9 citations · 24 across the 13 of their papers we have counts for
13 papers
Maximum Entropy Inverse Reinforcement Learning of Diffusion Models with Energy-Based Models
Sangwoong Yoon, Himchan Hwang, Dohyun Kwon +2
We present a maximum entropy inverse reinforcement learning (IRL) approach for improving the sample quality of diffusion generative models, especially when the number of generation…
Generalized Contrastive Divergence: Joint Training of Energy-Based Model and Diffusion Model through Inverse Reinforcement Learning
Sangwoong Yoon, Dohyun Kwon, Himchan Hwang +2
We present Generalized Contrastive Divergence (GCD), a novel objective function for training an energy-based model (EBM) and a sampler simultaneously. GCD generalizes Contrastive D…
Variational Weighting for Kernel Density Ratios
Sangwoong Yoon, Frank C. Park, Gunsu S Yun +2
Kernel density estimation (KDE) is integral to a range of generative and discriminative tasks in machine learning. Drawing upon tools from the multidimensional calculus of variatio…
Energy-Based Models for Anomaly Detection: A Manifold Diffusion Recovery Approach
Sangwoong Yoon, Young-Uk Jin, Yung-Kyun Noh +1
We present a new method of training energy-based models (EBMs) for anomaly detection that leverages low-dimensional structures within data. The proposed algorithm, Manifold Project…
Local Metric Learning for Off-Policy Evaluation in Contextual Bandits with Continuous Actions
Haanvid Lee, Jongmin Lee, Yunseon Choi +4
We consider local kernel metric learning for off-policy evaluation (OPE) of deterministic policies in contextual bandits with continuous action spaces. Our work is motivated by pra…
Evaluating Out-of-Distribution Detectors Through Adversarial Generation of Outliers
Sangwoong Yoon, Jinwon Choi, Yonghyeon Lee +2
A reliable evaluation method is essential for building a robust out-of-distribution (OOD) detector. Current robustness evaluation protocols for OOD detectors rely on injecting pert…
Autoencoding Under Normalization Constraints
Sangwoong Yoon, Yung-Kyun Noh, Frank Chongwoo Park
Likelihood is a standard estimate for outlier detection. The specific role of the normalization constraint is to ensure that the out-of-distribution (OOD) regime has a small likeli…
Learning to increase matching efficiency in identifying additional b-jets in the process
Cheongjae Jang, Sang-Kyun Ko, Yung-Kyun Noh +3
The process is an essential channel to reveal the Higgs properties but has an irreducible background from the $\text{t}\bar…
K-Beam Minimax: Efficient Optimization for Deep Adversarial Learning
Jihun Hamm, Yung-Kyun Noh
Minimax optimization plays a key role in adversarial training of machine learning algorithms, such as learning generative models, domain adaptation, privacy preservation, and robus…
Nearest neighbor density functional estimation from inverse Laplace transform
J. Jon Ryu, Shouvik Ganguly, Young-Han Kim +2
A new approach to -consistent estimation of a general density functional using -nearest neighbor distances is proposed, where the functional under consideration is in the f…
Scalable Iterative Algorithm for Robust Subspace Clustering
Sanghyuk Chun, Yung-Kyun Noh, Jinwoo Shin
Subspace clustering (SC) is a popular method for dimensionality reduction of high-dimensional data, where it generalizes Principal Component Analysis (PCA). Recently, several metho…
Direct Density-Derivative Estimation and Its Application in KL-Divergence Approximation
Hiroaki Sasaki, Yung-Kyun Noh, Masashi Sugiyama
Estimation of density derivatives is a versatile tool in statistical data analysis. A naive approach is to first estimate the density and then compute its derivative. However, such…
Learning Discriminative Metrics via Generative Models and Kernel Learning
Yuan Shi, Yung-Kyun Noh, Fei Sha +1
Metrics specifying distances between data points can be learned in a discriminative manner or from generative models. In this paper, we show how to unify generative and discriminat…