AI Paper Atlas

Research map / Learning theory and algorithms / Prediction and decision losses

Data-Efficient Learning via Minimizing Hyperspherical Energy

Xiaofeng Cao, Weiyang Liu, Ivor Wai-Hung Tsang

TPAMI 2023 · Learning theory and algorithms › Prediction and decision losses · approach: Determinantal point process inference · 22 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use SphericalKmeans instead of K-means for deep clustering (ablation)K-means+Auto+DEC · MNIST clusteringoptimal accuracy: 0.96221 -> 0.96864Improved
use SphericalKmeans instead of GMM (ablation)GMM+Auto+DEC · Fashion-MNIST clusteringoptimal accuracy: 0.61319 -> 0.63448Improved
add AutoEncoder and DEC loss to spherical K-means (ablation)SphericalKmeans · MNIST clusteringoptimal accuracy: 0.55188 -> 0.96864Improved
use l0 MHE instead of l2 MHE (ablation)l2 MHE · MNIST distribution matchingKL mean loss: 0.2751 -> 0.2183Improved
use l0 MHE instead of l1 MHE (ablation)l1 MHE · MNIST distribution matchingKL mean loss: 0.2103 -> 0.2183Hurt
use l0 MHE instead of l2 MHE (ablation)l2 MHE · Fashion-MNIST distribution matchingMMD_mu mean loss: 0.0410 -> 0.0364Improved
sample representative data in in-version-space instead of out-of-version-space (ablation)random sampling · MNIST and Fashion-MNISTclassification accuracyImproved
MHEAL versus Core-set in deep ALCore-set · MNIST 100 labelsaccuracy: 0.6310 -> 0.8648Improved
MHEAL versus Core-set in deep ALCore-set · CIFAR-100 2K labelsaccuracy: 0.2645 -> 0.3201Improved
MHEAL versus BALD at 2K CIFAR-10 labelsBALD · CIFAR-10 2K labelsaccuracy: 0.6203 -> 0.6510Hurt
add 10,000 repeated samples to training setMHEAL · CIFAR-10 10K labelsaccuracy: 0.8146 -> 0.8042Hurt
add 10,000 noisy samples to training setMHEAL · CIFAR-10 10K labelsaccuracy: 0.8146 -> 0.7885Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy