TrungTin Nguyen
I am currently a Postdoctoral Research Fellow at the The University of Queensland in the School of Mathematics and Physics from December 2023.
19
Documents
Affiliations actuelles
- 1144128
Présentation
You can find:
\- my webpage: <https://trung-tinnguyen.github.io/>
\- my CV: [https://trung-tinnguyen.github.io/files/CV\_TrungTin\_Nguyen.pdf](https://trung-tinnguyen.github.io/files/CV_TrungTin_Nguyen.pdf)
Publications
Towards Convergence Rates for Parameter Estimation in Gaussian-gated Mixture of ExpertsAISTATS 2024 - 27th International Conference on Artificial Intelligence and Statistics, May 2024, Valencia, Spain. pp.1-31
Communication dans un congrès
hal-04125056v1
|
|
Demystifying Softmax Gating Function in Gaussian Mixture of ExpertsAdvances in Neural Information Processing Systems, NeurIPS 2023 Spotlight, Acceptance rate 3.6% over 12343 submissions, Dec 2023, New Orleans, United States. pp.1-27
Communication dans un congrès
hal-04125060v1
|
|
|
HyperRouter: Towards Efficient Training and Inference of Sparse Mixture of ExpertsThe 2023 Conference on Empirical Methods in Natural Language Processing, EMNLP 2023 Main, Dec 2023, 2023 - Resorts World Convention Centre, Singapore. pp.1-12
Communication dans un congrès
hal-04257067v2
|
|
A non-asymptotic risk bound for model selection in a high-dimensional mixture of experts via joint rank and variable selectionAJCAI 2023 - Australasian Joint Conference on Artificial Intelligence, Nov 2023, Brisbane, Australia. pp.1-32
Communication dans un congrès
hal-03984011v3
|
|
Mixture of expert posterior surrogates for approximate Bayesian computationSFdS 2022 - 53èmes Journées de Statistique de la Société Française de Statistique, Jun 2022, Lyon, France. pp.1-6
Communication dans un congrès
hal-03679688v1
|
Bayesian nonparametric mixture of experts for high-dimensional inverse problemsBNP13 - 13th International Conference on Bayesian Nonparametrics, Oct 2022, Puerto Varas, Chile
Communication dans un congrès
hal-04001270v1
|
|
|
Model selection by penalization in mixture of experts models with a non-asymptotic approachJDS 2022 - 53èmes Journées de Statistique de la Société Française de Statistique (SFdS), Jun 2022, Lyon, France. pp.1-6
Communication dans un congrès
hal-03663348v1
|
Approximate Bayesian computation with surrogate posteriorsISBA 2021 - World Meeting of the International Society for Bayesian Analysis, Jun 2021, Marseille, France
Communication dans un congrès
hal-03337949v1
|
|
Bayesian Likelihood Free Inference using Mixtures of Experts2024
Pré-publication, Document de travail
hal-04436187v1
|
A General Theory for Softmax Gating Multinomial Logistic Mixture of Experts2023
Pré-publication, Document de travail
hal-04256824v1
|
|
|
Concentration results for approximate Bayesian computation without identifiability2023
Pré-publication, Document de travail
hal-03987197v1
|
|
Bayesian nonparametric mixture of experts for high-dimensional inverse problems2023
Pré-publication, Document de travail
hal-04015203v2
|
A non-asymptotic model selection in block-diagonal mixture of polynomial experts models2021
Pré-publication, Document de travail
hal-03214604v1
|
|
Non-asymptotic oracle inequalities for the Lasso in high-dimensional mixture of experts2020
Pré-publication, Document de travail
hal-02957892v1
|