Eren C. Kızıldağ

e-mail : eck2170@columbia.edu

I am a Founder's Postdoctoral Fellow at Columbia University, Department of Statistics. I received my PhD in Electrical Engineering and Computer Science from MIT, where I was very fortunate to be advised by David Gamarnik. At MIT, I was affiliated with the Laboratory for Information and Decision Systems (LIDS) and the Institute for Data, Systems, and Society (IDSS). You can find my CV here.

Research Interests

My research is a mix of probability, statistics and data science, and computer science. More specifically, I am interested in understanding computational tractability of random optimization problems and statistical inference models and in the mathematics of data science.

Journal Papers and Preprints

Planted Random Number Partitioning Problem
Eren C. Kızıldağ
Under review, 2024+
[Paper]

Sharp Phase Transition for Multi Overlap Gap Property in Ising p-Spin Glass and Random k-SAT Models
Eren C. Kızıldağ
Under review, 2024+
[Paper]

Shattering in the Ising Pure p-Spin Model
David Gamarnik, Aukosh Jagannath, Eren C. Kızıldağ
Under review, 2024+
[Paper]

Algorithmic Obstructions in the Random Number Partitioning Problem
David Gamarnik, Eren C. Kızıldağ
Annals of Applied Probability, 2023
[Paper] [Slides] [Talk] [Poster]
Conference version in ISIT 2022

Stationary Points of Shallow Neural Networks with Quadratic Activation Function
David Gamarnik, Eren C. Kızıldağ, Ilias Zadik
Mathematics of Operations Research, 2024
[Paper] [Slides] [Talk]

Symmetric Binary Perceptron with Random Labels: Capacity, Universality, and Overlap Gap Property
Eren C. Kızıldağ, Tanay Wakhare
Preprint, 2023

Self-Regularity of Non-Negative Output Weights for Overparameterized Two-Layer Neural Networks
David Gamarnik, Eren C. Kızıldağ, Ilias Zadik
IEEE Transactions on Signal Processing, 2022
[Paper] [Slides]
Conference version in ISIT 2021

Computing the Partition Function of the Sherrington-Kirkpatrick Model is Hard on Average
David Gamarnik, Eren C. Kızıldağ
Annals of Applied Probability, 2021
[Paper] [Slides]
Conference version in ISIT 2020

Inference in High-Dimensional Linear Regression via Lattice Basis Reduction and Integer Relation Detection
David Gamarnik, Eren C. Kızıldağ, Ilias Zadik
IEEE Transactions on Information Theory, 2021
[Paper]

Neural Networks and Polynomial Regression. Demystifying the Overparametrization Phenomena
Matt Emschwiller, David Gamarnik, Eren C. Kızıldağ, Ilias Zadik
Preprint, 2020
[Paper]

Conference Papers

A Random CSP with Connections to Discrepancy Theory and Randomized Trials
Eren C. Kızıldağ
IEEE International Symposium on Information Theory (ISIT), 2024 (To Appear)
[Extended Paper]

Geometric Barriers for Stable and Online Algorithms for Discrepancy Minimization
David Gamarnik, Eren C. Kızıldağ, Will Perkins, Changji Xu
Conference on Learning Theory (COLT), 2023
[Paper]

Symmetric Perceptron with Random Labels
Eren C. Kızıldağ, Tanay Wakhare
International Conference on Sampling Theory and Applications (SampTA), 2023
[Paper] [Slides]

Algorithms and Barriers in the Symmetric Binary Perceptron Model
David Gamarnik, Eren C. Kızıldağ, Will Perkins, Changji Xu
IEEE Symposium on Foundations of Computer Science (FOCS), 2022
[Paper] [Slides] [Poster]

The Random Number Partitioning Problem: Overlap Gap Property and Algorithmic Barriers
David Gamarnik, Eren C. Kızıldağ
IEEE International Symposium on Information Theory (ISIT), 2022
[Paper]

Self-Regularity of Output Weights for Overparameterized Two-Layer Neural Networks
David Gamarnik, Eren C. Kızıldağ, Ilias Zadik
IEEE International Symposium on Information Theory (ISIT), 2021
[Paper] [Slides]

Computing the Partition Function of the Sherrington-Kirkpatrick Model is Hard on Average
David Gamarnik, Eren C. Kızıldağ
IEEE International Symposium on Information Theory (ISIT), 2020
[Paper] [Slides]

High-Dimensional Linear Regression and Phase Retrieval via PSLQ Integer Relation Algorithm
David Gamarnik, Eren C. Kızıldağ
IEEE International Symposium on Information Theory (ISIT), 2019
[Paper] [Slides]

Thesis

Algorithms and Algorithmic Barriers in High-Dimensional Statistics and Random Combinatorial Structures
Ph.D thesis, Massachusetts Institute of Technology, 2022
[PDF]

Other Biographical Notes

I earned my B.S. degree with highest honors (summa cum laude) in Electrical and Electronics Engineering from Bogaziçi University, Istanbul, Turkey in 2014; and my M.S. degree in EECS from MIT in 2017. I did experimental research on magnetic resonance imaging (MRI) for my Master's thesis. Part of my thesis work appeared in the 24th Annual Meeting of International Society for Magnetic Resonance in Medicine (ISMRM), Singapore, 2016; and received a summa cum laude award (top 5% of all submitted works). Slides of my talk is available here.

I am a proud graduate of Ankara Science High School (AFL), class of 2010.