About

Welcome to my homepage! My full name is Quang Dung Le (in Vietnamese: Lê Quang Dũng, in Chinese: 黎光勇) and I am a third-year PhD Student at the Department of Statistics and Data Science. I am currently doing research under the guidance of Professor Nhat Ho and Professor Alessandro Rinaldo. Before that, I completed my Diplôme d’Ingénieur (Master level) at École polytechnique, and I graduated from the Department of Mathematics, Mechanics, and Informatics, VNU University of Science.

Outside of research, I enjoy working out, reading, and learning foreign languages, and listening to European pop, chanson, and rock music, especially classic Italian pop.

Email: quangdung0110@utexas.edu

Research Interests

My research interests lie in theoretical statistics and machine learning, particularly finite mixture models and mixture-of-experts architectures. I study identifiability, overspecification, minimax theory, and parameter convergence rates, with the goal of developing rigorous statistical tools for understanding modern AI models. I am also broadly interested in optimal transport, generative models, and stochastic processes.

Recent News

  • [Jan 2026] Our paper [1] on Optimal Transport and Optimization is accepted to AISTATS 2026.

  • [Sep 2025] Our paper [1] on Mixture of Expert is accepted to Potential Analysis.

(*) denotes equal contribution.

Publications on the Theory of Mixture of Experts

[T7] Partial Differential Equation Barriers to Identifiability in Infinite Mixture Models. Under Review.
*Dung Le*, Nicola Bariletto*, Alessandro Rinaldo, Nhat Ho.

[T6] On the Geometry of Separation in Finite Gaussian Mixtures. Under Review.
Huy Nguyen*, Dung Le*, Alessandro Rinaldo, Nhat Ho.

[T5] Convergence Rates for Latent Mixing Measures in Infinite Homoscedastic Location-Scale Mixture Models. Under Review.
Nicola Bariletto*, Dung Le*, Alessandro Rinaldo, Nhat Ho.

[T4] Improving Minimax Estimation Rates for Contaminated Mixture of Multinomial Logistic Experts via Expert Heterogeneity. Under Review.
Fanqi Yan*, Dung Le*, Trang Pham, Huy Nguyen, Nhat Ho.

[T3] Hypernetwork-Driven Low-Rank Adaptation Across Attention Heads. Under Review.
Nghiem T. Diep, Dung Le*, Tuan Truong, Tan Dinh, Huy Nguyen, Nhat Ho.

[T2] On Minimax Estimation of Parameters in Softmax-Contaminated Mixture of Experts. NeurIPS 2025.
Fanqi Yan*, Huy Nguyen*, Dung Le*, Pedram Akbarian, Nhat Ho, Alessandro Rinaldo.

[T1] Understanding Expert Structures on Minimax Parameter Estimation in Contaminated Mixture of Experts. AISTATS 2025.
Fanqi Yan*, Huy Nguyen*, Le Quang Dung*, Pedram Akbarian, Nhat Ho.

Publications on the Probability Theory and Stochastic Analysis

[P3] Berry-Esseen bounds for multivariate martingale difference sequences in the Kolmogorov distance. Under Review.
Weichen Wu, Le Quang Dung*, Arun Kumar Kuchibhotla*, Alessandro Rinaldo*.

[P2] Strong laws of large numbers for weighted sums of 𝑑-dimensional arrays of random variables and applications to marked point processes. Theory of Probability and Mathematical Statistics, 2024.
Ta Cong Son, Tran Manh Cuong, Le Quang Dung, Le Van Dung.
[P1] Rate of Convergence in the Smoluchowski-Kramers Approximation for Mean-field Stochastic Differential Equations. *Potential Analysis, 2023.

Ta Cong Son*, Dung Quang Le*, Manh Hong Duong.*

Publications on the Optimal Transport and Optimization

[O3] On Barycenter Computation: Analyzing Semi-Unbalanced Optimal Transport-based Method on Bures-Wasserstein manifold. AISTATS 2026
. Ngoc-Hai Nguyen*, Dung Le* Hoang-Phi Nguyen, Tung Pham, Nhat Ho.

[O2] Fast approximation of the generalized sliced-Wasserstein distance. ICASSP 2024.
Dung Le, Huy Nguyen*, Khai Nguyen*, Trang Nguyen, Nhat Ho.

[O1] Entropic Gromov-Wasserstein between Gaussian Distributions. ICML 2022.
Huy Nguyen*, Khang Le*, *Dung Le*, Dat Do, Tung Pham, Nhat Ho.