AI Paper Atlas

Research map / Learning theory and algorithms / Sample complexity

Two is Better Than One: Regularized Shrinkage of Large Minimum Variance Portfolios

Taras Bodnar, Nestor Parolya, Erik Thorsen

JMLR 2024 · Learning theory and algorithms › Sample complexity · approach: Optimal mean estimation and subsampling

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 double shrinkage instead of BPS linear shrinkage (ec target)GMV portfolio · S&P500, n=250, p=260out-of-sample std dev: 0.03912 -> 0.01104Improved
use double shrinkage instead of traditional GMVGMV portfolio · S&P500, n=500, p=431out-of-sample std dev: 0.02591 -> 0.01049Improved
use double shrinkage instead of LW2020 nonlinear shrinkageGMV portfolio · S&P500, n=250, p=260out-of-sample std dev: 0.01165 -> 0.01104Improved
use double shrinkage instead of LW2020GMV portfolio · S&P500, n=500, p=431out-of-sample std dev: 0.01099 -> 0.01049Improved
use double shrinkage instead of LW2020 for Sharpe ratioGMV portfolio · S&P500, n=250, p=260Sharpe ratio: 0.047 -> 0.036Hurt
use equally weighted target instead of equal correlation targetDouble shrinkage · S&P500, n=250, p=260turnover: 69.74 -> 3.36Improved
use equal correlation instead of equally weighted targetDouble shrinkage · S&P500, n=250, p=260out-of-sample std dev: 0.01129 -> 0.01104Improved
use double shrinkage instead of BPS in index trackingGMV portfolio · S&P500 index tracking, n=240turnover: 2555.37 -> 185.93Improved
use double shrinkage instead of BPS in index trackingGMV portfolio · S&P500 index tracking, n=240out-of-sample std dev: 0.00834 -> 0.00913Hurt
use double shrinkage instead of BPS in index trackingGMV portfolio · S&P500 index tracking, n=720Sharpe ratio: 0.028 -> 0.047Improved
increase window from n=250 to n=500Double shrinkage ec · S&P500, p=431out-of-sample std dev: 0.01088 -> 0.01049Improved
increase window from n=240 to n=720Double shrinkage · S&P500 index trackingturnover: 185.93 -> 143.85Improved

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