AI Paper Atlas

Research map / Optimization / Optimizers

Gradient Estimation with Simultaneous Perturbation and Compressive Sensing

Vivek S. Borkar, Vikranth R. Dwaracherla, Neeraja Sahasrabudhe

JMLR 2018 · Optimization › Optimizers · approach: Differentiating through embedded optimization

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 adaptive (few-iteration homotopy) l1-minimization inside gradient descent instead of full l1 solve each stepSP + compressive sensing gradient descent · sparse-gradient test function, n=25000time taken (s): 489 -> 39Improved
use adaptive l1-minimization instead of non-adaptiveSP + compressive sensing gradient descent · sparse-gradient test function, n=1000time taken (s): 50.572 -> 5.910Improved
use adaptive l1-minimization instead of non-adaptiveSP + compressive sensing gradient descent · sparse-gradient test function, n=10000time taken (s): 213.6 -> 30.4Improved
replace exact gradient with compressive-sensing estimated gradient (non-adaptive)gradient descent · sparse-gradient test function, n=10000time taken (s): 5873.8 -> 213.6Improved
replace exact gradient with compressive-sensing estimated gradient (non-adaptive)gradient descent · sparse-gradient test function, n=1000time taken (s): 171.150 -> 50.572Improved
use the proposed estimator instead of Sparse Gradient Learning for gradient descentgradient descent with estimated gradient · n=10000, s=100, m=500time taken (s): 993 -> 83Improved
add compressive sensing recovery on top of naive SP gradient estimate (ablation)SP gradient estimation · f(x)=x(1)^2+...+x(s)^2, sparse gradientpercentage gradient errorImproved
increase number of SP averaging iterations k (ablation)SP + compressive sensing gradient estimator · n=25000, m=50 sparse quadraticpercentage gradient errorImproved
increase sparsity s with fixed measurements m=50 (ablation)SP + compressive sensing gradient estimator · n=10000, m=50percentage gradient errorHurt
increase sparsity s (ablation)naive SP gradient estimate · sparse gradient test functionpercentage gradient 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