AI Paper Atlas

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

No Pressure! Addressing the Problem of Local Minima in Manifold Learning Algorithms

Max Vladymyrov

NeurIPS 2019 · Learning theory and algorithms › Prediction and decision losses · approach: Loss landscape analysis · 1 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
Add pressured-points optimization from random initializationElastic Embedding with Spectral Direction · COIL-20 (10 objects)objective function value: 3.84 ± 0.18 -> 3.6 ± 0.14Improved
Add pressured-points optimization after SD convergenceElastic Embedding with Spectral Direction · COIL-20 (10 objects)objective function value: 3.84 ± 0.18 -> 3.61 ± 0.19Improved
Add pressured-points optimization from random initializationSNE with Spectral Direction · COIL-20 (10 objects)objective function value: 11.07 ± 0.03 -> 11.03 ± 0.02Improved
Add pressured-points optimization after SD convergenceSNE with Spectral Direction · COIL-20 (10 objects)objective function value: 11.07 ± 0.03 -> 11.05 ± 0.03Improved
Add pressured-points optimization after SDElastic Embedding · COIL-20objective function value: 3.68 -> 3.3Improved
Apply pressured-points optimization to the long-tailed kernelst-SNE and UMAP · Experiments described in the paperobjective function value decreaseNo clear effect
Use pressured-points optimizationElastic Embedding with FMM approximation (p=5) · MNISTobjective function valueImproved
Use pressured-points optimization after SDElastic Embedding · word2vec vectors from Google News (5,000 words)objective function valueImproved

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