S
Seung-Jean Kim
Researcher at Stanford University
Publications - 56
Citations - 8122
Seung-Jean Kim is an academic researcher from Stanford University. The author has contributed to research in topics: Convex optimization & Geometric programming. The author has an hindex of 25, co-authored 56 publications receiving 7461 citations. Previous affiliations of Seung-Jean Kim include Citigroup.
Papers
More filters
Proceedings Article
A method for large-scale l 1 -regularized logistic regression
TL;DR: In this article, an efficient interior-point method for solving logistic regression with l1 regularization is proposed, which can solve large sparse problems with up to a thousand or so features and examples in seconds on a PC.
Proceedings ArticleDOI
An Efficient Method for Large-Scale l 1 -Regularized Convex Loss Minimization
TL;DR: An efficient interior-point method for solving large-scale lscr1-regularized convex loss minimization problems that uses a preconditioned conjugate gradient method to compute the search step and can solve very large problems.
Journal ArticleDOI
Estimating monotone convex functions via sequential shape modification
TL;DR: The uniform convergence rate achieved by the proposed method is nearly comparable to the best achievable rate for a non-parametric estimate which ignores the shape constraint.
Journal ArticleDOI
Estimating cell probabilities in contingency tables with constraints on marginals/conditionals by geometric programming with applications
TL;DR: This paper focuses on finding the MLE of cell probabilities in contingency tables under two common types of constraints: known marginals and ordered marginals/conditionals, and proposes a novel approach based on geometric programming.
Proceedings Article
Nonparametric Sharpe Ratio Function Estimation in Heteroscedastic Regression Models via Convex Optimization
TL;DR: The proposed parametrization leads to a functional that is jointly convex in the Sharpe ratio and inverse volatility functions, and the finite-sample performance of the proposed estimation method is superior to existing methods that estimate the mean and variance functions separately.