Hedge algorithm and Dual Averaging schemes
نویسندگان
چکیده
We show that the Hedge algorithm, a method that is widely used in Machine Learning, can be interpreted as a particular instance of Dual Averaging schemes, which have recently been introduced by Nesterov for regret minimization. Based on this interpretation, we establish three alternative methods of the Hedge algorithm: one in the form of the original method, but with optimal parameters, one that requires less a priori information, and one that is better adapted to the context of the Hedge algorithm. All our modified methods have convergence results that are better or at least as good as the performance guarantees of the vanilla method. In numerical experiments, our methods significantly outperform the original scheme.
منابع مشابه
Hedge Algorithm and Subgradient Methods
We show that the Hedge Algorithm, a method widely used in Machine Learning, can be interpreted as a particular subgradient algorithm for minimizing a well-chosen convex function, namely a Mirror Descent Scheme. Using this reformulation, we can improve slightly the worstcase convergence guarantees of the Hedge Algorithm. Recently, Nesterov has introduced the class of Primal-Dual Subgradient Algo...
متن کاملThe Hedge Algorithm on a Continuum
We consider an online optimization problem on a compact subset S ⊂ R (not necessarily convex), in which a decision maker chooses, at each iteration t, a probability distribution x over S, and seeks to minimize a cumulative expected loss, ∑T t=1 Es∼x(t) [`(s)], where ` is a Lipschitz loss function revealed at the end of iteration t. Building on previous work, we propose a generalized Hedge algor...
متن کاملA unified framework for primal/dual quadrilateral subdivision schemes
Quadrilateral subdivision schemes come in primal and dual varieties, splitting faces or respectively vertices. The scheme of Catmull-Clark is an example of the former, while the Doo-Sabin scheme exemplifies the latter. In this paper we consider the construction of an increasing sequence of alternating primal/dual quadrilateral subdivision schemes based on a simple averaging approach. Beginning ...
متن کاملSelection of Intermodal Conductivity Averaging Scheme for Unsaturated Flow in Homogeneous Media
The nonlinear solvers in numerical solution of water flow in variably saturated soils are prone to convergence difficulties. Many aspects can give rise to such difficulties, like very dry initial conditions, a steep pressure gradient and great variation of hydraulic conductivity occur across the wetting front during the infiltration of water. So, the averaging method applied to compute hydraul...
متن کاملRecovery of Primal Solution in Dual Subgradient Schemes
In this thesis, we study primal solutions for general optimization problems. In particular, we employ the subgradient method to solve the Lagrangian dual of a convex constrained problem, and use a primal-averaging scheme to obtain near-optimal and near-feasible primal solutions. We numerically evaluate the performance of the scheme in the framework of Network Utility Maximization (NUM), which h...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
- Math. Meth. of OR
دوره 77 شماره
صفحات -
تاریخ انتشار 2013