V
V. Roshan Joseph
Researcher at Georgia Institute of Technology
Publications - 115
Citations - 3758
V. Roshan Joseph is an academic researcher from Georgia Institute of Technology. The author has contributed to research in topics: Gaussian process & Computer science. The author has an hindex of 30, co-authored 102 publications receiving 2928 citations. Previous affiliations of V. Roshan Joseph include University of Michigan.
Papers
More filters
Journal ArticleDOI
Blind Kriging: A New Method for Developing Metamodels
TL;DR: A modified kriging method is proposed, which has an unknown mean model, called blind kriged, which is identified from experimental data using a Bayesian variable selection technique.
Journal Article
Orthogonal-maximin latin hypercube designs
V. Roshan Joseph,Ying Hung +1 more
TL;DR: A multi-objective optimization approach to find good LHDs by combining correlation and distance performance measures is proposed and a new exchange algorithm for efficiently generating such designs is proposed.
Proceedings ArticleDOI
Building Surrogate Models Based on Detailed and Approximate Simulations
TL;DR: In this article, a new approach is taken to integrate data from approximate and detailed simulations to build a surrogate model to describe the relationship between output and input parameters, which is used to construct a model based on a Gaussian process.
Journal ArticleDOI
Maximum projection designs for computer experiments
TL;DR: In this article, the authors proposed a method to maximize space-filling properties on projections to all subsets of factors, which can be computed at no more cost than a design criterion that ignores projection properties.
Journal ArticleDOI
Structured variable selection and estimation
TL;DR: This paper proposes non-negative garrote methods that can naturally incorporate such relationships defined through effect heredity principles or marginality principles, and shows that the methods are very easy to compute and enjoy nice theoretical properties.