AI Paper Atlas

Research map / Optimization / Optimizers

Ultrametric Fitting by Gradient Descent

Giovanni Chierchia, Benjamin Perret

NeurIPS 2019 · Optimization › Optimizers · approach: Surrogate losses and robust solvers · 15 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 gradient descent with the min-max ultrametric operator to fit the dissimilarity graphUltrametric fitting · Planar superpixel graphsmean square errorImproved
Use Closest+Size or Dasgupta instead of WardHierarchical clustering · Five LIBSVM datasetsclassification accuracyNo clear effect
Use Closest+Triplet with labeled tripletsSemi-supervised clustering · Five LIBSVM datasetsclassification accuracyNo clear effect
Use semi-supervised SVM instead of spectral clusteringSemi-supervised clustering · Five LIBSVM datasetsclassification accuracyImproved
Use the Dasgupta relaxation instead of Closest+SizeHierarchical clustering · Digit1 and Heartclassification accuracyHurt
Use average linkage or closest ultrametric instead of WardHierarchical clustering · Five LIBSVM datasetsclassification accuracyHurt
Add cluster-size regularization to closest-ultrametric fitting (ablation)Closest ultrametric · Illustrative hierarchical-clustering examplessmall clusters at large scalesImproved
Add triplet regularization to closest-ultrametric fitting (ablation)Closest ultrametric · Semi-supervised clusteringclassification accuracyImproved
Replace hard node cardinality with a differentiable soft-cardinal measure (ablation)Dasgupta cost · Hierarchical clusteringclassification accuracyNo clear effect

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