Search Results for author: Hung Bui

Found 21 papers, 6 papers with code

Temporal Predictive Coding For Model-Based Planning In Latent Space

2 code implementations14 Jun 2021 Tung Nguyen, Rui Shu, Tuan Pham, Hung Bui, Stefano Ermon

High-dimensional observations are a major challenge in the application of model-based reinforcement learning (MBRL) to real-world environments.

Model-based Reinforcement Learning Representation Learning

Structured Dropout Variational Inference for Bayesian Neural Networks

no code implementations16 Feb 2021 Son Nguyen, Duong Nguyen, Khai Nguyen, Nhat Ho, Khoat Than, Hung Bui

Approximate inference in deep Bayesian networks exhibits a dilemma of how to yield high fidelity posterior approximations while maintaining computational efficiency and scalability.

Bayesian Inference Out-of-Distribution Detection +1

On Robust Optimal Transport: Computational Complexity, Low-rank Approximation, and Barycenter Computation

no code implementations13 Feb 2021 Khang Le, Huy Nguyen, Quang Nguyen, Nhat Ho, Tung Pham, Hung Bui

Finally, we consider a barycenter problem based on RSOT, named $\textit{Robust Semi-Constrained Barycenter}$ problem (RSBP), and develop a robust iterative Bregman projection algorithm, called $\textbf{Normalized-RobustIBP}$ algorithm, to solve the RSBP in the discrete settings of probability distributions.

On Transportation of Mini-batches: A Hierarchical Approach

1 code implementation11 Feb 2021 Khai Nguyen, Dang Nguyen, Quoc Nguyen, Tung Pham, Hung Bui, Dinh Phung, Trung Le, Nhat Ho

To address these problems, we propose a novel mini-batching scheme for optimal transport, named Batch of Mini-batches Optimal Transport (BoMb-OT), that finds the optimal coupling between mini-batches and it can be seen as an approximation to a well-defined distance on the space of probability measures.

Domain Adaptation

Non-Markovian Predictive Coding For Planning In Latent Space

no code implementations1 Jan 2021 Tung Nguyen, Rui Shu, Tuan Pham, Hung Bui, Stefano Ermon

High-dimensional observations are a major challenge in the application of model-based reinforcement learning (MBRL) to real-world environments.

Model-based Reinforcement Learning Representation Learning

Bayesian Metric Learning for Robust Training of Deep Models under Noisy Labels

no code implementations1 Jan 2021 Toan Tran, Hieu Vu, Gustavo Carneiro, Hung Bui

Label noise is a natural event of data collection and annotation and has been shown to have significant impact on the performance of deep learning models regarding accuracy reduction and sample complexity increase.

Classification General Classification +2

Learning Compositional Sparse Gaussian Processes with a Shrinkage Prior

no code implementations21 Dec 2020 Anh Tong, Toan Tran, Hung Bui, Jaesik Choi

Choosing a proper set of kernel functions is an important problem in learning Gaussian Process (GP) models since each kernel structure has different model complexity and data fitness.

Gaussian Processes Time Series

Improving Relational Regularized Autoencoders with Spherical Sliced Fused Gromov Wasserstein

2 code implementations ICLR 2021 Khai Nguyen, Son Nguyen, Nhat Ho, Tung Pham, Hung Bui

To improve the discrepancy and consequently the relational regularization, we propose a new relational discrepancy, named spherical sliced fused Gromov Wasserstein (SSFG), that can find an important area of projections characterized by a von Mises-Fisher distribution.

Image Generation

Vec2Face: Unveil Human Faces from their Blackbox Features in Face Recognition

no code implementations CVPR 2020 Chi Nhan Duong, Thanh-Dat Truong, Kha Gia Quach, Hung Bui, Kaushik Roy, Khoa Luu

Unveiling face images of a subject given his/her high-level representations extracted from a blackbox Face Recognition engine is extremely challenging.

Face Recognition Image Reconstruction +1

Distributional Sliced-Wasserstein and Applications to Generative Modeling

1 code implementation ICLR 2021 Khai Nguyen, Nhat Ho, Tung Pham, Hung Bui

Sliced-Wasserstein distance (SW) and its variant, Max Sliced-Wasserstein distance (Max-SW), have been used widely in the recent years due to their fast computation and scalability even when the probability measures lie in a very high dimensional space.

On Unbalanced Optimal Transport: An Analysis of Sinkhorn Algorithm

no code implementations ICML 2020 Khiem Pham, Khang Le, Nhat Ho, Tung Pham, Hung Bui

We provide a computational complexity analysis for the Sinkhorn algorithm that solves the entropic regularized Unbalanced Optimal Transport (UOT) problem between two measures of possibly different masses with at most $n$ components.

On Efficient Multilevel Clustering via Wasserstein Distances

1 code implementation19 Sep 2019 Viet Huynh, Nhat Ho, Nhan Dam, XuanLong Nguyen, Mikhail Yurochkin, Hung Bui, and Dinh Phung

We propose a novel approach to the problem of multilevel clustering, which aims to simultaneously partition data in each group and discover grouping patterns among groups in a potentially large hierarchically structured corpus of data.

Prediction, Consistency, Curvature: Representation Learning for Locally-Linear Control

1 code implementation ICLR 2020 Nir Levine, Yin-Lam Chow, Rui Shu, Ang Li, Mohammad Ghavamzadeh, Hung Bui

A promising approach is to embed the high-dimensional observations into a lower-dimensional latent representation space, estimate the latent dynamics model, then utilize this model for control in the latent space.

Decision Making Representation Learning

On Deep Domain Adaptation: Some Theoretical Understandings

no code implementations15 Nov 2018 Trung Le, Khanh Nguyen, Nhat Ho, Hung Bui, Dinh Phung

The underlying idea of deep domain adaptation is to bridge the gap between source and target domains in a joint space so that a supervised classifier trained on labeled source data can be nicely transferred to the target domain.

Domain Adaptation Transfer Learning

Robust Locally-Linear Controllable Embedding

no code implementations15 Oct 2017 Ershad Banijamali, Rui Shu, Mohammad Ghavamzadeh, Hung Bui, Ali Ghodsi

We also propose a principled variational approximation of the embedding posterior that takes the future observation into account, and thus, makes the variational approximation more robust against the noise.

Graphical Model Sketch

no code implementations9 Feb 2016 Branislav Kveton, Hung Bui, Mohammad Ghavamzadeh, Georgios Theocharous, S. Muthukrishnan, Siqi Sun

Graphical models are a popular approach to modeling structured data but they are unsuitable for high-cardinality variables.

Boosted Markov Networks for Activity Recognition

no code implementations6 Aug 2014 Truyen Tran, Hung Bui, Svetha Venkatesh

We explore a framework called boosted Markov networks to combine the learning capacity of boosting and the rich modeling semantics of Markov networks and applying the framework for video-based activity recognition.

Activity Recognition Feature Selection +1

Human Activity Learning and Segmentation using Partially Hidden Discriminative Models

no code implementations6 Aug 2014 Truyen Tran, Hung Bui, Svetha Venkatesh

Learning and understanding the typical patterns in the daily activities and routines of people from low-level sensory data is an important problem in many application domains such as building smart environments, or providing intelligent assistance.

Automorphism Groups of Graphical Models and Lifted Variational Inference

no code implementations26 Sep 2013 Hung Bui, Tuyen Huynh, Sebastian Riedel

This automorphism group provides a precise mathematical framework for lifted inference in the general exponential family.

Variational Inference

Cannot find the paper you are looking for? You can Submit a new open access paper.