Research map / Learning theory and algorithms / Matrix and tensor methods
Sparse Parameter Recovery from Aggregated Data
Avradeep Bhowmik, Joydeep Ghosh, Oluwasanmi Koyejo
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 |
|---|---|---|---|
| increase number of datapoints used to compute group empirical means | sparse recovery from aggregated data · synthetic Gaussian and Bernoulli ensembles | probability of exact parameter recovery | Improved |
| noisy targets instead of noise-free targets | sparse recovery from aggregated data · synthetic Gaussian and Bernoulli ensembles | probability of exact parameter recovery | Mixed |
| increase number of datapoints per group | aggregated-data estimator · DE-SynPUF | l2 distance to full-data parameter | Improved |
| increase number of datapoints per group | aggregated-data estimator · TxID | support conflicts vs full-data LASSO | Improved |
| add second-order moments to first-order moments | aggregated-data estimator · theory (supplement) | estimation ease/accuracy | No clear effect |
Closest papers by meaning
- Learning from Aggregate responses: Instance Level versus Bag Level Loss Functions (ICLR 2024 · similarity 0.85)
- PriorBoost: An Adaptive Algorithm for Learning from Aggregate Responses (ICML 2024 · similarity 0.85)
- Minimal Variance Model Aggregation: A principled, non-intrusive, and versatile integration of black box models (ICLR 2025 · similarity 0.83)
- On the Recoverability of Causal Relations from Bulk Gene Expression Data (NeurIPS 2026 · similarity 0.82)
- Providing Fair Recourse over Plausible Groups (AAAI 2024 · similarity 0.82)
- Robust group and simultaneous inferences for high-dimensional single index model (NeurIPS 2024 · 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.
