Azar Louzi

Postdoctoral Researcher (2026-2028) - Certifiable AI and Stochastics

Xuwei Yang

Postdoctoral Researcher (2022-2025) - AI in Game Theory and Stochastics

Ruiyang Hong

PhD Candidate (2023-2027) - Foundations of AI

Yicen Li

PhD Candidate (2022-2026) - Deep Clustering

Hossein Rouhvarzi

MSc to PhD Candidate (2024-2028) - Foundations of Geometric Deep Learning

Dennis Zvigelsky

PhD Candidate (2025-2029) - AI Reasoning (Joint: Bradd Hart)

Hrad Ghoukasian

Visiting PhD Student (2026) - AI Safety and Fairness

(University of Toronto)

Alessio Spagnoletti

MSc Candidate (2022-2024) - Operator Learning in Finance

Co-Supervised at: Scuola Normale Superiore di Pisa

Reza Arabpour

MSc (2023-2025) - Hypernetworks for time-series prediction (CSE)

Kyle Sung

NSERC BSc Math (2024-2028) - Statistical Learning Theory

Kholood Khalil

BSc Math 2024, Summer Researcher - Adaptive Gradient Descent

Steven Samu

Computer Engineering 2025, Summer Researcher - Deep Learning

Trevor Tidy

Honors BSc Math (2024-2025) - Foundations of Geometric Deep Learning

Small Transformers Compute Universal Metric Embeddings

A Kratsios, V Debarnot, I Dokmanić, 2022

Designing Universal Causal Deep Learning Models: The Geometric (Hyper) Transformer

A. Accaio, A. Kratsios and G. Pammer, Mathematical Finance, 2022.

Do ReLU Networks Have An Edge When Approximating Compactly-Supported Functions?

A. Kratsios and B. Zamanlooy, TMLR, 2022.

Bridging the Gap Between Approximation and Learning via Optimal Approximation by ReLU MLPs of Maximal Regularity

R. Hong and A. Kratsios

Filtered not Mixed: Stochastic Filtering-Based Online Gating for Mixture of Large Language Models

R. Saquer, Y. Limmer, A. Kratsios, F. Krach, B. Horvath, etc, ICLR, 2025.

Neural Spacetimes for DAG Representation Learning

H. Borde Ocariz, A. Kratsios, T. Law, X. Dong, M. Bronstein, ICLR, 2025.

A Comprehensive Analysis on the Learning Curve in Kernel Ridge Regression

T. Cheng, A. Lucci, A. Kratsios, D. Belius, NeurIPS, 2024.

Inverse Entropic Optimal Transport Solves Semi-supervised Learning via Data Likelihood Maximization

M. Persiianov, A. Asadulaev, N. Andreev, A. Kratsios, A. Korotin, E. Burnaev, etc

Optimizing Optimizers: Regret-optimal gradient descent algorithms

P. Casgrain and A. Kratsios, COLT, 2021.

Designing Universal Causal Deep Learning Models: The Case of Infinite-Dimensional Dynamical Systems from Stochastic Analysis

L Galimberti, G Livieri, A Kratsios, 2022.

NEU: A meta-algorithm for universal uap-invariant feature representation

A. Kratsios and C. Hyndman, JMLR, 2021.

Universal Approximation Under Constraints is Possible with Transformers

A. Kratsios, B. Zamanlooy, I. Dokmanic, T. Liu, ICLR (Spotlight), 2022

Learning Sub-Patterns in Piece-Wise Continuous Functions

A. Kratsios and B. Zamanlooy, Neurocomputing, 2022.

Instance-Dependent Generalization Bounds via Optimal Transport

S Hou, P Kassraie, A Kratsios, J Rothfuss, A Krause, 2022.

Universal Regular Conditional Distributions

A. Kratsios, 2021.

Denise: Deep Robust Principal Component Analysis for Positive Semidefinite Matrices

LC Herrera, F Krach, A Kratsios, P Ruyssen, J Teichmann, 2021.