Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
Same Flow, Different Paths: Variance Reduction in Flow Matching
Alexander Tyurin
In flow matching (FM), a velocity model is trained using a predefined path that connects data and noise samples (e.g., ). In this w…
cs.LG2026
Global Convergence of Gradient Descent for Score Matching in Gaussian Mixtures via Reverse Fisher Divergence
Alexander Tyurin
The score matching problem is a central training objective in modern generative modeling, diffusion models, fitting unnormalized statistical models, and inverse problems. A standar…
cs.LG2024
From Logistic Regression to the Perceptron Algorithm: Exploring Gradient Descent with Large Step Sizes
Alexander Tyurin
We focus on the classification problem with a separable dataset, one of the most important and classical problems from machine learning. The standard approach to this task is logis…