IDEAS/STAT Optimization Seminar: “Gradient Equilibrium in Online Learning”
Amy Gutmann Hall, Room 414 3333 Chestnut Street, Philadelphia, United StatesWe present a new perspective on online learning that we refer to as gradient equilibrium: a sequence of iterates achieves gradient equilibrium if the average of gradients of losses along the sequence converges to zero. In general, this condition is not implied by, nor implies, sublinear regret. It turns out that gradient equilibrium is achievable […]