Logistic regression with total variation regularization

Abstract

We study logistic regression with total variation penalty on the canonical parameter and show that the resulting estimator satisfies a sharp oracle inequality: the excess risk of the estimator is adaptive to the number of jumps of the underlying signal or an approximation thereof. In particular when there are finitely many jumps, and jumps up are sufficiently separated from jumps down, then the estimator converges with a parametric rate up to a logarithmic term $\log n/n$, provided the tuning parameter is chosen appropriately of order $1/\sqrt{n}$. Our results extend earlier results for quadratic loss to logistic loss. We do not assume any a priori known bounds on the canonical parameter but instead only make use of the local curvature of the theoretical risk.

arXiv comment23 pages

References in corpus (4)

• Total Variation Classes Beyond 1d: Minimax Rates, and the Limitations of Linear Smoothers
• The DFS Fused Lasso: Linear-Time Denoising over General Graphs
• Bayesian Fused Lasso regression for dynamic binary networks
• Multivariate extensions of isotonic regression and total variation denoising via entire monotonicity and Hardy-Krause variation

Cited by in corpus (1)

• Exponential Family Trend Filtering on Lattices