Valeria Cherepanova

Valeria Cherepanova

PhD Student in Applied Math

University of Maryland

Biography

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).

Interests

  • Machine Learning

Education

  • PhD in Applied Mathematics, 2023

    University of Maryland

  • MSc in Computational Biology, 2018

    University College London

  • BSc in Mathematics, 2017

    Higher School of Economics

Experience

 
 
 
 
 

Lecturer

University of Maryland

Aug 2020 – Dec 2020 Maryland
Preparing lecturing material, teaching, and managing the STAT100 course.
 
 
 
 
 

Graduate Research Assistant

University of Maryland

May 2020 – Aug 2020 Maryland
Developing a tool based on adversarial perturbations for protecting photos people share online. More info about this research can be found in Projects.
 
 
 
 
 

Graduate Research Assistant

University of Maryland

May 2019 – Aug 2019 Maryland
Investigating the behaviour of approximate solutions to PDEs of order two and higher built as a linear combination of Generalized Plane Waves in the high frequency regime.
 
 
 
 
 

Data Analysis Intern

Teradata

Jul 2016 – Oct 2016 Moscow
Helping consultants with deploying machine learning methods in projects.

Projects

Can we trust fairness?

In this project we aim to analyse unintended consequences of fairness constraints in facial recognition systems.

Hiding from Facial Recognition

In this project we develop a tool to protect photos shared online from facial recognition systems.

Contact

  • 301 401 04 54
  • 4176 Campus Drive - Kirwan Hall, College Park, MD 20740
  • Office 4204