Parameter-Free Convex Learning through Coin Betting
نویسندگان
چکیده
We present a new parameter-free algorithm for online linear optimization over any Hilbert space. It is theoretically optimal, with regret guarantees as good as with the best possible learning rate. The algorithm is simple and easy to implement. The analysis is given via the adversarial coin-betting game, Kelly betting and the Krichevsky-Trofimov estimator. Applications to obtain parameter-free convex optimization and machine learning algorithms are shown.
منابع مشابه
Coin Betting and Parameter-Free Online Learning
In the recent years, a number of parameter-free algorithms have been developed for online linear optimization over Hilbert spaces and for learning with expert advice. These algorithms achieve optimal regret bounds that depend on the unknown competitors, without having to tune the learning rates with oracle choices. We present a new intuitive framework to design parameter-free algorithms based o...
متن کاملImproved Strongly Adaptive Online Learning using Coin Betting
This paper describes a new parameter-free online learning algorithm for changing environments. In comparing against algorithms with the same time complexity as ours, we obtain a strongly adaptive regret bound that is a factor of at least log(T ) better, where T is the time horizon. Empirical results show that our algorithm outperforms state-of-theart methods in learning with expert advice and...
متن کاملOnline Learning for Changing Environments using Coin Betting
A key challenge in online learning is that classical algorithms can be slow to adapt to changing environments. Recent studies have proposed “meta” algorithms that convert any online learning algorithm to one that is adaptive to changing environments, where the adaptivity is analyzed in a quantity called the strongly-adaptive regret. This paper describes a new meta algorithm that has a strongly-...
متن کاملParameter-free online learning via model selection
We introduce an efficient algorithmic framework for model selection in online learning, also known as parameter-free online learning. Departing from previous work, which has focused on highly structured function classes such as nested balls in Hilbert space, we propose a generic meta-algorithm framework that achieves online model selection oracle inequalities under minimal structural assumption...
متن کاملPredicting the NFL
As the most popular sports league in the United States, the National Football League (NFL) draws wide popular interest and is the subject of a $3 billion legal betting market each year. In addition, with the current trend toward more liberal gambling laws it is likely that in the near future a portion of the the illegal betting market which is estimated to be at least an order of magnitude larg...
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:
دوره شماره
صفحات -
تاریخ انتشار 2016