Lenka Zdeborová
Also known as Lenka Zdeborova
Lenka Zdeborová works across statistical physics, machine learning and inference. She earned a dual physics doctorate in 2008, spent two years at Los Alamos and researched at CEA Saclay before moving to EPFL in September 2020. With Florent Krzakala, she coauthored a review explaining how phase transitions reveal limits in inference and guide algorithm design. Her laboratory develops solvable models and theoretical principles for learning, generalization and memory. She received an ERC Starting Grant in 2016 and an Advanced Grant in 2025.
Timeline
-
2008–2010
Physics training and Los Alamos
Zdeborová received physics doctorates from Paris-Sud and Charles University in Prague in 2008. She spent the next two years as a Director’s Postdoctoral Fellow at Los Alamos National Laboratory.
-
2010–2020
Research at Saclay
She conducted CNRS research at the Institute of Theoretical Physics in CEA Saclay during 2010–2020.
-
2015–2016
Thresholds and inference algorithms
With Florent Krzakala, she reviewed statistical physics of inference. The work explains how phase transitions can identify barriers in recovering information from measurements, with examples from network communities and compressed sensing. It appeared as a preprint in 2015 and a journal review in 2016.
-
2020–2025
Build theory for learning systems
She joined EPFL in September 2020. Her lab studies models of how AI systems generalize, memorize and scale, and she received an ERC Advanced Grant in 2025.
Sources and credits
Photo: EPFL-MEDIACOM, via Wikimedia Commons. License: CC BY 4.0. Source: commons.wikimedia.org. Cropped to a square and resized. Ask us to remove or replace this photo.
