Logarithmic Regret for parameter-free Online Logistic Regression

02/26/2019
by   Joseph De Vilmarest, et al.
0

We consider online optimization procedures in the context of logistic regression, focusing on the Extended Kalman Filter (EKF). We introduce a second-order algorithm close to the EKF, named Semi-Online Step (SOS), for which we prove a O(log(n)) regret in the adversarial setting, paving the way to similar results for the EKF. This regret bound on SOS is the first for such parameter-free algorithm in the adversarial logistic regression. We prove for the EKF in constant dynamics a O(log(n)) regret in expectation and in the well-specified logistic regression model.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/18/2020

Efficient improper learning for online logistic regression

We consider the setting of online logistic regression and consider the r...
research
02/07/2020

Logistic Regression Regret: What's the Catch?

We address the problem of the achievable regret rates with online logist...
research
10/08/2021

Mixability made efficient: Fast online multiclass logistic regression

Mixability has been shown to be a powerful tool to obtain algorithms wit...
research
03/31/2023

Almost Linear Constant-Factor Sketching for ℓ_1 and Logistic Regression

We improve upon previous oblivious sketching and turnstile streaming res...
research
04/27/2022

Asymptotic Inference for Infinitely Imbalanced Logistic Regression

In this paper we extend the work of Owen (2007) by deriving a second ord...
research
02/24/2022

Solving optimization problems with Blackwell approachability

We introduce the Conic Blackwell Algorithm^+ (CBA^+) regret minimizer, a...

Please sign up or login with your details

Forgot password? Click here to reset