In online bandit learning, the learner aims to minimize a sequence of losses, while only observing the value of each loss at a single point. Although various algorithms and theories have been developed for online bandit learning, most of them are limited to convex losses. In this paper, we investigate the problem of online bandit learning with non-convex losses, and develop an efficient algorithm with formal theoretical guarantees. To be specific, we consider a class of losses which is a composition of a non-increasing scalar function and a linear function. This setting models a wide range of supervised learning applications such as online classification with a non-convex loss. Theoretical analysis shows that our algorithm achieves an O(poly(d)T2/3) regret bound when the variation of the loss function is small. To the best of our knowledge, this is the first work in online bandit learning that does not rely on convexity.

Subspace recovery from noisy or even corrupted data is critical for various applications in machine learning and data analysis. To detect outliers, Robust PCA (R PCA) via Outlier Pursuit was proposed and had found many successful applications. However, the current theoretical analysis on Outlier Pursuit only shows that it succeeds when the sparsity of the corruption matrix is of O(n/r), where n is the number of the samples and r is the rank of the intrinsic matrix which may be comparable to n. Moreover, the regularization parameter is suggested as 3/(7 squareroot gamma n}, where gamma is a parameter that is not known a priori. In this paper, with incoherence condition and proposed ambiguity condition we prove that Outlier Pursuit succeeds when the rank of the intrinsic matrix is of O(n log n) and the sparsity of the corruption matrix is of O(n). We further show that the orders of both bounds are tight. Thus R-PCA via Outlier Pursuit is able to recover intrinsic matrix of higher rank and identify much denser corruptions than what the existing results could predict. Moreover, we suggest that the regularization parameter be chosen as 1 squareroot{log n}, which is definite. Our analysis waives the necessity of tuning the regularization parameter and also significantly extends the working range of the Outlier Pursuit. Experiments on synthetic and real data verify our theories.

Learning an appropriate feature representation across source and target domains is one of the most effective solutions to domain adaptation problems. Conventional cross-domain feature learning methods rely on the Reproducing Kernel Hilbert Space (RKHS) induced by a single kernel. Recently, Multiple Kernel Learning (MKL), which bases classifiers on combinations of kernels, has shown improved performance in the tasks without distribution difference between domains. In this paper, we generalize the framework of MKL for cross-domain feature learning and propose a novel Transfer Feature Representation (TFR) algorithm. TFR learns a convex combination of multiple kernels and a linear transformation in a single optimization which integrates the minimization of distribution difference with the preservation of discriminating power across domains. As a result, standard machine learning models trained in the source domain can be reused for the target domain data. After rewritten into a differentiable formulation, TFR can be optimized by a reduced gradient method and reaches the convergence. Experiments in two real-world applications verify the effectiveness of our proposed method.

Hashing techniques have been widely applied for large scale similarity search problems due to the computational and memory efficiency.However, most existing hashing methods assume data examples are independently and identically distributed.But there often exists various additional dependency/structure information between data examplesin many real world applications. Ignoring this structure information may limit theperformance of existing hashing algorithms.This paper explores the research problemof learning to Hash on Structured Data (HSD) and formulates anovel framework that considers additional structure information.In particular, the hashing function is learned in a unified learning framework by simultaneously ensuring the structural consistency and preserving the similarities between data examples.An iterative gradient descent algorithm is designed as the optimization procedure. Furthermore, we improve the effectiveness of hashing function through orthogonal transformation by minimizing the quantization error.Experimentalresults on two datasets clearly demonstrate the advantages ofthe proposed method over several state-of-the-art hashing methods.

Active learning is a machine learning technique that trains a classifier after selecting a subset from an unlabeled dataset for labeling and using the selected data for training. Recently, batch mode active learning, which selects a batch of samples to label in parallel, has attracted a lot of attention. Its challenge lies in the choice of criteria used for guiding the search of the optimal batch. In this paper, we propose a novel approach to selecting the optimal batch of queries by minimizing the α-relative Pearson divergence (RPE) between the labeled and the original datasets. This particular divergence is chosen since it can distinguish the optimal batch more easily than other measures especially when available candidates are similar. The proposed objective is a min-max optimization problem, and it is difficult to solve due to the involvement of both minimization and maximization. We find that the objective has an equivalent convex form, and thus a global optimal solution can be obtained. Then the subgradient method can be applied to solve the simplified convex problem. Our empirical studies on UCI datasets demonstrate the effectiveness of the proposed approach compared with the state-of-the-art batch mode active learning methods.

