AI Paper Atlas

Research map / Learning theory and algorithms / Kernels and regression theory

Meta-analysis of heterogeneous data: integrative sparse regression in high-dimensions

Subha Maity, Yuekai Sun, Moulinath Banerjee

JMLR 2022 · Learning theory and algorithms › Kernels and regression theory · approach: High-dimensional linear regression theory

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 changedWhereMeasuredEffect
Use MrLasso global parameter instead of Mean, Median, Huber and square/absolute trade-offglobal estimators · Simulated linear model, varying n_kl2 estimation errorImproved
Increase number of datasets mall global estimators · Simulated linear model (n_k=200, s=5)l2 estimation errorImproved
Increase sparsity s of the global parameter (denser) (ablation)MrLasso vs others · Simulated linear model (n_k=200, m=5)l2 estimation error gapHurt
Vary eta within a reasonable range (ablation)MrLasso · Simulated linear model (n_k=200, s=5, m=5)l2 estimation errorNo clear effect
Use MrLasso instead of Mean and global lassoglobal estimators · CCLE drug response on rare cancer types (PD-0325901, Paclitaxel, Topotecan)prediction MSEImproved
Use MrLasso instead of Mean when effect sizes differ across cancer typesMean · CCLE drug responseprediction MSEImproved
Use MrLasso instead of other global estimatorsglobal estimators · Simulated test data without outlier local coefficientsprediction errorImproved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy