Vincent Counathe - Ph.D. Statistics and Machine Learning Cornell University

Vincent Counathe I am a Ph.D. student at Cornell University, where I work with Prof. Chris De Sa on efficient generative modeling, with a focus on discrete diffusion and quantization for language models. I am supported by a Cornell University Fellowship. Before Cornell, I completed my Master's in Statistics and Machine Learning at Université Paris-Saclay (Institut de Mathématiques d'Orsay), where I worked on high-dimensional statistics and machine learning with Florent Krzakala, Lenka Zdeborová, and Christophe Giraud. Email / CV / GitHub
Research
Low-Degree Hardness in Feature-Augmented Stochastic Block Models Vincent Counathe, Ludovic Stephan, Florent Krzakala, Lenka Zdeborová Unified framework for feature-augmented SBMs; statistical and computational thresholds for community detection.
Statistical Risk Bounds for Genealogical Reconstruction on Random Recursive Trees Vincent Counathe [Link] Non-asymptotic risk bounds for a Jordan-ordering estimator in genealogical inference.
Other
Localization Schemes for Mixing Bounds in Markov Chains (Chen & Eldan framework) Vincent Counathe, Matthieu Dagès Expository report on mixing times and spectral gaps of Markov chains, with applications in high-dimensional sampling. [Link]
Community Detection in Random Graphs Vincent Counathe, Matthieu Dagès Expository note based on Vershynin's work on spectral methods for community detection using perturbation theory and concentration inequalities. [Link]

Template from here.

Research