KC Tsiolis

KC Tsiolis

PhD Student in Statistics at the University of Toronto

Publications

You can also find my articles on my Google Scholar profile.

Preprints

SGD in Multiclass Logistic Regression: Sequential Learning and Scaling Laws

Preprint (Under Review), 2026

Abstract: We study the training dynamics of multiclass logistic regression on high-dimensional Gaussian mixture models with a large number of classes and establish precise scaling laws governing the cross-entropy risk under gradient-based optimization. We show that learning proceeds sequentially across classes, from most to least frequent. When the class priors follow a power law distribution, the risk dynamics decompose into three phases: an initial plateau until the first class is learned, a power-law decay regime during which sequential learning occurs, and a final convergence regime.

Recommended citation: Konstantinos Christopher Tsiolis, Denny Wu, Christos Thrampoulidis, and Murat A. Erdogdu. SGD in Multiclass Logistic Regression: Sequential Learning and Scaling Laws arXiv preprint arXiv:2609.07868, 2026.
Download

Conference Papers

Learning Efficient Task-Specific Embeddings with Word Prisms

Published in The 28th International Confernence on Comutational Linguistics (COLING), 2020

Recommended citation: Jingyi He, KC Tsiolis, Kian Kenyon-Dean, and Jackie Chi Kit Cheung. Learning Efficient Task-Specific Meta-Embeddings with Word Prisms. In Proceedings of the 28th International Conference on Computational Linguistics, pages 1229–1241, Barcelona, Spain (Online). International Committee on Computational Linguistics, 2020.
Download

Theses

Course Projects

Undergraduate Research