Kyurae Kim

Kyurae Kim
University of Pennsylvania | UP · Department of Computer and Information Science

Bachelor of Engineering

About

11
Publications
2,490
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
42
Citations
Citations since 2016
11 Research Items
41 Citations
201620172018201920202021202205101520
201620172018201920202021202205101520
201620172018201920202021202205101520
201620172018201920202021202205101520
Education
March 2016 - February 2021
Sogang University
Field of study
  • Electronics Engineering

Publications

Publications (11)
Article
Background and objective: Cardiac perfusion magnetic resonance imaging (MRI) with first pass dynamic contrast enhancement (DCE) is a useful tool to identify perfusion defects in myocardial tissues. Automatic segmentation of the myocardium can lead to efficient quantification of perfusion defects. The purpose of this study was to investigate the us...
Article
Full-text available
This paper proposes Bayesian optimization augmented factoring self-scheduling (BO FSS), a new parallel loop scheduling strategy. BO FSS is an automatic tuning variant of the factoring self-scheduling (FSS) algorithm and is based on Bayesian optimization (BO), a black-box optimization algorithm. Its core idea is to automatically tune the internal pa...
Preprint
Full-text available
Markov-chain Monte Carlo (MCMC) is a popular method for performing asymptotically exact Bayesian inference. However, the acceleration of MCMC by parallelizing its computation is a significant challenge. Despite the numerous algorithms developed for parallelizing MCMC, a fundamental question remains unanswered. If parallel MCMC is the answer, what i...
Preprint
Full-text available
Image enhancement methods are an essential tool for improving the clinical performance of medical ultrasound imaging systems. However, the benefits of these algorithms can only be obtained after tedious tuning of their many parameters. Unfortunately, tuning these parameters is challenging because the clinical performance of image enhancement method...
Conference Paper
Full-text available
Minimizing the inclusive Kullback-Leibler (KL) divergence with stochastic gradient descent (SGD) is challenging since its gradient is defined as an integral over the posterior. Recently, multiple methods have been proposed to run SGD with biased gradient estimates obtained from a Markov chain. This paper provides the first non-asymptotic convergenc...
Article
Full-text available
Background The purpose of this study was to develop a software tool and evaluate different T1 map calculation methods in terms of computation time in cardiac magnetic resonance imaging. Methods The modified Look-Locker inversion recovery (MOLLI) sequence was used to acquire multiple inversion time (TI) images for pre- and post-contrast T1 mapping....
Article
Full-text available
This paper proposes Hermes, a container-based preemptive GPU scheduling framework for accelerating hyper-parameter optimization in deep learning (DL) clusters. Hermes accelerates hyper-parameter optimization by time-sharing between DL jobs and prioritizing jobs with more promising hyper-parameter combinations. Hermes’s scheduling policy is grounded...
Preprint
In this paper, we propose a new parallel loop scheduling algorithm: Bayesian optimization augmented factoring self-scheduling (BO FSS). BO FSS is an automatic self-tuning variant of the factoring self-scheduling (FSS) algorithm. It automatically tunes the internal parameter of FSS by solving an optimization problem using Bayesian optimization (BO),...
Preprint
Full-text available
Bayesian optimization (BO) is a popular method for solving non-convex, noisy, black-box optimization problems. In practice, applying BO is not straightforward because of the hyperparameters associated with the internal Gaussian process (GP) surrogate model. Properly tuning these hyperparameters is essential for fast convergence, and more importantl...
Conference Paper
Full-text available
Efficient parallelization of loops is critical to improving the performance of high-performance computing applications. Many classical parallel loop scheduling algorithms have been developed to increase parallelization efficiency. Recently, workload-aware methods were developed to exploit the structure of workloads. However, both classical and work...
Article
Quantitative evaluation of diseased myocardium in cardiac magnetic resonance imaging (MRI) plays an important role in the diagnosis and prognosis of cardiovascular disease. The development of a user interface with state-of-the-art techniques would be beneficial for the efficient post-processing and analysis of cardiac images. The aim of this study...

Network

Cited By