Weihong Guo

2 accepted papers

2025

Neuromanifold-Regularized KANs for Shape-fair Feature Representations

Mazlum Ferhat Arslan, Weihong Guo, Shuo Li

ICCV 2025poster

Traditional deep networks struggle to acquire shape-fair representations due to their high expressivity. Kolmogorov-Arnold Networks (KANs) are promising candidates as they learn nonlinearities directly, a property that makes them more adaptive. However, KANs perform suboptimally in terms of shape-fa…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2016

On the Consistency of Feature Selection With Lasso for Non-linear Targets

Yue Zhang, Weihong Guo, Soumya Ray

ICML 2016poster

An important question in feature selection is whether a selection strategy recovers the “true” set of features, given enough data. We study this question in the context of the popular Least Absolute Shrinkage and Selection Operator (Lasso) feature selection strategy. In particular, we consider the s…

Cited by 30 Source ↗PDF ↗Scholar ↗