Scholar
Hyokun Yun
Google Scholar ID: W4oOmZEAAAAJ
Machine Learning Scientist at Amazon
Citations & Impact
Citations
957
H-index
11
i10-index
13
Publications
20
Co-authors
28
list available
Contact
Publications
Cited
0
Resume (English only)
Academic Achievements
- Thesis: Doubly Separable Models and Distributed Parameter Estimation
- Paper: Robustness to Capitalization Errors in Named Entity Recognition
- Paper: Scaling Multinomial Logistic Regression via Hybrid Parallelism
- Paper: Deep Active Learning for Named Entity Recognition
- Paper: Distributed Stochastic Optimization of the Regularized Risk
- Paper: WordRank: Learning Word Embeddings via Robust Ranking
- Paper: Nomadic Computing for Big Data Analytics
- Paper: A Scalable Asynchronous Distributed Algorithm for Topic Modeling
- Paper: Ranking via Robust Binary Classification and Parallel Parameter Estimation in Large-Scale Data
- Paper: NOMAD: Non-locking, stOchastic Multi-machine algorithm for Asynchronous and Decentralized matrix completion
- Paper: How to Filter out Random Clickers in a Crowdsourcing-Based Study?
- Paper: Efficiently Sampling Multiplicative Attribute Graphs Using a Ball-Dropping Process
- Paper: Quilting Stochastic Kronecker Graphs to Generate Multiplicative Attribute Graphs
- Book Chapter: Valid Prior-Free Probabilistic Inference and its Applications in Medical Statistics
- Software: NOMAD: Non-locking, stOchastic Multi-machine algorithm for Asynchronous and Decentralized matrix completion
Research Experience
- Machine Learning Scientist, Amazon LLC (current)
- Machine Learning Intern, Amazon LLC, Summer 2013
- Research Intern, Microsoft Research India, Fall 2012
- Predictive Analytics Intern, Blizzard Entertainment, Summer 2012
- Internship Researcher, Max Planck Institute Tuebingen, Summer 2011
- Associate Researcher, Cyram(c), 2006 - 2008
- Internship Consultant, Accenture Company, Summer 2005
Background
- Machine Learning Scientist, with research interests in efficient optimization algorithms for large-scale machine learning and statistical modeling of graphs.
Miscellany
- Hope to see more international presence of POSTECH alumni; please feel free to contact if I could be of any help.
