AI Paper Atlas

Research map / Learning theory and algorithms / Matrix and tensor methods

Fast Projection onto the Capped Simplex with Applications to Sparse Regression in Bioinformatics

Andersen Ang, Jianzhu Ma, Nianjun Liu, Kun Huang, Yijie Wang

NeurIPS 2021 · Learning theory and algorithms › Matrix and tensor methods · approach: Sparse regression with guarantees

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
Newton projection instead of Gurobicapped simplex projection · n=1e6runtime (s): 2.8229 -> 0.4723Improved
Newton projection instead of Gurobicapped simplex projection · n=1e7runtime (s): 32.26 -> 4.2067Improved
Newton projection instead of Gurobicapped simplex projection · n=1e8runtime (s): 14.925Improved
Newton projection instead of C++ sorting-based methodcapped simplex projection · n=1e5runtime (s): 10.3985 -> 0.0406Improved
Newton projection instead of C++ sorting-based methodcapped simplex projection · n=50runtime (s): 0.00003 -> 0.00013Hurt
Increase input range alpha from 1 to 1000 (ablation)Newton projection · n=1e5runtimeNo clear effect
Very large input bound alpha (about a million)Newton projection · bounded-input assumptionruntimeHurt
Increase n from 1e4 to 1e8 (ablation)Newton projection · k=100iterations T: 6.2 -> 13No clear effect
Increase k from 10 to 1e5 (ablation)Newton projection · n=1e6iterations T: 11.4 -> 5.1Improved
Proposed projection instead of Gurobi inside PQNPQN on P_BR · simulated sparse regressionAccNo clear effect
Proposed projection instead of Gurobi inside PQNPQN on P_BR · GWAS chromosomes 20, 5, 2computational timeImproved
PQN solver instead of SS subgradient methodP_BR · simulated sparse regressionobjective and AccImproved

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