Sitemap
A list of all the posts and pages found on the site. For you robots out there, there is an XML version available for digesting as well.
Pages
Posts
publications
Dual Representations of Words with Asymmetric Contexts
Undergraduate Summer Research Report, 2019
Quantifier Scope Disambiguation
Undergraduate Summer Research Report, 2020
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
A Brief Survey of Semi-Supervised Learning and Its Application in Natural Language Processing
COMP 599 - Statistical Learning Theory (taught by Profs. Adam Oberman and Prakash Panangaden) at McGill University, 2020
Analyzing Random Features via Linearization and the Matrix Dyson Equation
MATH 598 - Random Matrix Theory (taught by Prof. Elliot Paquette) at McGill University, 2022
Contrastive Learning as Kernel Approximation
MSc Thesis, 2023
Recommended citation: Konstantinos Christopher Tsiolis. Contrastive Learning as Kernel Approximation. McGill University (Canada), 2023.
Download
Explaining and Forecasting Homelessness in the United States
STA2201 - Methods of Applied Statistics II (taught by Prof. Monica Alexander) at the University of Toronto, 2024
From Information to Generative Exponent: Learning Rate Induces Phase Transitions in SGD
39th International Conference on Neural Information Processing Systems (NeurIPS), 2025
Recommended citation: Konstantinos Christopher Tsiolis, Alireza Mousavi-Hosseini, and Murat A. Erdogdu. From Information to Generative Exponent: Learning Rate Induces Phase Transitions in SGD. In Advances in Neural Information Processing Systems, 2025.
Download
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