# Efficient improper learning for online logistic regression

18 Mar 2020Rémi JézéquelPierre GaillardAlessandro Rudi

We consider the setting of online logistic regression and consider the regret with respect to the 2-ball of radius B. It is known (see [Hazan et al., 2014]) that any proper algorithm which has logarithmic regret in the number of samples (denoted n) necessarily suffers an exponential multiplicative constant in B... (read more)

PDF Abstract