Hi! I am a postdoctoral researcher at Empirical Inference department of Max Planck Institute for Intelligent Systems. My research interests are in self-supervised learning methods and interpretable representation learning. I did my Ph.D. at Skoltech under the supervision of Ivan Oseledets, during that time I was working on Numerical Linear Algebra methods for better approximation in learning and inference broadly across machine learning.

My resume is here. Feel free to reach out via e-mail: maremun at gmail dot com.

Selected Publications

M. Munkhoeva, I. Oseledets
Bridging Spectral Embedding and Matrix Completion in Self-Supervised Learning
in submission
preprint

A.Tsitsulin, M. Munkhoeva, B. Perrozi
Unsupervised Embedding Quality Evaluation
Workshop on Topology, Algebra and Geometry in Machine Learning (TAG-ML) at ICML 2023
paper

M. Pautov, N. Tursynbek, M. Munkhoeva, N. Muravev, A. Petiushko, and I. Oseledets
CC-Cert: A probabilistic approach to certify general robustness of neural networks
AAAI Conference on Artificial Intelligence (AAAI 2022)
paper

A.Tsitsulin, M. Munkhoeva, D. Mottin, P. Karras, I. Oseledets and E. Müller
FREDE: Linear-Space Anytime Graph Embeddings
International Conference on Very Large Databases (VLDB 2021)
paper, code

A.Tsitsulin*, M. Munkhoeva*, D. Mottin, P. Karras, A. Bronstein, I. Oseledets, E. Muller
The Shape of Data: Intrinsic Distance for Data Distributions
International Conference on Learning Representations (ICLR 2020).
paper, code

A.Tsitsulin*, M. Munkhoeva*, B.Perrozi
Just SLaQ When You Approximate: Accurate Spectral Distances for Web-Scale Graphs
International World Wide Web Conference (WWW 2020).
paper

M. Munkhoeva, Y. Kapushev, E. Burnaev and I. Oseledets
Quadrature-based Features for Kernel Approximation
Neural Information Processing Systems (NeurIPS 2018).
paper, code