Anastasis develops and studies universal deep learning models capable of leveraging geometric structures in data science and time-series problems. He is now an Assistant Professor at McMaster University, Ontario, Canada.

## Research interests

**Geometric Deep Learning**

- Developed the first neural model which can proveably approximate any function while implementing exact constraint satisfaction
*with*B. Zamanlooy, I. Dokmanic, T. Liu. - Developed a simple framework for building universal approximators between any differentiable manifold
*with*L. Papon and E. Bilokopytov. - Introduced the universal the first known class of UAP (Universal Approximation Property)-Invariant feature maps
*with*C. Hyndman. - Identified the first known homotopic obstructions to non-Euclidean universal approximation
*with*L. Papon.

**Foundations of Data Science**

- Developed the first probability-measure valued universal approximator and showed that it can approximate any regular conditional distribution.
- Introduced the first regret-optimal descent algorithms via control and variational approach to meta-optimization
*with*P. Casgrain. - Developed the first deep neural model capable of uniformly approximating any piecewise continuous function with finitely many pieces
*with*B. Zamanlooy.

**Mathematical Finance**

- Introduced the first penalty for arbitrage-free learning
*with*C. Hyndman. - Introduce the fastest matrix completion algorithm for rapid low-rank + sparse decomposition of asset's covariance matrices
*with*J. Teichmann, C. Herrera, F. Krach, and Google Research's P. Ruyssen.