6 citations · 8 across the 10 of their papers we have counts for
10 papers
Mean Square Error Analysis of Stochastic Runge-Kutta Integrators
Xuda Ye
We analyze the mean square error of stochastic Runge-Kutta integrators for overdamped Langevin dynamics whose potential is strongly convex outside a bounded region. A decomposition…
Mode Coverage in Normalizing Flow Boltzmann Generators via Log-Ratio Variation
Qi Feng, Rongjie Lai, Di Qi +1
Normalizing flow Boltzmann generators retain a tractable pushforward density, but training with forward KL depends on target samples that may be biased or omit modes. As a result,…
Jeffreys Flow: Robust Boltzmann Generators for Rare Event Sampling via Parallel Tempering Distillation
Guang Lin, Christian Moya, Di Qi +1
Sampling physical systems with rough energy landscapes is hindered by rare events and metastable trapping. While Boltzmann generators already offer a solution, their reliance on th…
Mean square error analysis of stochastic gradient and variance-reduced sampling algorithms
Jianfeng Lu, Xuda Ye, Zhennan Zhou
This paper considers mean square error (MSE) analysis for stochastic gradient sampling algorithms applied to underdamped Langevin dynamics under a global convexity assumption. A no…
Statistical Error of Numerical Integrators for Underdamped Langevin Dynamics with Deterministic And Stochastic Gradients
Xuda Ye, Zhennan Zhou
We propose a novel discrete Poisson equation approach to estimate the statistical error of a broad class of numerical integrators for the underdamped Langevin dynamics. The statist…
Optimal Convergence Rate of Lie-Trotter Approximation for Quantum Thermal Averages
Xuda Ye, Zhennan Zhou
The Lie--Trotter product formula is a foundational approximation for the quantum partition function, yet obtaining rigorous error bounds for the unbounded Hamiltonians common in ph…
Dimension-free Ergodicity of Path Integral Molecular Dynamics
Xuda Ye, Zhennan Zhou
The quantum thermal average plays a central role in describing the thermodynamic properties of a quantum system. Path integral molecular dynamics (PIMD) is a prevailing approach fo…
Error Analysis of Time-Discrete Random Batch Method for Interacting Particle Systems and Associated Mean-Field Limits
Xuda Ye, Zhennan Zhou
The random batch method provides an efficient algorithm for computing statistical properties of a canonical ensemble of interacting particles. In this work, we study the error esti…
Ergodicity and long-time behavior of the Random Batch Method for interacting particle systems
Shi Jin, Lei Li, Xuda Ye +1
We study the geometric ergodicity and the long time behavior of the Random Batch Method for interacting particle systems, which exhibits superior numerical performance in recent la…
Efficient Sampling of Thermal Averages of Interacting Quantum Particle Systems with Random Batches
Xuda Ye, Zhennan Zhou
An efficient sampling method, the pmmLang+RBM, is proposed to compute the quantum thermal average in the interacting quantum particle system. Benefiting from the random batch metho…