3 papers
cs.DS2026
A General Framework for Metropolis-Adjusted Dikin Walks: Dimension-Square Mixing on Polytopes and Log-Det Walks on Spectrahedra
Zhao Song, Lichen Zhang
We analyze exact-metric, Metropolis-adjusted Dikin walks by keeping the proposal determinant and reverse quadratic form together. Their leading uncentered terms cancel in the compl…
cs.DS2024
Log-concave Sampling from a Convex Body with a Barrier: a Robust and Unified Dikin Walk
Yuzhou Gu, Nikki Lijing Kuang, Yi-An Ma +2
We consider the problem of sampling from a -dimensional log-concave distribution for -Lipschitz , constrained to a convex body with an efficient…
stat.ML2024
Binary Hypothesis Testing for Softmax Models and Leverage Score Models
Yuzhou Gu, Zhao Song, Junze Yin
Softmax distributions are widely used in machine learning, including Large Language Models (LLMs), where the attention unit uses softmax distributions. We abstract the attention un…