Research map / Learning theory and algorithms / Kernels and regression theory
Anonymous Learning via Look-Alike Clustering: A Precise Analysis of Model Generalization
Adel Javanmard, Vahab Mirrokni
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 |
|---|---|---|---|
| replace full-feature min-norm estimator with look-alike clustering estimator at low SNR | look-alike estimator · linear GMM model | risk | Improved |
| increase SNR (r_s/sigma) | look-alike estimator gain over min-norm · linear model | log gain Delta | Hurt |
| increase alignment rho of model with cluster centers | look-alike estimator · linear model | gain Delta | Improved |
| increase non-sensitive signal norm r_ns | look-alike estimator · overparametrized linear model | gain Delta | Improved |
| increase cluster center norm mu | look-alike estimator · linear model | log gain Delta | Hurt |
| use look-alike modeling with GLM logit link | look-alike estimator · non-linear GLM, test set 50K | gain log Delta | Improved |
| compare asymptotic theory to simulation | risk characterization · GMM d=500, p=200, k=3 | risk | Improved |
Closest papers by meaning
- It's My Data Too: Private ML for Datasets with Multi-User Training Examples (ICML 2025 · similarity 0.86)
- Making Old Things New: A Unified Algorithm for Differentially Private Clustering (ICML 2024 · similarity 0.86)
- Private Adaptive Covariance Estimation via Gaussian Graphical Models (NeurIPS 2026 · similarity 0.85)
- Leveraging Randomness in Model and Data Partitioning for Privacy Amplification (ICML 2025 · similarity 0.85)
- Interaction-Aware Gaussian Weighting for Clustered Federated Learning (ICML 2025 · similarity 0.85)
- Efficiently Computing Similarities to Private Datasets (ICLR 2024 · similarity 0.85)
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.
