Search Results for author: Rui Shu

Found 19 papers, 10 papers with code

Dazzle: Using Optimized Generative Adversarial Networks to Address Security Data Class Imbalance Issue

no code implementations22 Mar 2022 Rui Shu, Tianpei Xia, Laurie Williams, Tim Menzies

Conclusion: Based on this study, we would suggest the use of optimized GANs as an alternative method for security vulnerability data class imbalanced issues.

Bayesian Optimization

Mind Your Bits and Errors: Prioritizing the Bits that Matter in Variational Autoencoders

no code implementations29 Sep 2021 Rui Shu, Stefano Ermon

In this work, we consider the task of image generative modeling with variational autoencoders and posit that the nature of high-dimensional image data distributions poses an intrinsic challenge.

Temporal Predictive Coding For Model-Based Planning In Latent Space

3 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

Anytime Sampling for Autoregressive Models via Ordered Autoencoding

1 code implementation ICLR 2021 Yilun Xu, Yang song, Sahaj Garg, Linyuan Gong, Rui Shu, Aditya Grover, Stefano Ermon

Experimentally, we demonstrate in several image and audio generation tasks that sample quality degrades gracefully as we reduce the computational budget for sampling.

Audio Generation Computational Efficiency

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

Omni: Automated Ensemble with Unexpected Models against Adversarial Evasion Attack

no code implementations23 Nov 2020 Rui Shu, Tianpei Xia, Laurie Williams, Tim Menzies

Conclusion: When employing ensemble defense against adversarial evasion attacks, we suggest creating an ensemble with unexpected models that are distant from the attacker's expected model (i. e., target model) through methods such as hyperparameter optimization.

BIG-bench Machine Learning Ensemble Learning +2

Predictive Coding for Locally-Linear Control

1 code implementation ICML 2020 Rui Shu, Tung Nguyen, Yin-Lam Chow, Tuan Pham, Khoat Than, Mohammad Ghavamzadeh, Stefano Ermon, Hung H. Bui

High-dimensional observations and unknown dynamics are major challenges when applying optimal control to many real-world decision making tasks.

Decision Making

How to Better Distinguish Security Bug Reports (using Dual Hyperparameter Optimization

no code implementations4 Nov 2019 Rui Shu, Tianpei Xia, Jianfeng Chen, Laurie Williams, Tim Menzies

For example, in a study of security bug reports from the Chromium dataset, the median recalls of FARSEC and Swift were 15. 7% and 77. 4%, respectively.

Software Engineering

Fair Generative Modeling via Weak Supervision

1 code implementation ICML 2020 Kristy Choi, Aditya Grover, Trisha Singh, Rui Shu, Stefano Ermon

Real-world datasets are often biased with respect to key demographic factors such as race and gender.

Image Generation

Weakly Supervised Disentanglement with Guarantees

1 code implementation ICLR 2020 Rui Shu, Yining Chen, Abhishek Kumar, Stefano Ermon, Ben Poole

Learning disentangled representations that correspond to factors of variation in real-world data is critical to interpretable and human-controllable machine learning.

Disentanglement

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 Open-Ended Question Answering +1

Training Variational Autoencoders with Buffered Stochastic Variational Inference

no code implementations27 Feb 2019 Rui Shu, Hung H. Bui, Jay Whang, Stefano Ermon

The recognition network in deep latent variable models such as variational autoencoders (VAEs) relies on amortized inference for efficient posterior approximation that can scale up to large datasets.

Variational Inference

Amortized Inference Regularization

no code implementations NeurIPS 2018 Rui Shu, Hung H. Bui, Shengjia Zhao, Mykel J. Kochenderfer, Stefano Ermon

In this paper, we leverage the fact that VAEs rely on amortized inference and propose techniques for amortized inference regularization (AIR) that control the smoothness of the inference model.

Density Estimation Representation Learning

Constructing Unrestricted Adversarial Examples with Generative Models

1 code implementation NeurIPS 2018 Yang Song, Rui Shu, Nate Kushman, Stefano Ermon

Then, conditioned on a desired class, we search over the AC-GAN latent space to find images that are likely under the generative model and are misclassified by a target classifier.

Generative Adversarial Network

A DIRT-T Approach to Unsupervised Domain Adaptation

4 code implementations ICLR 2018 Rui Shu, Hung H. Bui, Hirokazu Narui, Stefano Ermon

Domain adaptation refers to the problem of leveraging labeled data in a source domain to learn an accurate model in a target domain where labels are scarce or unavailable.

Unsupervised Domain Adaptation

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.

Bottleneck Conditional Density Estimation

1 code implementation ICML 2017 Rui Shu, Hung H. Bui, Mohammad Ghavamzadeh

We introduce a new framework for training deep generative models for high-dimensional conditional density estimation.

Density Estimation

Automated Attribution and Intertextual Analysis

no code implementations3 May 2014 James Brofos, Ajay Kannan, Rui Shu

In this work, we employ quantitative methods from the realm of statistics and machine learning to develop novel methodologies for author attribution and textual analysis.

Author Attribution Authorship Attribution +1

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