Anastasiia Koloskova
Stanford University
anastasiia.koloskova.v@gmail.com
Bio
I am a postdoc at Stanford University advised by Prof. Sanmi Koyejo. Previously I completed my PhD at EPFL, Switzerland under supervision of Prof. Martin Jaggi. My research interests lie in machine learning, optimization, and their intersections with decentralized learning, collaborative learning, and privacy. My PhD was supported by Google PhD Fellowship 2021-2024.
Areas of Research
- Machine Learning
Optimization Algorithms for Decentralized, Distributed and Collaborative Machine Learning
In distributed learning, multiple workers (e.g., GPUs) contribute in parallel to expedite the training of machine learning models. In collaborative learning, the training data is distributed among several participants due to the privacy-sensitive nature of the data, and these participants collaborate to solve a common machine learning task. My research focuses on various challenges encountered in both scenarios, including communication efficiency, data heterogeneity, and privacy protection of the training data. From an optimization theory perspective, we analyze existing widespread algorithms and, based on theoretical findings, propose more efficient training schemes.