker-based risk score, PancRISK.