3 papers
math.PR2020
An Almost Constant Lower Bound of the Isoperimetric Coefficient in the KLS Conjecture
Yuansi Chen
We prove an almost constant lower bound of the isoperimetric coefficient in the KLS conjecture. The lower bound has the dimension dependency . When the dimension is la…
stat.ML2019
Fast mixing of Metropolized Hamiltonian Monte Carlo: Benefits of multi-step gradients
Yuansi Chen, Raaz Dwivedi, Martin J. Wainwright +1
Hamiltonian Monte Carlo (HMC) is a state-of-the-art Markov chain Monte Carlo sampling algorithm for drawing samples from smooth probability densities over continuous spaces. We stu…
stat.ML2018
Stability and Convergence Trade-off of Iterative Optimization Algorithms
Yuansi Chen, Chi Jin, Bin Yu
The overall performance or expected excess risk of an iterative machine learning algorithm can be decomposed into training error and generalization error. While the former is contr…