Marko Medvedev

About

I work on data-centric machine learning. I am also interested in the theory of deep learning.

I am a fifth-year PhD student at The University of Chicago, advised by Professor Nathan Srebro and Professor Alexander Razborov. Before joining UChicago, I obtained my Bachelor of Arts in Mathematics from Princeton University.

Publications

1. Learning through Internalization

   Nikolaos Tsilivis, Nirmit Joshi, Marko Medvedev, Julia Kempe, Nathan Srebro

   SubmittedarXiv

2. Positive Distribution Shift as a Framework for Understanding Tractable Learning

   Marko Medvedev, Idan Attias, Elisabetta Cornacchia, Theodor Misiakiewicz, Gal Vardi, Nathan Srebro

   ICML 2026arXiv

3. Shift is Good: Mismatched Data Mixing Improves Test Performance

   Marko Medvedev, Kaifeng Lyu, Zhiyuan Li, Nathan Srebro

   AISTATS 2026arXiv

4. Weak-to-Strong Generalization Even in Random Feature Networks, Provably

   Marko Medvedev, Kaifeng Lyu, Dingli Yu, Sanjeev Arora, Zhiyuan Li, Nathan Srebro

   ICML 2025arXiv

5. Overfitting Behaviour of Gaussian Kernel Ridgeless Regression: Varying Bandwidth or Dimensionality

   Marko Medvedev, Gal Vardi, Nathan Srebro

   NeurIPS 2024arXiv

6. Refinement of Chebotarev's density theorem in SL₂(Z)

   Marko Medvedev

   Senior Thesis, Princeton University

Talks

1. Weak-to-Strong Generalization Even in Random Feature Networks, Provably

   Deep Learning Theory Workshop, Simons Institute for the Theory of Computing

   February 2025