6 papers
BridgeTwist: Twisting Schrödinger Bridges for Training-Free Conditional Sampling
Mengyu Li, Qianqian Qu, Jun S. Liu
Generative models are often required to serve many downstream conditional tasks. In the training-free setting, a pretrained unconditional model is reused as a prior and combined wi…
TFTF: Training-Free Targeted Flow for Conditional Sampling
Qianqian Qu, Jun S. Liu
We propose a training-free conditional sampling method for flow matching models based on importance sampling. Because a naïve application of importance sampling suffers from weight…
Factor Analysis of Multivariate Stochastic Volatility Model
Taehee Lee, Jun S. Liu
Modeling the time-varying covariance structures of high-dimensional variables is critical across diverse scientific and industrial applications; however, existing approaches exhibi…
Tuning free Catoni type joint robust estimation
Xiang Li, Jun S. Liu, Qiang Sun +1
This paper develops a Catoni-type joint (tuning-free) estimation framework for parametric models with heavy-tailed noise, in which the target parameter and the unknown noise varian…
Towards a Statistical Understanding of Neural Networks: Beyond the Neural Tangent Kernel Theories
Yicheng Li, Haobo Zhang, Jianfa Lai +2
A primary advantage of neural networks lies in their feature learning characteristics, which is challenging to theoretically analyze due to the complexity of their training dynamic…
A Variational Spike-and-Slab Approach for Group Variable Selection
Buyu Lin, Changhao Ge, Jun S. Liu
We introduce a class of generic spike-and-slab priors for high-dimensional linear regression with grouped variables and present a Coordinate-ascent Variational Inference (CAVI) alg…