AI Paper Atlas

Research map / Learning theory and algorithms / Sample complexity

SURF: A Simple, Universal, Robust, Fast Distribution Learning Algorithm

Yi Hao, Ayush Jain, Alon Orlitsky, Vaishakh Ravindrakumar

NeurIPS 2020 · Learning theory and algorithms › Sample complexity · approach: Sample complexity of learning distributions · 1 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
Use SURF (no t needed) instead of ADLS with a misspecified number of pieces tpiecewise-linear estimator · Beta, Gamma, Gaussian mixture syntheticl1 errorImproved
Use ADLS with t=5, roughly the number of pieces SURF outputsADLS · Beta, Gamma, Gaussian mixture syntheticl1 errorNo clear effect
Increase number of samples nSURF d=1,2,3 · Beta mixtures f1,f2,f3l1 errorImproved
Increase polynomial degree d from 1 to 3 (ablation)SURF · Beta mixtures f1,f2,f3l1 error across distributionsMixed
Increase n from 1024 to 65536SURF d=2 · 0.3Beta(3,10)+0.7Beta(17,4)l1 and pointwise convergence: n=1024,4096,16384, 65536Improved
Use SURF instead of MATLAB fitdist Epanechnikov and Gaussian kernel estimatorsSURF · 1994 US census salaries and sensorless drive datatest perplexityImproved

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