Research map / Probabilistic and scientific modeling / Variational and generative sampling
Relevant sparse codes with variational information bottleneck
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 gaussian response marginal with student-t (sparse) marginal in IB | linear IB on denoising bars task · 9x9 bar patches denoising | relevant information I(R;Y): greater over a range of bottleneck strengths | Helped |
| Replace gaussian response marginal with student-t (sparse) marginal in kernel IB | kernel IB on artificial occlusion task · occlusion task | performance on occlusion reconstruction: small but significant improvement | Helped |
| Replace gaussian response marginal with student-t (sparse) marginal in kernel IB | kernel IB on USPS handwritten digit occlusion · USPS occlusion | response distribution heavy-tailedness and decoding filters | No clear effect |
| Use a null model with responses equal to input plus white noise instead of IB encoder (ablation) | linear gaussian IB · denoising bars task | relevant information I(R;Y) | No clear effect |
Closest papers by meaning
- Caveats for information bottleneck in deterministic scenarios (ICLR 2019 · similarity 0.88)
- Perturbation Theory for the Information Bottleneck (NeurIPS 2021 · similarity 0.87)
- Structured IB: Improving Information Bottleneck with Structured Feature Learning (AAAI 2025 · similarity 0.85)
- Cauchy-Schwarz Divergence Information Bottleneck for Regression (ICLR 2024 · similarity 0.85)
- Information Bottleneck Analysis of Deep Neural Networks via Lossy Compression (ICLR 2024 · similarity 0.84)
- Sparse Variational Student-t Processes (AAAI 2024 · similarity 0.84)
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.