Research map / Learning theory and algorithms / Kernels and regression theory
Perturbation Theory for the 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 |
|---|---|---|---|
| allow the perturbed encoder to use representation values outside the uninformative encoder's support | Information Bottleneck learning-onset perturbation theory · Synthetic joint distributions | critical trade-off parameter | Helped |
| restrict the perturbed encoder to the uninformative encoder's support (ablation) | Information Bottleneck learning-onset perturbation theory · Binary classification | critical trade-off parameter | Hurt |
| use the full perturbation theory, including representation values outside the uninformative encoder's support | Information Bottleneck learning-onset perturbation theory · Synthetic joint distribution | mutual information near learning onset | Helped |
| use a discrete representation rather than a continuous one | Information Bottleneck for joint Gaussian variables · Joint Gaussian variables | critical trade-off parameter | No clear effect |
| increase the noise level | Information Bottleneck learning onset for noisy functional relationships · Noisy functional relationships | first-order relevant information | Hurt |
| increase the noise level | Information Bottleneck learning onset for noisy functional relationships · Noisy functional relationships | critical trade-off parameter | Hurt |
Closest papers by meaning
- Caveats for information bottleneck in deterministic scenarios (ICLR 2019 · similarity 0.89)
- Relevant sparse codes with variational information bottleneck (NeurIPS 2016 · similarity 0.87)
- Information Bottleneck Analysis of Deep Neural Networks via Lossy Compression (ICLR 2024 · similarity 0.86)
- Latent Representation and Simulation of Markov Processes via Time-Lagged Information Bottleneck (ICLR 2024 · similarity 0.85)
- Cauchy-Schwarz Divergence Information Bottleneck for Regression (ICLR 2024 · similarity 0.85)
- Understanding and Leveraging the Learning Phases of Neural Networks (AAAI 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.