On-Line Learning Algorithms for Path Experts with Non-Additive Losses
نویسندگان
چکیده
We consider two broad families of non-additive loss functions covering a large number of applications: rational losses and tropical losses. We give new algorithms extending the Followthe-Perturbed-Leader (FPL) algorithm to both of these families of loss functions and similarly give new algorithms extending the Randomized Weighted Majority (RWM) algorithm to both of these families. We prove that the time complexity of our extensions to rational losses of both FPL and RWM is polynomial and present regret bounds for both. We further show that these algorithms can play a critical role in improving performance in applications such as structured prediction.
منابع مشابه
AF: Small: Collaborative Research: On-Line Learning Algorithms for Path Experts with Non-Additive Losses
On-line learning algorithms are increasingly adopted as the key solution to modern learning applications with very large data sets of several hundred million or billion points. These algorithms process one sample at a time with an update per iteration that is often computationally cheap and easy to implement. As a result, they are substantially more efficient both in time and space than standar...
متن کاملFollow the Leader with Dropout Perturbations
We consider online prediction with expert advice. Over the course of many trials, the goal of the learning algorithm is to achieve small additional loss (i.e. regret) compared to the loss of the best from a set of K experts. The two most popular algorithms are Hedge/Weighted Majority and Follow the Perturbed Leader (FPL). The latter algorithm first perturbs the loss of each expert by independen...
متن کاملOnline Multi-task Learning with Hard Constraints
We discuss multi-task online learning when a decision maker has to deal simultaneously with M tasks. The tasks are related, which is modeled by imposing that the M–tuple of actions taken by the decision maker needs to satisfy certain constraints. We give natural examples of such restrictions and then discuss a general class of tractable constraints, for which we introduce computationally effici...
متن کاملOnline Learning of Combinatorial Objects via Extended Formulation
The standard on-line learning techniques for combinatorial objects perform multiplicative updates followed by projections into the convex hull of all the objects. However, this framework can be expensive if the convex hull contains many facets. For example, the convex hull of n-symbol Huffman trees is known to have exponentially many facets (Maurras et al., 2010). We get around this problem by ...
متن کاملOpen Problem: Shifting Experts on Easy Data
A number of online algorithms have been developed that have small additional loss (regret) compared to the best “shifting expert”. In this model, there is a set of experts and the comparator is the best partition of the trial sequence into a small number of segments, where the expert of smallest loss is chosen in each segment. The regret is typically defined for worst-case data / loss sequences...
متن کامل