Research map / Optimization / Distributed and compressed
Rate-Distortion Theoretic Bounds on Generalization Error for Distributed Learning
Milad Sefidgaran, Romain Chor, Abdellatif Zaidi
Read the paperCheck your idea against 137,217 papers
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 |
|---|---|---|---|
| Use client-wise rate-distortion bounds that compress one local algorithm while keeping the other clients' models uncompressed | Distributed learning generalization bounds · Distributed learning | upper bound on generalization error | Improved |
| Increase the number of clients | Distributed SVM · Distributed SVM | expected generalization error: decreases with K with a rate of log(K)/K | Improved |
| Increase the number of clients | Federated SGLD · Federated SGLD | expected generalization error | Improved |
| Increase the number of clients | Distributed SVM · MNIST digit 1 versus 6 | generalization error | Improved |
| Increase the number of clients | Distributed SVM · Distributed versus centralized SVM | population risk | Mixed |
| Increase the number of clients | Distributed SVM · Distributed SVM | difference between aggregated-model and average local empirical risks | Hurt |
Closest papers by meaning
- Lessons from Generalization Error Analysis of Federated Learning: You May Communicate Less Often! (ICML 2024 · similarity 0.90)
- Generalization Bounds for Federated Learning: Fast Rates, Unparticipating Clients and Unbounded Losses (ICLR 2023 · similarity 0.89)
- Slicing Mutual Information Generalization Bounds for Neural Networks (ICML 2024 · similarity 0.87)
- Exactly Tight Information-theoretic Generalization Bounds via Binary Jensen-Shannon Divergence (ICML 2025 · similarity 0.86)
- Stability and Generalization Analysis of Decentralized SGD: Sharper Bounds Beyond Lipschitzness and Smoothness (ICML 2025 · similarity 0.86)
- Stability and Generalization of Asynchronous SGD: Sharper Bounds Beyond Lipschitz and Smoothness (NeurIPS 2024 · similarity 0.86)
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.
