Coresets for the Average Case Error for Finite Query Sets
Coreset is usually a small weighted subset of an input set of items, that provably approximates their loss function for a given set of queries (models, classifiers, hypothesis). That is, the maximum (worst-case) error over all queries is bounded. To obtain smaller coresets, we suggest a natural rela...
Main Authors: | Alaa Maalouf, Ibrahim Jubran, Murad Tukan, Dan Feldman |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-10-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/21/19/6689 |
Similar Items
-
Deterministic Coresets for <em>k</em>-Means of Big Sparse Data
by: Artem Barger, et al.
Published: (2020-04-01) -
Autonomous Toy Drone via Coresets for Pose Estimation
by: Soliman Nasser, et al.
Published: (2020-05-01) -
Understanding Collections of Related Datasets Using Dependent MMD Coresets
by: Sinead A. Williamson, et al.
Published: (2021-09-01) -
Sphere Fitting with Applications to Machine Tracking
by: Dror Epstein, et al.
Published: (2020-07-01) -
GAN Training Acceleration Using Fréchet Descriptor-Based Coreset
by: Yanzhe Xu, et al.
Published: (2022-07-01)