Multitask learning with expert advice

We consider the problem of prediction with expert advice in the setting where a forecaster is presented with several online prediction tasks. Instead of competing against the best expert separately on each task, we assume the tasks are related, and thus we expect that a few experts will perform well on the entire set of tasks. That is, our forecaster would like, on each task, to compete against the best expert chosen from a small set of experts. While we describe the “ideal” algorithm and its performance bound, we show that the computation required for this algorithm is as hard as computation of a matrix permanent. We present an efficient algorithm based on mixing priors, and prove a bound that is nearly as good for the sequential task presentation case. We also consider a harder case where the task may change arbitrarily from round to round, and we develop an efficient approximate randomized algorithm based on Markov chain Monte Carlo techniques.

A learning-based approach to reactive security

Despite the conventional wisdom that proactive security is superior to reactive security, we show that reactive security can be competitive with proactive security as long as the reactive defender learns from past attacks instead of myopically overreacting to the last attack. Our game-theoretic model follows common practice in the security literature by making worst-case assumptions about the attacker: we grant the attacker complete knowledge of the defender’s strategy and do not require the attacker to act rationally. In this model, we bound the competitive ratio between a reactive defense algorithm (which is inspired by online learning theory) and the best fixed proactive defense. Additionally, we show that, unlike proactive defenses, this reactive strategy is robust to a lack of information about the attacker’s incentives and knowledge.

A unifying view of multiple kernel learning

Recent research on multiple kernel learning has lead to a number of approaches for combining kernels in regularized risk minimization. The proposed approaches include different formulations of objectives and varying regularization strategies. In this paper we present a unifying optimization criterion for multiple kernel learning and show how existing formulations are subsumed as special cases. We also derive the criterion’s dual representation, which is suitable for general smooth optimization algorithms. Finally, we evaluate multiple kernel learning in this framework analytically using a Rademacher complexity bound on the generalization error and empirically in a set of experiments.

Multiview point cloud kernels for semisupervised learning [Lecture Notes]

In semisupervised learning (SSL), a predictive model is learn from a collection of labeled data and a typically much larger collection of unlabeled data. These paper presented a framework called multi-view point cloud regularization (MVPCR), which unifies and generalizes several semisupervised kernel methods that are based on data-dependent regularization in reproducing kernel Hilbert spaces (RKHSs). Special cases of MVPCR include coregularized least squares (CoRLS), manifold regularization (MR), and graph-based SSL. An accompanying theorem shows how to reduce any MVPCR problem to standard supervised learning with a new multi-view kernel.

Correction to “The Importance of Convexity in Learning With Squared Loss” [Sep 98 1974-1980]

The paper "the importance of convexity in learning with squared loss" gave a lower bound on the sample complexity of learning with quadratic loss using a nonconvex function class. The proof contains an error. We show that the lower bound is true under a stronger condition that holds for many cases of interest.

Open problems in the security of learning

Machine learning has become a valuable tool for detecting and preventing malicious activity. However, as more applications employ machine learning techniques in adversarial decision-making situations, increasingly powerful attacks become possible against machine learning systems. In this paper, we present three broad research directions towards the end of developing truly secure learning. First, we suggest that finding bounds on adversarial influence is important to understand the limits of what an attacker can and cannot do to a learning system. Second, we investigate the value of adversarial capabilities-the success of an attack depends largely on what types of information and influence the attacker has. Finally, we propose directions in technologies for secure learning and suggest lines of investigation into secure techniques for learning in adversarial environments. We intend this paper to foster discussion about the security of machine learning, and we believe that the research directions we propose represent the most important directions to pursue in the quest for secure learning.

Implicit online learning

Online learning algorithms have recently risen to prominence due to their strong theoretical guarantees and an increasing number of practical applications for large-scale data analysis problems. In this paper, we analyze a class of online learning algorithms based on fixed potentials and nonlinearized losses, which yields algorithms with implicit update rules. We show how to efficiently compute these updates, and we prove regret bounds for the algorithms. We apply our formulation to several special cases where our approach has benefits over existing online learning methods. In particular, we provide improved algorithms and bounds for the online metric learning problem, and show improved robustness for online linear prediction problems. Results over a variety of data sets demonstrate the advantages of our framework.

