Scalable Cox Regression via Grouped Risk Sets and Sharper LogSumExp Rates

Excerpt

arXiv:2609.40120v1 Announce Type: new Abstract: Motivated by the computational challenges of large-scale Cox regression, we study stochastic minimization of LogSumExp objectives over large sets. Mini-batch normalizer estimates generally yield biased gradients. We instead use a softplus surrogate that introduces one auxiliary scalar per normalizer and admits unbiased single-sample gradients. For smooth convex LogSumExp objectives, we prove an $O(T^{-1/2})$ averaged objective bound, improving the