Research map / Learning theory and algorithms / Sample complexity
Efficient List-Decodable Regression using Batches
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 batches of size n rather than single samples | List-decodable linear regression · List-decodable linear regression | estimation error: For n = \tilde\Omega(1/\alpha), the estimation error is \tilde\cO(\sigma/\sqrt{n\alpha}); for n = 1, no algorithm ... ca | Helped |
| Average sample gradients into batch gradients | List-decodable linear regression · List-decodable linear regression | gradient covariance: reduces the co-variance by a factor n | Helped |
| Clip batch gradients using an adaptively selected clipping parameter | MainAlgorithm · Good batches | good-batch sample complexity: \tilde O_{n,\alpha}(d); unclipped gradients ... would instead require \Omega(d^2) samples | Helped |
Closest papers by meaning
- Batch List-Decodable Linear Regression via Higher Moments (ICML 2025 · similarity 0.94)
- Linear Regression using Heterogeneous Data Batches (NeurIPS 2024 · similarity 0.87)
- Robust Sparse Regression with Non-Isotropic Designs (NeurIPS 2024 · similarity 0.83)
- Information-Computation Tradeoffs for Noiseless Linear Regression with Oblivious Contamination (NeurIPS 2025 · similarity 0.83)
- Robust Mixture Learning when Outliers Overwhelm Small Groups (NeurIPS 2024 · similarity 0.83)
- The Generative Leap: Tight Sample Complexity for Efficiently Learning Gaussian Multi-Index Models (NeurIPS 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.