← Authors

nhật Hồ

86 papers · 2017–2025 · 8 conferences · across top CS/AI conferences

Achievements

🌍 Conference Polyglot (8) 🗺️ Taxonomy Completionist (23) 🐝 Cross-Pollinator (11) 🌈 Renaissance Researcher (9) 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🌉 Interdisciplinary Bridge 🏃 Academic Marathon (8) 🏠 Conference Loyalist (23) 👑 Triple Crown 🔬 Deep Specialist (21) 🤝 Dynamic Duo (27) 🏆 Keyword Champion (4) 🏆 Grand Slam 📈 Trend Setter ❓ The Questioner ⚡ Prolific Year (14) 🗃️ Keyword Collector (76) 💎 Century Club (86) 🔥 Unstoppable (9)

Conferences

ICML (25) NIPS (23) ICLR (14) AISTATS (13) JMLR (6) AAAI (2) ICCV (2) CVPR (1)

Top co-authors

Khai Nguyen (27) Huy Nguyen (20) Dinh Phung (10) Tung Pham (9) Hung Bui (8) Trung Le (8) Michael I. Jordan (7) Tan Minh Nguyen (7) Tianyi Lin (6) Pedram Akbarian (6)

Research topics

Statistics (3)

Keywords

optimal transport (19) convergence rate (10) probability measure (8) wasserstein distance (8) entropic regularization (7) sliced wasserstein distance (7) sinkhorn algorithm (6) mixture of expert (6) maximum likelihood estimation (6) parameter estimation (5) domain adaptation (5) computational complexity (5) gaussian mixture model (4) neural network (4) representation learning (4) transformer architecture (4) maximum likelihood (4) wasserstein barycenter (4) gradient flow (3) statistical learning (3)

