3 papers
stat.ML2026
Distribution-Free Confidence Ellipsoids for Ridge Regression with PAC Bounds
Szabolcs Szentpéteri, Balázs Csanád Csáji
Linearly parametrized models are widely used in control and signal processing, with the least-squares (LS) estimate being the archetypical solution. When the input is insufficientl…
eess.SP2025
Finite Sample Analysis of Distribution-Free Confidence Ellipsoids for Linear Regression
Szabolcs Szentpéteri, Balázs Csanád Csáji
The least squares (LS) estimate is the archetypical solution of linear regression problems. The asymptotic Gaussianity of the scaled LS error is often used to construct approximate…
stat.ML2024
Sample Complexity of the Sign-Perturbed Sums Method
Szabolcs Szentpéteri, Balázs Csanád Csáji
We study the sample complexity of the Sign-Perturbed Sums (SPS) method, which constructs exact, non-asymptotic confidence regions for the true system parameters under mild statisti…