Contact

Email: kc (dot) tsiolis (at) mail (dot) utoronto (dot) ca

Bio

Hello world! My full name is Konstantinos Christopher Tsiolis, but I go by my initials “KC”. I am a first-year Ph.D. student in Statistics at the University of Toronto and the Vector Institute under the supervision of Murat Erdogdu. I am broadly interested in developing a rigorous theoretical understanding of deep learning. More specifically, my current research involves using tools from high-dimensional probability to describe the behaviour of stochastic optimization methods.

I proudly hail from beautiful Montreal, QC and completed my previous studies there. I received my M.Sc. in Mathematics and Statistics at McGill University and Mila under the supervision of Adam Oberman. My thesis research was on contrastive self-supervised learning methods. During this time, I also collaborated with Elliot Paquette on random matrix theory for neural networks.

I graduated with a B.Sc. from McGill in Honours Mathematics and Computer Science in 2021. During my first two summers of undergraduate studies, I was a research assistant at Mila and the McGill Reasoning and Learning Lab under the supervision of Jackie Cheung, where I worked on word embeddings and computational pragmatics.

CV

You can view my CV here.

Publications

Jingyi He, KC Tsiolis, Kian Kenyon-Dean, and Jackie Chi Kit Cheung. 2020. Learning Efficient Task-Specific Meta-Embeddings with Word Prisms. Proceedings of the 28th International Conference on Computational Lingusitics, pages 1229-1241. [pdf]

Research Summaries

KC Tsiolis. 2023. Contrastive Learning as Kernel Approximation. Master’s Thesis. McGill University. [pdf]

KC Tsiolis. 2020. Quantifier Scope Disambiguation. Summary of research conducted in Summer 2020 under the supervision of Jackie Cheung. [pdf]

KC Tsiolis. 2019. Dual Representations of Words with Asymmetric Contexts. Summary of research conducted in Summer 2019 with Jingyi He and Edward Newell, supervised by Jackie Cheung. [pdf]

Teaching

TAships at U of T

Winter 2025: STA261 (Probability and Statistics II)
Fall 2024: STA314 (Statistical Methods for Machine Learning I)
Winter 2024: STA221 (The Practice of Statistics II)
Fall 2023: STA130 (Introduction to Statistical Reasoning and Data Science)

TAships at McGill

Fall 2022: MATH 222 (Calculus 3)
Fall 2021: COMP 251 (Algorithms and Data Structures)