9 citations · 12 across the 6 of their papers we have counts for
4 papers · 1 filter
Semi-Supervised Learning with Noisy Proxy Covariates: Generalization Bounds and Distribution Regression
Kwangho Kim, Jisu Kim
In many modern machine learning pipelines, abundant pretrained representations serve as noisy proxy covariates, while task-specific labels remain scarce. We study semi-supervised r…
Topological Learning for Motion Data via Mixed Coordinates
Hengrui Luo, Jisu Kim, Alice Patania +1
Topology can extract the structural information in a dataset efficiently. In this paper, we attempt to incorporate topological information into a multiple output Gaussian process m…
TopP&R: Robust Support Estimation Approach for Evaluating Fidelity and Diversity in Generative Models
Pum Jun Kim, Yoojin Jang, Jisu Kim +1
We propose a robust and reliable evaluation metric for generative models by introducing topological and statistical treatments for rigorous support estimation. Existing metrics, su…
PLLay: Efficient Topological Layer based on Persistence Landscapes
Kwangho Kim, Jisu Kim, Manzil Zaheer +3
We propose PLLay, a novel topological layer for general deep learning models based on persistence landscapes, in which we can efficiently exploit the underlying topological feature…