Research map / Probabilistic and scientific modeling / Molecules and proteins
Geometry Based Data Generation
Ofir Lindenbaum, Jay Stanley, Guy Wolf, Smita Krishnaswamy
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Apply SUGAR augmentation before k-NN classification | k-NN · 60 imbalanced datasets | ACP: 0.67 -> 0.78 | Improved |
| Apply SUGAR augmentation before k-NN classification | k-NN · 60 imbalanced datasets | ACR: 0.64 -> 0.77 | Improved |
| Apply SUGAR augmentation before kernel SVM classification | kernel SVM · 60 imbalanced datasets | ACR: 0.78 -> 0.84 | Improved |
| Apply SUGAR augmentation before kernel SVM classification | kernel SVM · 60 imbalanced datasets | ACP: 0.77 -> 0.77 | No clear effect |
| Apply SUGAR to unevenly sampled manifold data | Swiss roll · Swiss roll | degree variance: 0.19 -> 0.09 | Improved |
| Apply SUGAR to unevenly sampled manifold data | Stanford Bunny · Stanford Bunny | degree variance: 0.24 -> 0.019 | Improved |
| Use SUGAR to augment density-biased data before clustering | k-means · 115 imbalanced datasets | Rand Index | Improved |
| Generate manifold samples using SUGAR rather than a VAE | MNIST rotated handwritten 6 · MNIST rotated handwritten 6 | coverage of sparse manifold angles | Improved |
Closest papers by meaning
- Enforcing Latent Euclidean Geometry in Single-Cell VAEs for Manifold Interpolation (ICML 2025 · similarity 0.86)
- Rectifying Categorical Flows on Statistical Manifolds for One-Step Generation (NeurIPS 2026 · similarity 0.85)
- What Secrets Do Your Manifolds Hold? Understanding the Local Geometry of Generative Models (ICLR 2025 · similarity 0.85)
- A Geometric Framework for Understanding Memorization in Generative Models (ICLR 2025 · similarity 0.84)
- Categorical Flow Matching on Statistical Manifolds (NeurIPS 2024 · similarity 0.84)
- Recovering Manifold Structure Using Ollivier Ricci Curvature (ICLR 2025 · similarity 0.83)
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.
