Statistical Learning
Double Randomized Underdamped Langevin with Dimension-Independent Convergence Guarantee Y uanshi Liu, Cong Fang, Tong Zhang School of Intelligence Science and Technology, Peking University
Sampling from a high-dimensional distribution serves as one of the key components in statistics, machine learning, and scientific computing, and constitutes the foundation of the fields including Bayesian statistics and generative models [Liu and Liu, 2001, Brooks et al., 2011, Song et al.,
Tight Risk Bounds for Gradient Descent on Separable Data
Recently, there has been a marked increase in interest regarding the generalization capabilities of unregularized gradient-based learning methods.
Tight Risk Bounds for Gradient Descent on Separable Data
Recently, there has been a marked increase in interest regarding the generalization capabilities of unregularized gradient-based learning methods.
Diffusion-Reward Adversarial Imitation Learning
Despite its encouraging results, GAIL training is often brittle and unstable.
