AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Enumerate Lasso Solutions for Feature Selection

Satoshi Hara, Takanori Maehara

AAAI 2017 · Label-efficient and robust learning › Recognition and long-tail · approach: Data augmentation and generalization bias · 45 citations (OpenAlex)

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
enumerate solutions beyond the Lasso optimum and pick later ones (k>30)Lasso · Thaliana gene expression (FLC)test mean square error: error ratio within ± 2% of optimum; solutions after 30 enumerations smallerImproved
enumerated solution beta(34) instead of Lasso optimumLasso · Thaliana gene expression (FLC)number of non-zero coefficients: 45 -> 39Improved
enumerated top-50 solutions rather than only optimumLasso · Thaliana gene expression (FLC)objective function value: up to 0.05% increaseHurt
enumerated top-50 solutions rather than only optimumLasso logistic regression · 20 Newsgroupstest error: up to 4% increaseHurt
lower regularization rho (below 0.01n) (ablation)Lasso enumeration · Synthetic (p=10, n=100)number of solutions needed for exact support recoveryHurt
stronger feature collinearity (small alpha) (ablation)Lasso enumeration · Synthetic (p=10, n=100)number of solutions needed for exact support recoveryHurt

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