30 citations · 59 across the 20 of their papers we have counts for
25 papers
Hamiltonian Monte Carlo on ReLU Neural Networks is Inefficient
Vu C. Dinh, Lam Si Tung Ho, Cuong V. Nguyen
We analyze the error rates of the Hamiltonian Monte Carlo algorithm with leapfrog integrator for Bayesian neural network inference. We show that due to the non-differentiability of…
Simple Transferability Estimation for Regression Tasks
Cuong N. Nguyen, Phong Tran, Lam Si Tung Ho +4
We consider transferability estimation, the problem of estimating how well deep learning models transfer from a source to a target task. We focus on regression tasks, which receive…
Generalization Bounds for Deep Transfer Learning Using Majority Predictor Accuracy
Cuong N. Nguyen, Lam Si Tung Ho, Vu Dinh +2
We analyze new generalization bounds for deep learning models trained by transfer learning from a source to a target task. Our bounds utilize a quantity called the majority predict…
When can we reconstruct the ancestral state? Beyond Brownian motion
Nhat L. Vu, Thanh P. Nguyen, Binh T. Nguyen +2
Reconstructing the ancestral state of a group of species helps answer many important questions in evolutionary biology. Therefore, it is crucial to understand when we can estimate…
Posterior concentration and fast convergence rates for generalized Bayesian learning
Lam Si Tung Ho, Binh T. Nguyen, Vu Dinh +1
In this paper, we study the learning rate of generalized Bayes estimators in a general setting where the hypothesis class can be uncountable and have an irregular shape, the loss f…
When can we reconstruct the ancestral state? A unified theory
Lam Si Tung Ho, Vu Dinh
Ancestral state reconstruction is one of the most important tasks in evolutionary biology. Conditions under which we can reliably reconstruct the ancestral state have been studied…
Searching for Minimal Optimal Neural Networks
Lam Si Tung Ho, Vu Dinh
Large neural network models have high predictive power but may suffer from overfitting if the training set is not large enough. Therefore, it is desirable to select an appropriate…
OASIS: An Active Framework for Set Inversion
Binh T. Nguyen, Duy M. Nguyen, Lam Si Tung Ho +1
In this work, we introduce a novel method for solving the set inversion problem by formulating it as a binary classification problem. Aiming to develop a fast algorithm that can wo…
Convergence of maximum likelihood supertree reconstruction
Lam Si Tung Ho, Vu Dinh
Supertree methods are tree reconstruction techniques that combine several smaller gene trees (possibly on different sets of species) to build a larger species tree. The question of…
Convergence of Griddy Gibbs Sampling and other perturbed Markov chains
Vu Dinh, Ann E. Rundell, Gregery T. Buzzard
The Griddy Gibbs sampling was proposed by Ritter and Tanner (1992) as a computationally efficient approximation of the well-known Gibbs sampling method. The algorithm is simple and…
Consistent Feature Selection for Analytic Deep Neural Networks
Vu Dinh, Lam Si Tung Ho
One of the most important steps toward interpretability and explainability of neural network models is feature selection, which aims to identify the subset of relevant features. Th…
Consistent feature selection for neural networks via Adaptive Group Lasso
Vu Dinh, Lam Si Tung Ho
One main obstacle for the wide use of deep learning in medical and engineering sciences is its interpretability. While neural network models are strong tools for making predictions…
Bayesian Active Learning With Abstention Feedbacks
Cuong V. Nguyen, Lam Si Tung Ho, Huan Xu +2
We study pool-based active learning with abstention feedbacks where a labeler can abstain from labeling a queried example with some unknown abstention rate. This is an important pr…
On the convergence of the maximum likelihood estimator for the transition rate under a 2-state symmetric model
Lam Si Tung Ho, Vu Dinh, Frederick A. Matsen +1
Maximum likelihood estimators are used extensively to estimate unknown parameters of stochastic trait evolution models on phylogenetic trees. Although the MLE has been proven to co…
Non-bifurcating phylogenetic tree inference via the adaptive LASSO
Cheng Zhang, Vu Dinh, Frederick A. Matsen
Phylogenetic tree inference using deep DNA sequencing is reshaping our understanding of rapidly evolving systems, such as the within-host battle between viruses and the immune syst…
A surrogate function for one-dimensional phylogenetic likelihoods
Brian C. Claywell, Vu C. Dinh, Connor O. McCoy +1
Phylogenetics has seen an steady increase in substitution model complexity, which requires increasing amounts of computational power to compute likelihoods. This model complexity m…
Bayesian Pool-based Active Learning With Abstention Feedbacks
Cuong V. Nguyen, Lam Si Tung Ho, Huan Xu +2
We study pool-based active learning with abstention feedbacks, where a labeler can abstain from labeling a queried example with some unknown abstention rate. This is an important p…
Probabilistic Path Hamiltonian Monte Carlo
Vu Dinh, Arman Bilge, Cheng Zhang +1
Hamiltonian Monte Carlo (HMC) is an efficient and effective means of sampling posterior distributions on Euclidean space, which has been extended to manifolds with boundary. Howeve…
Online Bayesian phylogenetic inference: theoretical foundations via Sequential Monte Carlo
Vu Dinh, Aaron E. Darling, Frederick A. Matsen
Phylogenetics, the inference of evolutionary trees from molecular sequence data such as DNA, is an enterprise that yields valuable evolutionary understanding of many biological sys…
Fast learning rates with heavy-tailed losses
Vu Dinh, Lam Si Tung Ho, Duy Nguyen +1
We study fast learning rates when the losses are not necessarily bounded and may have a distribution with heavy tails. To enable such analyses, we introduce two new conditions: (i)…
Consistency and convergence rate of phylogenetic inference via regularization
Vu Dinh, Lam Si Tung Ho, Marc A. Suchard +1
It is common in phylogenetics to have some, perhaps partial, information about the overall evolutionary tree of a group of organisms and wish to find an evolutionary tree of a spec…
The shape of the one-dimensional phylogenetic likelihood function
Vu Dinh, Frederick A. Matsen
By fixing all parameters in a phylogenetic likelihood model except for one branch length, one obtains a one-dimensional likelihood function. In this work, we introduce a mathematic…
Learning From Non-iid Data: Fast Rates for the One-vs-All Multiclass Plug-in Classifiers
Vu Dinh, Lam Si Tung Ho, Nguyen Viet Cuong +2
We prove new fast learning rates for the one-vs-all multiclass plug-in classifiers trained either from exponentially strongly mixing data or from data generated by a converging dri…
Generalization and Robustness of Batched Weighted Average Algorithm with V-geometrically Ergodic Markov Data
Nguyen Viet Cuong, Lam Si Tung Ho, Vu Dinh
We analyze the generalization and robustness of the batched weighted average algorithm for V-geometrically ergodic Markov data. This algorithm is a good alternative to the empirica…