The related problems of transfer learning and multitask learning have attracted significant attention, generating a rich literature of models and algorithms. Yet most existing approaches are studied in an offline fashion, implicitly assuming that data from different domains are given as a batch. Such an assumption is not valid in many real-world applications where data samples arrive sequentially, and one wants a good learner even from few examples. The goal of our work is to provide sound extensions to existing transfer and multitask learning algorithms such that they can be used in an anytime setting. More specifically, we propose two novel online boosting algorithms, one for transfer learning and one for multitask learning, both designed to leverage the knowledge of instances in other domains. The experimental results show state-of-the-art empirical performance on standard benchmarks, and we present results of using our methods for effectively detecting new seizures in patients with epilepsy from very few previous samples.

The traditional way of obtaining models from data, inductive learning, has proved itself both in theory and in many practical applications. However, in domains where data is difficult or expensive to obtain, e.g., medicine, deep transfer learning is a more promising technique. It circumvents the model acquisition difficulties caused by scarce data in a target domain by carrying over structural properties of a model learned in a source domain where training data is ample. Nonetheless, the lack of a principled view of transfer learning so far has limited its adoption. In this paper, we address this issue by regarding transfer learning as a process that biases learning in a target domain in favor of patterns useful in a source domain. Specifically, we consider a first-order logic model of the data as an instantiation of a set of second-order templates. Hence, the usefulness of a model is partly determined by the learner's prior distribution over these template sets. The main insight of our work is that transferring knowledge amounts to acquiring a posterior over the second-order template sets by learning in the source domain and using this posterior when learning in the target setting. Our experimental evaluation demonstrates our approach to outperform the existing transfer learning techniques in terms of accuracy and runtime.

We present a probabilistic model for tensor decomposition where one or more tensor modes may have side-information about the mode entities in form of their features and/or their adjacency network. We consider a Bayesian approach based on the Canonical PARAFAC (CP) decomposition and enrich this single-layer decomposition approach with a two-layer decomposition. The second layer fits a factor model for each layer-one factor matrix and models the factor matrix via the mode entities' features and/or the network between the mode entities. The second-layer decomposition of each factor matrix also learns a binary latent representation for the entities of that mode, which can be useful in its own right. Our model can handle both continuous as well as binary tensor observations. Another appealing aspect of our model is the simplicity of the model inference, with easy-to-sample Gibbs updates. We demonstrate the results of our model on several benchmarks datasets, consisting of both real and binary tensors.

Ensemble learning is among the state-of-the-art learning techniques, which trains and combines many base learners. Ensemble pruning removes some of the base learners of an ensemble, and has been shown to be able to further improve the generalization performance. However, the two goals of ensemble pruning, i.e., maximizing the generalization performance and minimizing the number of base learners, can conflict when being pushed to the limit. Most previous ensemble pruning approaches solve objectives that mix the two goals. In this paper, motivated by the recent theoretical advance of evolutionary optimization, we investigate solving the two goals explicitly in a bi-objective formulation and propose the PEP (Pareto Ensemble Pruning) approach. We disclose that PEP does not only achieve significantly better performance than the state-of-the-art approaches, and also gains theoretical support.

Reinforcement learning (RL) is a common paradigm for learning tasks in robotics. However, a lot of exploration is usually required, making RL too slow for high-level tasks. We present V-MIN, an algorithm that integrates teacher demonstrations with RL to learn complex tasks faster. The algorithm combines active demonstration requests and autonomous exploration to find policies yielding rewards higher than a given threshold Vmin. This threshold sets the degree of quality with which the robot is expected to complete the task, thus allowing the user to either opt for very good policies that require many learning experiences, or to be more permissive with sub-optimal policies that are easier to learn. The threshold can also be increased online to force the system to improve its policies until the desired behavior is obtained. Furthermore, the algorithm generalizes previously learned knowledge, adapting well to changes. The performance of V-MIN has been validated through experimentation, including domains from the international planning competition. Our approach achieves the desired behavior where previous algorithms failed.