Research map / Learning theory and algorithms / Prediction and decision losses
An Information-Theoretic Framework for Fast and Robust Unsupervised Learning via Neural Population Infomax
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 |
|---|---|---|---|
| Use Algorithm 1 or Algorithm 2 instead of IICA | Unsupervised learning on Olshausen natural-image patches · Olshausen natural images | training convergence rate | Helped |
| Use FICA instead of Algorithm 1 or Algorithm 2 | Unsupervised learning on Olshausen natural-image patches · Olshausen natural images | training convergence rate | No clear effect |
| Use FICA instead of Algorithm 1 or Algorithm 2 | Unsupervised learning on Olshausen natural-image patches · Olshausen natural images | coefficient entropy (CFE) | Hurt |
| Use SRBM instead of Algorithm 1 or Algorithm 2 | Unsupervised learning on Olshausen natural-image patches · Olshausen natural images | conditional entropy (CDE) | Hurt |
| Increase the sparsity-control constant (ablation) | SRBM · Olshausen natural images | conditional entropy (CDE): p=0.01 -> p=0.03 | Helped |
| Increase the sparsity-control constant (ablation) | SRBM · Olshausen natural images | Gabor-like filter learning: p=0.01 -> p=0.03 | Hurt |
Closest papers by meaning
- Efficient Distribution Matching of Representations via Noise-Injected Deep InfoMax (ICLR 2025 · similarity 0.84)
- A Global Geometric Analysis of Maximal Coding Rate Reduction (ICML 2024 · similarity 0.84)
- Information Bottleneck Analysis of Deep Neural Networks via Lossy Compression (ICLR 2024 · similarity 0.84)
- Sharp feature-learning transitions and Bayes-optimal neural scaling laws in extensive-width networks (NeurIPS 2026 · similarity 0.83)
- How Deep Networks Learn Sparse and Hierarchical Data: the Sparse Random Hierarchy Model (ICML 2024 · similarity 0.83)
- InfoNet: Neural Estimation of Mutual Information without Test-Time Optimization (ICML 2024 · 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.