We examine gradient descent on unregularised logistic regression problems, with homogeneous linear predictors on linearly separable datasets. We show the predictor converges to the direction of the max-margin (hard margin SVM) solution.

I will complete a couple of proofs from last week's student seminar on determinantal complexity. I will recall the required background for the proofs. On the way, we will learn a cute linear-algebraic fact.

Fair division of a set of resources among several agents is a commonly occurring problem in many real-world settings.

Hyperbolicity cones are convex semialgebraic sets generalizing both polyhedral and spectrahedral cones, the latter forming the basic geometric sets from linear and semidefinite programming.