T. Nguyen

发表

Momentum Transformer: Closing the Performance Gap Between Self-attention and Its Linearization

Robert M. Kirby, Richard Baraniuk, S. Osher, 2022, MSML.

The Latent-Dependent Deep Rendering Model

Michael I. Jordan, Ankit B. Patel, Richard Baraniuk, 2018 .

A Bayesian Perspective of Convolutional Neural Networks through a Deconvolutional Generative Model

Michael I. Jordan, Ankit B. Patel, Richard Baraniuk, 2018, 1811.02657.

Improving Generative Flow Networks with Path Regularization

Khuong N. Nguyen, Nhat Ho, S. Osher, 2022, arXiv.org.

GRAND++: G RAPH N EURAL D IFFUSION WITH A S OURCE T ERM

S. Osher, T. Strohmer, A. Bertozzi, 2022 .

Turbulence forecasting via Neural ODE.

Michael Chertkov, Andreas Dengel, Anima Anandkumar, 2019, 1911.05180.

FourierFormer: Transformer Meets Generalized Fourier Integral Theorem

Nhat Ho, S. Osher, Khai Nguyen, 2022, NeurIPS.

Scheduled Restart Momentum for Accelerated Stochastic Gradient Descent

S. Osher, Richard Baraniuk, Tan Nguyen, 2020, SIAM J. Imaging Sci..

Principled Approaches Applications Interpretability Robustness Efficiency Deep Learning Systems Natural Language Processing Computer Vision Mathematical Modeling

T. Nguyen, 2022 .

Robustify Transformers with Robust Kernel Density Estimation

Nhat Ho, Khai Nguyen, J. Ghosh, 2022, ArXiv.

Revisiting Over-smoothing and Over-squashing using Ollivier's Ricci Curvature

Khuong N. Nguyen, Nhat Ho, T. Nguyen, 2022, ArXiv.

Neural Collapse in Deep Linear Network: From Balanced to Imbalanced Data

Nhat Ho, Hien Dang, T. Nguyen, 2023, ArXiv.

Hierarchical Sliced Wasserstein Distance

Nhat Ho, Khai Nguyen, Tongzheng Ren, 2022, ArXiv.

How does momentum benefit deep neural networks architecture design? A few case studies

S. Osher, Bao Wang, Hedi Xia, 2022, Research in the Mathematical Sciences.

How does momentum benefit deep neural networks architecture design? A few case studies pdf

Stanley Osher, Tan Nguyen, Hedi Xia, 2021, Research in the Mathematical Sciences.

Heavy Ball Neural Ordinary Differential Equations pdf

Andrea L. Bertozzi, Hangjie Ji, Hedi Xia, 2021, NeurIPS.

MomentumRNN: Integrating Momentum into Recurrent Neural Networks pdf

Richard G. Baraniuk, Andrea L. Bertozzi, Stanley J. Osher, 2020, NeurIPS.

Improving Transformers with Probabilistic Attention Keys

Richard Baraniuk, Nhat Ho, Tan Nguyen, 2021, ICML.

Dual Dynamic Inference: Enabling More Efficient, Adaptive, and Controllable Deep Inference

Yue Wang, Yingyan Lin, Pengfei Xu, 2019, IEEE Journal of Selected Topics in Signal Processing.

SP-GPT2: Semantics Improvement in Vietnamese Poetry Generation

Tan Nguyen, Tuan Nguyen, Hanh Pham, 2021, 2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA).

InfoCNF: An Efficient Conditional Continuous Normalizing Flow with Adaptive Solvers pdf

Richard G. Baraniuk, Anima Anandkumar, Animesh Garg, 2019, ArXiv.

InfoCNF: An Efficient Conditional Continuous Normalizing Flow with Adaptive Solvers

Richard Baraniuk, Anima Anandkumar, Animesh Garg, 2019, 1912.03978.

Revisiting Over-smoothing and Over-squashing using Ollivier's Ricci Curvature

Vinh Phu Nguyen, Khuong N. Nguyen, Nhat Ho, 2022, ArXiv.

Algorithms for Direct 0-1 Loss Optimization in Binary Classification

Scott Sanner, Tan Nguyen, S. Sanner, 2013, ICML.

FMMformer: Efficient and Flexible Transformer via Decomposed Near-field and Far-field Attention pdf

Stanley J. Osher, Bao Wang, Vai Suliafu, 2021, NeurIPS.

Transformer with Fourier Integral Attentions

Nhat Ho, Tan Nguyen, S. Osher, 2022, ArXiv.

Out-of-Distribution Detection Using Neural Rendering Generative Models pdf

Richard G. Baraniuk, Anima Anandkumar, Yujia Huang, 2019, ArXiv.

GRAND++: Graph Neural Diffusion with A Source Term

S. Osher, T. Strohmer, A. Bertozzi, 2022, ICLR.

Hierarchical Sliced Wasserstein Distance

Nhat Ho, Khai Nguyen, Tongzheng Ren, 2022, ICLR.

Neural Networks with Recurrent Generative Feedback

Doris Y. Tsao, Anima Anandkumar, James Gornet, 2020, NeurIPS.

Neural Collapse in Deep Linear Networks: From Balanced to Imbalanced Data

Nhat Ho, Hien Dang, T. Nguyen, 2023, ICML.

Neural Rendering Model: Joint Generation and Prediction for Semi-Supervised Learning pdf

Michael I. Jordan, Richard G. Baraniuk, Anima Anandkumar, 2018, ArXiv.

Revisiting Over-smoothing and Over-squashing using Ollivier's Ricci Curvature

Vinh Phu Nguyen, Khuong N. Nguyen, Nhat Ho, 2022, ICML.

Posterior Collapse in Linear Conditional and Hierarchical Variational Autoencoders

Nhat Ho, T. Nguyen, Tho Tran, 2023, ArXiv.

Improving Neural Ordinary Differential Equations with Nesterov's Accelerated Gradient Method

Thieu N. Vo, S. Osher, N. Nguyen, 2022, NeurIPS.

A Primal-Dual Framework for Transformers and Neural Networks

Richard Baraniuk, Nhat Ho, S. Osher, 2023, ICLR.

EnergyNet: Energy-Efficient Dynamic Inference

Yingyan Lin, Yang Zhao, Richard G. Baraniuk, 2018 .

InfoCNF: An Efficient Conditional Continuous Normalizing Flow with Adaptive Solvers

Richard Baraniuk, Anima Anandkumar, Animesh Garg, 2019, ArXiv.

Transformer with a Mixture of Gaussian Keys pdf

Richard G. Baraniuk, Nhat Ho, Stanley J. Osher, 2021, ArXiv.

Improving Transformer with an Admixture of Attention Heads

Nhat Ho, S. Osher, Minh Pham, 2022, NeurIPS.