online learning 1ordinary differential equations 1rough signals 1signature kernels 1single trajectory forcing 1
From the 1 of 3 linked papers with an AI index.
3 papers
math.NA2026
Branched Signature Kernel Solvers for ODEs with rough Single-Trajectory signals
Munawar Ali, Qi Feng, Charlie Pyle +1
The paper introduces a branched signature kernel method for solving linear and nonlinear ODEs driven by a single, possibly rough, forcing trajectory, using a count‑sampling scheme…
cs.LG2025
Non-Reversible Langevin Algorithms for Constrained Sampling
Hengrong Du, Qi Feng, Changwei Tu +2
We consider the constrained sampling problem where the goal is to sample from a target distribution on a constrained domain. We propose skew-reflected non-reversible Langevin dynam…
cs.LG2024
Constrained Exploration via Reflected Replica Exchange Stochastic Gradient Langevin Dynamics
Haoyang Zheng, Hengrong Du, Qi Feng +2
Replica exchange stochastic gradient Langevin dynamics (reSGLD) is an effective sampler for non-convex learning in large-scale datasets. However, the simulation may encounter stagn…