Filip Kovačević

I am a PhD student at ISTA, supervised by Prof. Marco Mondelli.

Before that, I have obtained a MS in Mathematics from ETH Zurich, and a BS in Mathematics from University of Belgrade.

My interest lies at the interestion of mathematics and machine learning. More specifically, I am currently exploring the use of high-dimensional probability, random matrix theory and information theory to provide theoretical gurantees for algorithm analysis.

Email  /  CV  /  GitHub  /  Google Scholar  /  LinkedIn

profile photo

Publications
project image

Spectral Estimators for Multi-Index Models: Precise Asymptotics and Optimal Weak Recovery


Filip Kovačević, Yihan Zhang, Marco Mondelli
COLT, 2025
arxiv /

We provide a precise analysis of spectral methods for recovering low-dimensional signal subspaces in multi-index models, revealing a phase transition phenomenon that determines exactly when these methods succeed and enabling minimization of the needed sample size.
project image

Learning Pareto manifolds in high dimensions: How can regularization help?


Tobias Wegel, Filip Kovačević, Alexandru Ţifrea, Fanny Yang
AISTATS, 2025
arxiv / poster /

We discuss how the application of vanilla regularization approaches can fail, and propose a two-stage MOL framework that can successfully leverage low-dimensional structure.



Teaching

ETH Zurich, TA: Linear Algebra (Spring 2022), Algebra 1 (Spring 2023), Algebra 2 (Fall 2023)

University of Belgrade, TA: Linear Algebra (Fall 2020)


Design and source code from Leonid Keselman's website