COMS 4772 Fall 2014
نویسنده
چکیده
Consider a scenario where you have to repeatedly make a decision on some important matter, and each decision has some quantifiable consequence which you would like to optimize. Formally, suppose there are T rounds of this decision-making game. In each round, you (the “learner”) must choose between two actions, {−1,+1}. Your adversary (Nature) picks one of the actions for that round to be correct, and the other action is a mistake. You would like to minimize the number of mistakes you make over the T rounds. So far, this setting is impossibly abstract. Whatever actions you choose, they could all be correct, or they could all be mistakes, . . . Let’s make things more tractable. Suppose that before choosing your action in each round, you receive a recommended action from each of N experts. Why should this help? Our hope is that some (maybe just one!) of the experts make good recommendations over the T rounds—we will formalize this shortly. If this is the case, we can then try to just do (almost) as well as the best of these experts.
منابع مشابه
COMS 4772 Fall 2013 Mixture models
The mixing distribution is also sometimes called the mixing weights. There are a number of statistical estimation / unsupervised learning tasks associated with mixture models. Three such tasks are as follows (assuming an iid sample from some m? ∈M is given): 1. Density estimation: Here we assume that each distribution in M has a density. The task is to pick m̂ ∈ M such that m̂ is close to m? unde...
متن کاملCOMS 4772 Fall 2014 Experts , bandits , and games
Warning: notes are incomplete and unchecked for correctness 1 Prediction with expert advice Algorithm 1 Protocol for online decision-making with expert advice 1: for t = 1 to T do 2: Receive experts' recommendations: b t,i ∈ {±1} for i ∈ [N ]. Recall that the " Follow the weighted majority " algorithm has the following guarantee. Letting M T denote the number of mistakes made by the learner in ...
متن کاملClustering Daniel Hsu COMS 4772
Let (X , ρ) be a metric space. Goal: given a set S ⊂ X , find a set C ⊂ X (" centers ") that has small cardinality, and " represents " the set S well (as measured by a cost function).
متن کاملControl of Competence for DNA Transformation in Streptococcus suis by Genetically Transferable Pherotypes
Here we show that S. suis, a major bacterial pathogen of pigs and emerging pathogen in humans responds to a peptide pheromone by developing competence for DNA transformation. This species does not fall within any of the phylogenetic clusters of streptococci previously shown to regulate competence via peptide pheromones suggesting that more species of streptococci may be naturally competent. Ind...
متن کامل