From Information to Generative Exponent: Learning Rate Induces Phase Transitions in SGD
To appear in 39th International Conference on Neural Information Processing Systems (NeurIPS), 2025
Publications
You can also find my articles on my Google Scholar profile.
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. 2020. 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.
Download
Theses
Contrastive Learning as Kernel Approximation
MSc Thesis, 2023
Recommended citation: Konstantinos Christopher Tsiolis. 2023. Contrastive Learning as Kernel Approximation. McGill University (Canada).
Download
Course Projects
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
Analyzing Random Features via Linearization and the Matrix Dyson Equation
MATH 598 - Random Matrix Theory (taught by Prof. Elliot Paquette) at McGill University, 2022
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
Undergraduate Research
Quantifier Scope Disambiguation
Undergraduate Summer Research Report, 2020
Dual Representations of Words with Asymmetric Contexts
Undergraduate Summer Research Report, 2019