Research map / Learning theory and algorithms / Combinatorial and search optimization
Neural Fisher Discriminant Analysis: Optimal Neural Network Embeddings in Polynomial Time
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Replace linear FLDA projection with a two-layer ReLU NFDA embedding (feature lifting plus FLDA on lifted data) | Two spirals dataset (binary, 1-D projection) · Two spirals dataset | class separation of projected histograms (qualitative) | Helped |
| Increase regularization coefficient beta in the NFDA linear system (ReLU, two spirals) (ablation) | NFDA decision boundary · Two spirals dataset | decision boundary noise (qualitative) | Helped |
| Replace linear FLDA with NFDA (ReLU, P'=20 lifted patterns) for 10-class embedding | MNIST 9-dimensional embedding · MNIST (n=60000) | t-SNE class separation (qualitative) | Helped |
| Replace linear FLDA with NFDA (ReLU, P'=15) on face images, producing more diverse discriminative projection directions | Yale Face projection directions · Yale Face (5 subjects, 165 images) | visual diversity of projection directions (qualitative) | Helped |
Closest papers by meaning
- Trace Ratio Optimization With Feature Correlation Mining for Multiclass Discriminant Analysis (AAAI 2018 · similarity 0.85)
- Relative Fisher Information and Natural Gradient for Learning Large Modular Models (ICML 2017 · similarity 0.84)
- Trade-Offs of Diagonal Fisher Information Matrix Estimators (NeurIPS 2024 · similarity 0.84)
- Scalable Kronecker-Factored Fisher Approximation for Neural Network Parameter Sensitivity (ICML 2026 · similarity 0.84)
- Fishers for Free? Approximating the Fisher Information Matrix by Recycling the Squared Gradient Accumulator (ICML 2025 · similarity 0.83)
- Training-free Neural Architecture Search through Variance of Knowledge of Deep Network Weights (CVPR 2025 · similarity 0.82)
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.