Papers

On Zero-Initialized Attention: Optimal Prompt and Gating Factor Estimation ICML 2025
Attack on Prompt: Backdoor Attack in Prompt-Based Continual Learning AAAI 2025
Understanding Expert Structures on Minimax Parameter Estimation in Contaminated Mixture of Experts AISTATS 2025
Instability, Computational Efficiency and Statistical Accuracy JMLR 2025
Beyond Losses Reweighting: Empowering Multi-Task Learning via the Generalization Perspective ICCV 2025
Statistical Advantages of Perturbing Cosine Router in Mixture of Experts ICLR 2025
X-Drive: Cross-modality Consistent Multi-Sensor Data Synthesis for Driving Scenarios ICLR 2025
Towards Marginal Fairness Sliced Wasserstein Barycenter ICLR 2025
Revisiting Prefix-tuning: Statistical Benefits of Reparameterization among Prompts ICLR 2025
Improving Generalization with Flat Hilbert Bayesian Inference ICML 2025
RepLoRA: Reparameterizing Low-rank Adaptation via the Perspective of Mixture of Experts ICML 2025
Lightspeed Geometric Dataset Distance via Sliced Optimal Transport ICML 2025
A Bayesian Approach for Personalized Federated Learning in Heterogeneous Settings NIPS 2024
Hierarchical Hybrid Sliced Wasserstein: A Scalable Metric for Heterogeneous Joint Distributions NIPS 2024
Sigmoid Gating is More Sample Efficient than Softmax Gating in Mixture of Experts NIPS 2024
Mixture of Experts Meets Prompt-Based Continual Learning NIPS 2024
Sliced Wasserstein with Random-Path Projecting Directions ICML 2024
Is Temperature Sample Efficient for Softmax Gaussian Mixture of Experts? ICML 2024
Neural Collapse for Cross-entropy Class-Imbalanced Learning with Unconstrained ReLU Features Model ICML 2024
Improving Computational Complexity in Statistical Models with Local Curvature Information ICML 2024
Revisiting Deep Audio-Text Retrieval Through the Lens of Transportation ICLR 2024
Sliced Wasserstein Estimation with Control Variates ICLR 2024
On Parameter Estimation in Deviated Gaussian Mixture of Experts AISTATS 2024
Structure-Aware E(3)-Invariant Molecular Conformer Aggregation Networks ICML 2024
Towards Convergence Rates for Parameter Estimation in Gaussian-gated Mixture of Experts AISTATS 2024
Integrating Efficient Optimal Transport and Functional Maps For Unsupervised Shape Correspondence Learning CVPR 2024
Quasi-Monte Carlo for 3D Sliced Wasserstein ICLR 2024
Beyond Vanilla Variational Autoencoders: Detecting Posterior Collapse in Conditional and Hierarchical Variational Autoencoders ICLR 2024
Statistical Perspective of Top-K Sparse Softmax Gating Mixture of Experts ICLR 2024
Diffeomorphic Mesh Deformation via Efficient Optimal Transport for Cortical Surface Reconstruction ICLR 2024
On Least Square Estimation in Softmax Gating Mixture of Experts ICML 2024
A General Theory for Softmax Gating Multinomial Logistic Mixture of Experts ICML 2024
On the Computational and Statistical Complexity of Over-parameterized Matrix Sensing JMLR 2024
Bayesian Nonparametrics Meets Data-Driven Distributionally Robust Optimization NIPS 2024
FuseMoE: Mixture-of-Experts Transformers for Fleximodal Fusion NIPS 2024
Hierarchical Sliced Wasserstein Distance ICLR 2023
Demystifying Softmax Gating Function in Gaussian Mixture of Experts NIPS 2023
Energy-Based Sliced Wasserstein Distance NIPS 2023
LVM-Med: Learning Large-Scale Self-Supervised Vision Models for Medical Imaging via Second-order Graph Matching NIPS 2023
Minimax Optimal Rate for Parameter Estimation in Multivariate Deviated Models NIPS 2023
Markovian Sliced Wasserstein Distances: Beyond Independent Projections NIPS 2023
Designing Robust Transformers using Robust Kernel Density Estimation NIPS 2023
Joint Self-Supervised Image-Volume Representation Learning with Intra-inter Contrastive Clustering AAAI 2023
Global-Local Regularization Via Distributional Robustness AISTATS 2023
A Primal-Dual Framework for Transformers and Neural Networks ICLR 2023
Neural Collapse in Deep Linear Networks: From Balanced to Imbalanced Data ICML 2023
On Excess Mass Behavior in Gaussian Mixture Models with Orlicz-Wasserstein Distances ICML 2023
Revisiting Over-smoothing and Over-squashing Using Ollivier-Ricci Curvature ICML 2023
Self-Attention Amortized Distributional Projection Optimization for Sliced Wasserstein Point-Cloud Reconstruction ICML 2023
Improving Transformer with an Admixture of Attention Heads NIPS 2022
Beyond black box densities: Parameter learning for the deviated components NIPS 2022
FourierFormer: Transformer Meets Generalized Fourier Integral Theorem NIPS 2022
Amortized Projection Optimization for Sliced Wasserstein Generative Models NIPS 2022
On Multimarginal Partial Optimal Transport: Equivalent Forms and Computational Complexity AISTATS 2022
Towards Statistical and Computational Complexities of Polyak Step Size Gradient Descent AISTATS 2022
Weak Separation in Mixture Models and Implications for Principal Stratification AISTATS 2022
On the Complexity of Approximating Multimarginal Optimal Transport JMLR 2022
Revisiting Sliced Wasserstein on Images: From Vectorization to Convolution NIPS 2022
On Structured Filtering-Clustering: Global Error Bound and Optimal First-Order Algorithms AISTATS 2022
Entropic Gromov-Wasserstein between Gaussian Distributions ICML 2022
Architecture Agnostic Federated Learning for Neural Networks ICML 2022
Refined Convergence Rates for Maximum Likelihood Estimation under Finite Mixture Models ICML 2022
Improving Transformers with Probabilistic Attention Keys ICML 2022
On Transportation of Mini-batches: A Hierarchical Approach ICML 2022
Improving Mini-batch Optimal Transport via Partial Transportation ICML 2022
On the Efficiency of Entropic Regularized Algorithms for Optimal Transport JMLR 2022
Convergence Rates for Gaussian Mixtures of Experts JMLR 2022
Stochastic Multiple Target Sampling Gradient Descent NIPS 2022
Point-Set Distances for Learning Representations of 3D Point Clouds ICCV 2021
Flow-based Alignment Approaches for Probability Measures in Different Spaces AISTATS 2021
On the Minimax Optimality of the EM Algorithm for Learning Two-Component Mixed Linear Regression AISTATS 2021
LAMDA: Label Matching Deep Domain Adaptation ICML 2021
On Robust Optimal Transport: Computational Complexity and Barycenter Computation NIPS 2021
Structured Dropout Variational Inference for Bayesian Neural Networks NIPS 2021
On efficient multilevel Clustering via Wasserstein distances JMLR 2021
Distributional Sliced-Wasserstein and Applications to Generative Modeling ICLR 2021
Improving Relational Regularized Autoencoders with Spherical Sliced Fused Gromov Wasserstein ICLR 2021
On Unbalanced Optimal Transport: An Analysis of Sinkhorn Algorithm ICML 2020
Sharp Analysis of Expectation-Maximization for Weakly Identifiable Models AISTATS 2020
Fast Algorithms for Computational Optimal Transport and Wasserstein Barycenter AISTATS 2020
Fixed-Support Wasserstein Barycenters: Computational Hardness and Fast Algorithm NIPS 2020
Projection Robust Wasserstein Distance and Riemannian Optimization NIPS 2020
On Efficient Optimal Transport: An Analysis of Greedy and Accelerated Mirror Descent Algorithms ICML 2019
Probabilistic Multilevel Clustering via Composite Transportation Distance AISTATS 2019
Theoretical guarantees for EM under misspecified Gaussian mixture models NIPS 2018
Multilevel Clustering via Wasserstein Means ICML 2017