Seung-Hwan Lim Research Scientist Contact LIMS1@ORNL.GOV All Publications In-Place Zero-Space Memory Protection for CNN A Quantitative Study of Deep Learning Training on Heterogeneous Supercomputers Wootz: a compiler-based framework for fast CNN pruning via composability SORA: Scalable Overlap-graph Reduction Algorithms for Genome Assembly using Apache Spark in the Cloud 167-PFlops deep learning for electron microscopy: from learning physics to atomic manipulation Exploring flexible communications for streamlining DNN ensemble training pipelines A Heterogeneity-Aware Task Scheduler for Spark Scaling Up Data-Parallel Analytics Platforms: Linear Algebraic Operation Cases Scientific User Behavior and Data-Sharing Trends in a Petascale File System TagIt: An Integrated Indexing and Search Service for File Systems... A Quantitative Model of Application Slow-Down in Multi-Resource Shared Systems... Kernels for scalable data analysis in science: Towards an architecture-portable future Constellation: A Science Graph Network for Scalable Data and Knowledge Discovery in Extreme-Scale Scientific Collaborations... Mini-Apps for High Performance Data Analysis FatMan vs. LittleBoy: Scaling up Linear Algebraic Operations in Scale-out Data Platforms Evaluation of Graph Pattern Matching Workloads in Graph Analysis Systems Enabling Graph Mining in RDF Triplestores using SPARQL for Holistic In-situ Graph Analysis An analysis of image storage systems for scalable training of deep neural networks Benchmarking High Performance Graph Analysis Systems with Graph Mining and Pattern Matching Workloads Optimizing Deep Learning Hyper-Parameters Through an Evolutionary Algorithm... Graph Mining Meets the Semantic Web... Graph processing platforms at scale: practices and experiences Table2Graph: A Scalable Graph Construction From Relational Tables using Map-Reduce... A Scalable Graph Construction from Relational Tables using Map-Reduce Optimizing deep learning hyper-parameters through an evolutionary algorithm Pagination First page « First Previous page ‹‹ Page 1 Current page 2 Page 3 Next page ›› Last page Last » Key Links ORCID Organizations Computing and Computational Sciences Directorate Computer Science and Mathematics Division Mathematics in Computation Section Discrete Algorithms Group
Research Highlight Adaptive Single Parameter Total Variation Regularization for Derivative Estimation
