Learning a Label-Noise Robust Logistic Regression: Analysis and Experiments

Label-noise robust logistic regression (rLR) is an extension of logistic regression that includes a model of random mislabelling. This paper attempts a theoretical analysis of rLR. By decomposing and interpreting the gradient of the likelihood objective of rLR as employed in gradient ascent optimisation, we get insights into the ability of the rLR learning algorithm to counteract the negative effect of mislabelling as a result of an intrinsic re-weighting mechanism. We also give an upper-bound on the error of rLR using Rademacher complexities.