About Me
I am currently a research scientist in machine learning at Huawei Paris research center.
Previously, I was a PhD student at EURECOM and Sorbonne University, under the supervision of Prof. Maurizio Filippone.
My research interests span from the intersections of probabilistic modeling and deep learning to extremely efficient AI models.
My ambitious goal is to develop models that are more interpretable, scalable, and efficient in terms of both data and energy. I have been exploring improved priors, more efficient inference techniques for deep probabilistic models, and innovative paradigms for extremely efficient deep learning through binarization and quantization.
Contact: ba (dot) hien (dot) tran (at) huawei (dot) com ; bahientranvn (at) gmail (dot) com .
Latest News
June 19, 2024 Austria (Vienna)
Our paper ‘Boolean Logic for Low-Energy Deep Learning’ has been accepted at ICML Workshop on Advancing Neural Network Training: Computational Efficiency, Scalability, and Resource Optimization 2024!
June 03, 2024
Check out our new paper: ‘Robust Classification by Coupling Data Mollification with Label Smoothing’!
May 25, 2024
Check out our new paper: ‘BOLD: Boolean Logic Deep Learning’!
April 11, 2024
Our paper ‘Spatial Bayesian Neural Networks’ has been accepted in the Spatial Statistics journal!
December 22, 2023
I have joined Huawei Paris research center as a research scientist in machine learning
December 06, 2023
I have received the 1st prize of ‘Prix de thèse de l’EDITE 2023’ (Best PhD thesis award) from Sorbonne University!
October 13, 2023
I have defended successfully my PhD thesis! The members of the jury include Chris Oates, Mark van der Wilk, Marco Lorenzi, Serena Villata, Pietro Michiardi, and Maurizio Filippone.
September 21, 2023 U.S. (New Orleans)
Our paper ‘One-Line-of-Code Data Mollification Improves Optimization of Likelihood-based Generative Models’ has been accepted at NeurIPS 2023!
September 20, 2023 Denmark (Copenhagen)
I will be attending and presenting a poster at the workshop ‘Generative models and uncertainty quantification’, GenU 2023.
June 20, 2023 U.S. (Hawaii)
Our paper ‘Improving Training of Likelihood-based Generative Models with Gaussian Homotopy’ has been accepted at ICML Workshop on Structured Probabilistic Inference and Generative Modeling 2023!
May 31, 2023
Check out our new paper: ‘One-Line-of-Code Data Mollification Improves Optimization of Likelihood-based Generative Models’!
April 24, 2023 U.S. (Hawaii)
Our paper ‘Fully Bayesian Autoencoders with Latent Sparse Gaussian Processes’ has been accepted at ICML 2023!
February 09, 2023
Check out our new paper: ‘Fully Bayesian Autoencoders with Latent Sparse Gaussian Processes’!
November 30, 2022 U.S. (New Orleans)
I will be attending the NeurIPS conference and presenting our JMLR paper.
October 01, 2022 U.S. (California, Irvine)
I’m visiting the groups of Professors Stephan Mandt and Babak Shahbaba at UCI for three months.
May 09, 2022 US (California)
I’ve had a California trip during April 26th ~ May 8th to visit and give talks at Ermon’s lab (Stanford) and Mandt’s lab (UCI).
April 01, 2022 U.S. (Washington, DC)
Accepted for a contributed talk at Joint Statistical Meetings (JSM) 2022 on ‘Functional Priors for Bayesian Deep Learning’.
March 25, 2022
Our paper ‘All You Need is a Good Functional Prior for Bayesian Deep Learning’ has been accepted by JMLR!
March 24, 2022 Canada (Montreal)
Received an ISBA Travel Award for Young Researchers.
March 21, 2022 Germany (online)
Invited talk at the SIAM Conference on Imaging Science (IS22), organized by Society for Industrial and Applied Mathematics.
March 01, 2022 Canada (Montreal)
Accepted for a contributed talk at ISBA 2022 World Meeting on ‘Functional Priors for Bayesian Deep Learning’.
September 28, 2021 Australia (online)
Our paper ‘Model Selection for Bayesian Autoencoders’ has been accepted at NeurIPS 2021!
September 01, 2021
Invited to serve as a reviewer for AISTATS.
June 11, 2021
Check out our new paper: ‘Model Selection for Bayesian Autoencoders’!
February 17, 2021 UK (online)
Invited talk at the Data Centric Engineering group, Alan Turing Institute, UK (virtual): ‘Functional priors for Bayesian neural networks’.
January 12, 2021
The paper ‘Functional Priors for Bayesian Neural Networks through Wasserstein Distance Minimization to Gaussian Processes’ has been accepted at the 3rd Symposium on Advances in Approximate Bayesian Inference 2021!
November 26, 2020
Check out our new paper: ‘All You Need is a Good Functional Prior for Bayesian Deep Learning’!
September 14, 2020
I have defended successfully my master thesis at Telecom Paris and EURECOM.
September 01, 2020
I have joined EURECOM as a PhD student in Machine Learning.