92 citations · 117 across the 8 of their papers we have counts for
9 papers
Score-based Outlier Generation via Controlling the Radon-Nikodym Derivative
Amartya Mukherjee, Tristan Milne, Kry Yik-Chau Lui +2
Outliers are important for stress-testing algorithms and understanding system behaviour under rare conditions. Despite being commonly described as low-likelihood events, existing g…
LassoFlexNet: Flexible Neural Architecture for Tabular Data
Kry Yik Chau Lui, Cheng Chi, Kishore Basu +1
Despite their dominance in vision and language, deep neural networks often underperform relative to tree-based models on tabular data. To bridge this gap, we incorporate five key i…
Rethinking Test-time Likelihood: The Likelihood Path Principle and Its Application to OOD Detection
Sicong Huang, Jiawei He, Kry Yik Chau Lui
While likelihood is attractive in theory, its estimates by deep generative models (DGMs) are often broken in practice, and perform poorly for out of distribution (OOD) Detection. V…
Robust Risk-Sensitive Reinforcement Learning Agents for Trading Markets
Yue Gao, Kry Yik Chau Lui, Pablo Hernandez-Leal
Trading markets represent a real-world financial application to deploy reinforcement learning agents, however, they carry hard fundamental challenges such as high variance and cost…
On the Sensitivity of Adversarial Robustness to Input Data Distributions
Gavin Weiguang Ding, Kry Yik Chau Lui, Xiaomeng Jin +2
Neural networks are vulnerable to small adversarial perturbations. Existing literature largely focused on understanding and mitigating the vulnerability of learned models. In this…
MMA Training: Direct Input Space Margin Maximization through Adversarial Training
Gavin Weiguang Ding, Yash Sharma, Kry Yik Chau Lui +1
We study adversarial robustness of neural networks from a margin maximization perspective, where margins are defined as the distances from inputs to a classifier's decision boundar…
Dimensionality Reduction has Quantifiable Imperfections: Two Geometric Bounds
Kry Yik Chau Lui, Gavin Weiguang Ding, Ruitong Huang +1
In this paper, we investigate Dimensionality reduction (DR) maps in an information retrieval setting from a quantitative topology point of view. In particular, we show that no DR m…
Improving GAN Training via Binarized Representation Entropy (BRE) Regularization
Yanshuai Cao, Gavin Weiguang Ding, Kry Yik-Chau Lui +1
We propose a novel regularizer to improve the training of Generative Adversarial Networks (GANs). The motivation is that when the discriminator D spreads out its model capacity in…
Implicit Manifold Learning on Generative Adversarial Networks
Kry Yik Chau Lui, Yanshuai Cao, Maxime Gazeau +1
This paper raises an implicit manifold learning perspective in Generative Adversarial Networks (GANs), by studying how the support of the learned distribution, modelled as a subman…