Varieties of Regret in Online Prediction
نویسندگان
چکیده
We present a general framework for analyzing regret in the online prediction problem. We develop this from sets of linear transformations of strategies. We establish relationships among the varieties of regret and present a class of regret-matching algorithms. Finally we consider algorithms that exhibit the asymptotic no-regret property. Our main results are an analysis of observed regret in expectation and two regretmatching algorithms that exhibit no-observed-internal-regret in expectation.
منابع مشابه
Hierarchies of Relaxations for Online Prediction Problems with Evolving Constraints
We study online prediction where regret of the algorithm is measured against a benchmark defined via evolving constraints. This framework captures online prediction on graphs, as well as other prediction problems with combinatorial structure. A key aspect here is that finding the optimal benchmark predictor (even in hindsight, given all the data) might be computationally hard due to the combina...
متن کاملFollowing the Perturbed Leader for Online Structured Learning
We investigate a new Follow the Perturbed Leader (FTPL) algorithm for online structured prediction problems. We show a regret bound which is comparable to the state of the art of FTPL algorithms and is comparable with the best possible regret in some cases. To better understand FTPL algorithms for online structured learning, we present a lower bound on the regret for a large and natural class o...
متن کاملNewtron: an Efficient Bandit algorithm for Online Multiclass Prediction
We present an efficient algorithm for the problem of online multiclass prediction with bandit feedback in the fully adversarial setting. We measure its regret with respect to the log-loss defined in [AR09], which is parameterized by a scalar α. We prove that the regret of NEWTRON is O(log T ) when α is a constant that does not vary with horizon T , and at mostO(T ) if α is allowed to increase t...
متن کاملDistributed sequence prediction: A consensus+innovations approach
This paper focuses on the problem of distributed sequence prediction in a network of sparsely interconnected agents, where agents collaborate to achieve provably reasonable predictive performance. An expert assisted online learning algorithm in a distributed setup of the consensus+innovations form is proposed, in which the agents update their weights for the experts’ predictions by simultaneous...
متن کاملOnline Convex Optimization Using Predictions
Making use of predictions is a crucial, but under-explored, area of online algorithms. This paper studies a class of online optimization problems where we have external noisy predictions available. We propose a stochastic prediction error model that generalizes prior models in the learning and stochastic control communities, incorporates correlation among prediction errors, and captures the fac...
متن کامل