Abstract. This paper presents a new approach to online multi-class learning with bandit feedback. This algorithm, named PAB (Passive Aggressive in Bandit) is a variant of Online Passive-Aggressive Algorithm proposed by [2], the latter being an e↵ective framework for performing max-margin online learning. We analyze some of its operating principles, and show it to provide a good and scalable sol...

We study the problem of learning a latent variable model from a stream of data. Latent variable models are popular in practice because they can explain observed data in terms of unobserved concepts. These models have been traditionally studied in the offline setting. The online EM is arguably the most popular algorithm for learning latent variable models online. Although it is computationally e...

Kernel methods have been successfully applied to reinforcement learning problems to address some challenges such as high dimensional and continuous states, value function approximation and state transition probability modeling. In this paper, we develop an online policy search algorithm based on a recent state-of-the-art algorithm REPS-RKHS that uses conditional kernel embeddings. Our online al...

The issue of QoS (quality of service) provisioning for adaptive multimedia in wireless communication networks is considered. A reinforcement learning based online adaptive bandwidth allocation optimization algorithm is proposed. First, an event-driven stochastic switching model is introduced to formulate the adaptive bandwidth allocation problem as a constrained continuous-time Markov decision ...

Learning for maximizing AUC performance is an important research problem in Machine Learning and Artificial Intelligence. Unlike traditional batch learning methods for maximizing AUC which often suffer from poor scalability, recent years have witnessed some emerging studies that attempt to maximize AUC by single-pass online learning approaches. Despite their encouraging results reported, the ex...

We introduce a novel technique, which we call online-to-confidence-set conversion. The technique allows us to construct highprobability confidence sets for linear prediction with correlated inputs given the predictions of any algorithm (e.g., online LASSO, exponentiated gradient algorithm, online least-squares, p-norm algorithm) targeting online learning with linear predictors and the quadratic...

Online learning methods are typically faster and have a much smaller memory footprint than batch learning methods. However, in practice online learners frequently require multiple passes over the same training data in order to achieve accuracy comparable to batch learners. We investigate the problem of single-pass online learning, i.e., training only on a single pass over the data. We compare t...

Efficient online learning with pairwise loss functions is a crucial component in building largescale learning system that maximizes the area under the Receiver Operator Characteristic (ROC) curve. In this paper we investigate the generalization performance of online learning algorithms with pairwise loss functions. We show that the existing proof techniques for generalization bounds of online a...

Mobile learning (m-learning) is gaining popularity as the „anytime, anywhere‟ online learning channel. Academics and practitioners alike are showing interest in examining its ability to support online learning. However, prior studies have highlighted the challenges in promoting m-learning adoption. The extantm-learning literature has mainly focused on technology related factors to examine m-lea...

Bagging frequently improves the predictive performance of a model. An online version has recently been introduced, which attempts to gain the benefits of an online algorithm while approximating regular bagging. However, regular online bagging is an approximation to its batch counterpart and so is not lossless with respect to the bagging operation. By operating under the Bayesian paradigm, we in...