13 citations · 29 across the 17 of their papers we have counts for
4 papers · 1 filter
Variable-Complexity Weighted-Tempered Gibbs Samplers for Bayesian Variable Selection
Lan V. Truong
Subset weighted-Tempered Gibbs Sampler (wTGS) has been recently introduced by Jankowiak to reduce the computation complexity per MCMC iteration in high-dimensional applications whe…
Global Convergence Rate of Deep Equilibrium Models with General Activations
Lan V. Truong
In a recent paper, Ling et al. investigated the over-parametrized Deep Equilibrium Model (DEQ) with ReLU activation. They proved that the gradient descent converges to a globally o…
On Rademacher Complexity-based Generalization Bounds for Deep Learning
Lan V. Truong
We show that the Rademacher complexity-based framework can establish non-vacuous generalization bounds for Convolutional Neural Networks (CNNs) in the context of classifying a smal…
Generalization Error Bounds on Deep Learning with Markov Datasets
Lan V. Truong
In this paper, we derive upper bounds on generalization errors for deep neural networks with Markov datasets. These bounds are developed based on Koltchinskii and Panchenko's appro…