Berfin Şimşek

Berfin Şimşek

doctoral researcher @ EPFL

About me

I am a fifth-year doctoral researcher at Ecole Polytechnique Fédérale de Lausanne (EPFL) in Computer and Communication Sciences. My thesis is supervised by Clément Hongler and co-supervised by Wulfram Gerstner.

My research focus is the theory of neural networks and other related areas, such as random features and out-of-distribution generalization. I am a theoretician working at the intersection of mathematics and physics, but I also enjoy large-scale experiments I partook in during a research internship at Meta AI.

I am currently on the job market!

Before my Ph.D., I studied Electrical-Electronics Engineering and Mathematics double-major at Koç University. I also earned two bronze medals in International Mathematical Olympiad (IMO). I am an avid Argentine Tango dancer.

Publications

Quickly discover relevant content by filtering publications.
Deep Linear Networks Dynamics: Low-Rank Biases Induced by Initialization Scale and L2 Regularization
Geometry of the Loss Landscape in Overparameterized Neural Networks: Symmetries and Invariances
Kernel Alignment Risk Estimator: Risk Prediction from Training Data