3 citations · 5 across the 6 of their papers we have counts for
6 papers
Empirical Risk Minimization for Losses without Variance
Guanhua Fang, Ping Li, Gennady Samorodnitsky
This paper considers an empirical risk minimization problem under heavy-tailed settings, where data does not have finite variance, but only has -th moment with . In…
Copula for Instance-wise Feature Selection and Ranking
Hanyu Peng, Guanhua Fang, Ping Li
Instance-wise feature selection and ranking methods can achieve a good selection of task-friendly features for each sample in the context of neural networks. However, existing appr…
Catoni-style Confidence Sequences under Infinite Variance
Sujay Bhatt, Guanhua Fang, Ping Li +1
In this paper, we provide an extension of confidence sequences for settings where the variance of the data-generating distribution does not exist or is infinite. Confidence sequenc…
Best Subset Selection with Efficient Primal-Dual Algorithm
Shaogang Ren, Guanhua Fang, Ping Li
Best subset selection is considered the `gold standard' for many sparse learning problems. A variety of optimization techniques have been proposed to attack this non-convex and NP-…
Total variation approximations and conditional limit theorems for multivariate regularly varying random walks conditioned on ruin
Jose Blanchet, Jingchen Liu
We study a new technique for the asymptotic analysis of heavy-tailed systems conditioned on large deviations events. We illustrate our approach in the context of ruin events of mul…
Efficient Simulation and Conditional Functional Limit Theorems for Ruinous Heavy-tailed Random Walks
Jose Blanchet, Jingchen Liu
The contribution of this paper is to introduce change of measure based techniques for the rare-event analysis of heavy-tailed stochastic processes. Our changes-of-measure are param…