Explanipedia

Natural Gradient Variational Bayes Without Fisher Matrix Analytic Calculation and Its Inversion Open

Antoine Godichon‐Baggioni, Dao Nguyen, M.-N. Tran · 2024

This paper introduces a method for efficiently approximating the inverse of the Fisher information matrix, a crucial step in achieving effective variational Bayes inference. A notable aspect of our approach is the avoidance of analytically…

Natural Gradient Variational Bayes without Fisher Matrix Analytic Calculation and Its Inversion Open

Antoine Godichon‐Baggioni, Dao Nguyen, Mai Duc Tran · 2023

This paper introduces a method for efficiently approximating the inverse of the Fisher information matrix, a crucial step in achieving effective variational Bayes inference. A notable aspect of our approach is the avoidance of analytically…

Accelerated Iterated Filtering Open

Dao Nguyen · 2023

Simulation-based inferences have attracted much attention in recent years, as the direct computation of the likelihood function in many real-world problems is difficult or even impossible. Iterated filtering (Ionides, Bretó, and King 2006;…

Non-convex weakly smooth Langevin Monte Carlo using regularization Open

Dao Nguyen, Xin Dang, Yi-Xin Chen · 2021

Discretization of continuous-time diffusion processes is a widely recognized method for sampling. However, the canonical Euler Maruyama discretization of the Langevin diffusion process, referred as Langevin Monte Carlo (LMC), studied mostl…

Unadjusted Langevin algorithm for non-convex weakly smooth potentials Open

Dao Nguyen, Xin Dang, Yixin Chen · 2021

Discretization of continuous-time diffusion processes is a widely recognized method for sampling. However, the canonical Euler Maruyama discretization of the Langevin diffusion process, referred as Unadjusted Langevin Algorithm (ULA), stud…

Sequential Monte Carlo Methods in the nimble and nimbleSMC R Packages Open

Nicholas Michaud, Perry de Valpine, Daniel Turek, Christopher J. Paciorek, Dao Nguyen · 2021

nimble is an R package for constructing algorithms and conducting inference on hierarchical models. The nimble package provides a unique combination of flexible model specification and the ability to program model-generic algorithms. Speci…

Black-box sampling for weakly smooth Langevin Monte Carlo using p-generalized Gaussian smoothing Open

Anh Duc Doan, Xin Dang, Dao Nguyen · 2020

Discretization of continuous-time diffusion processes is a widely recognized method for sampling. However, the canonical Euler-Maruyama discretization of the Langevin diffusion process, also named as Langevin Monte Carlo (LMC), studied mos…

Weakly smooth Langevin Monte Carlo using p-generalized Gaussian smoothing Open

Anh Duc Doan, Xin Dang, Dao Nguyen · 2020

Estimating Feature-Label Dependence Using Gini Distance Statistics Open

Silu Zhang, Xin Dang, Dao Nguyen, Dawn Wilkins, Yixin Chen · 2019

Identifying statistical dependence between the features and the label is a fundamental problem in supervised learning. This paper presents a framework for estimating dependence between numerical features and a categorical label using gener…

Nested Adaptation of MCMC Algorithms Open

Dao Nguyen, Perry de Valpine, Yves F. Atchadé, Daniel Turek, Nicholas Michaud , et al. · 2019

Markov chain Monte Carlo (MCMC) methods are ubiquitous tools for simulation-based inference in many fields but designing and identifying good MCMC samplers is still an open question. This paper introduces a novel MCMC algorithm, namely, Ne…

Simulation-based inference methods for partially observed Markov model via the R package is2 Open

Duc Anh Doan, Dao Nguyen, Xin Dang · 2018

Partially observed Markov process (POMP) models are powerful tools for time series modeling and analysis. Inherited the flexible framework of R package pomp, the is2 package extends some useful Monte Carlo statistical methodologies to impr…

A new Gini correlation between quantitative and qualitative variables Open

Xin Dang, Dao Nguyen, Yixin Chen, Junying Zhang · 2018

We propose a new Gini correlation to measure dependence between a categorical and numerical variables. Analogous to Pearson $R^2$ in ANOVA model, the Gini correlation is interpreted as the ratio of the between-group variation and the total…

Automatic adaptation of MCMC algorithms Open

Dao Nguyen, Perry de Valpine, Yves F. Atchadé, Daniel Turek, Nicholas Michaud , et al. · 2018

Markov chain Monte Carlo (MCMC) methods are ubiquitous tools for simulation-based inference in many fields but designing and identifying good MCMC samplers is still an open question. This paper introduces a novel MCMC algorithm, namely, Au…

Accelerate iterated filtering Open

Dao Nguyen · 2018

In simulation-based inferences for partially observed Markov process models (POMP), the by-product of the Monte Carlo filtering is an approximation of the log likelihood function. Recently, iterated filtering [14, 13] has originally been i…

Sequential Monte Carlo Methods in the nimble R Package Open

Nicholas Michaud, Perry de Valpine, Daniel Turek, Christopher J. Paciorek, Dao Nguyen · 2017

nimble is an R package for constructing algorithms and conducting inference on hierarchical models. The nimble package provides a unique combination of flexible model specification and the ability to program model-generic algorithms. Speci…

Iterated Filtering and Smoothing with Application to Infectious Disease Models. Open

Dao Nguyen · 2016

Partially observed Markov process (POMP) models are ubiquitous tools for modeling time series data in many fields including statistics, econometrics, ecology, and engineering. Because of incomplete measurements, and possibly weakly identif…

Inference for dynamic and latent variable models via iterated, perturbed Bayes maps Open

Edward L. Ionides, Dao Nguyen, Yves F. Atchadé, Stilian Stoev, Aaron A. King · 2015

Significance Many scientific challenges involve the study of stochastic dynamic systems for which only noisy or incomplete measurements are available. Inference for partially observed Markov process models provides a framework for formulat…

Dao Nguyen YOU? Author Swipe