A unifying view of multiple kernel learning

Recent research on multiple kernel learning has lead to a number of approaches for combining kernels in regularized risk minimization. The proposed approaches include different formulations of objectives and varying regularization strategies. In this paper we present a unifying general optimization criterion for multiple kernel learning and show how existing formulations are subsumed as special cases. We also derive the criterion's dual representation, which is suitable for general smooth optimization algorithms. Finally, we evaluate multiple kernel learning in this framework analytically using a Rademacher complexity bound on the generalization error and empirically in a set of experiments.

Matrix regularization techniques for online multitask learning

In this paper we examine the problem of prediction with expert advice in a setup where the learner is presented with a sequence of examples coming from different tasks. In order for the learner to be able to benefit from performing multiple tasks simultaneously, we make assumptions of task relatedness by constraining the comparator to use a lesser number of best experts than the number of tasks. We show how this corresponds naturally to learning under spectral or structural matrix constraints, and propose regularization techniques to enforce the constraints. The regularization techniques proposed here are interesting in their own right and multitask learning is just one application for the ideas. A theoretical analysis of one such regularizer is performed, and a regret bound that shows benefits of this setup is reported.

Adaptive online gradient descent

We study the rates of growth of the regret in online convex optimization. First, we show that a simple extension of the algorithm of Hazan et al eliminates the need for a priori knowledge of the lower bound on the second derivatives of the observed functions. We then provide an algorithm, Adaptive Online Gradient Descent, which interpolates between the results of Zinkevich for linear functions and of Hazan et al for strongly convex functions, achieving intermediate rates between [square root T] and [log T]. Furthermore, we show strong optimality of the algorithm. Finally, we provide an extension of our results to general norms.

Multitask learning with expert advice

We consider the problem of prediction with expert advice in the setting where a forecaster is presented with several online prediction tasks. Instead of competing against the best expert separately on each task, we assume the tasks are related, and thus we expect that a few experts will perform well on the entire set of tasks. That is, our forecaster would like, on each task, to compete against the best expert chosen from a small set of experts. While we describe the "ideal" algorithm and its performance bound, we show that the computation required for this algorithm is as hard as computation of a matrix permanent. We present an efficient algorithm based on mixing priors, and prove a bound that is nearly as good for the sequential task presentation case. We also consider a harder case where the task may change arbitrarily from round to round, and we develop an efficient approximate randomized algorithm based on Markov chain Monte Carlo techniques.

Learning the Kernel Matrix with Semi-Definite Programming

Kernel-based learning algorithms work by embedding the data into a Euclidean space, and then searching for linear relations among the embedded data points. The embedding is performed implicitly, by specifying the inner products between each pair of points in the embedding space. This information is contained in the so-called kernel matrix, a symmetric and positive definite matrix that encodes the relative positions of all points. Specifying this matrix amounts to specifying the geometry of the embedding space and inducing a notion of similarity in the input space -- classical model selection problems in machine learning. In this paper we show how the kernel matrix can be learned from data via semi-definite programming (SDP) techniques. When applied to a kernel matrix associated with both training and test data this gives a powerful transductive algorithm -- using the labelled part of the data one can learn an embedding also for the unlabelled part. The similarity between test points is inferred from training points and their labels. Importantly, these learning problems are convex, so we obtain a method for learning both the model class and the function without local minima. Furthermore, this approach leads directly to a convex method to learn the 2-norm soft margin parameter in support vector machines, solving another important open problem. Finally, the novel approach presented in the paper is supported by positive empirical results.

Scoping work integrated learning purposes, practices and issues

A range of terms is used in Australian higher education institutions to describe learning approaches and teaching models that provide students with opportunities to engage in learning connected to the world of work. The umbrella term currently being used widely is Work Integrated Learning (WIL). The common aim of approaches captured under the term WIL is to integrate discipline specific knowledge learnt in university setting with that learnt in the practice of work through purposefully designed curriculum. In endeavours to extend WIL opportunities for students, universities are currently exploring authentic learning experiences, both within and outside of university settings. Some universities describe these approaches as ‘real world learning’ or ‘professional learning’. Others refer to ‘social engagement’ with the community and focus on building social capital and citizenship through curriculum design that enables students to engage with the professions through a range of learning experiences. This chapter discusses the context for, the scope, purposes, characteristics and effectiveness of WIL across Australian universities as derived from a national scoping study. This study, undertaken in response to a high level of interest in WIL, involved data collection from academic and professional staff, and students at nearly all Australian universities. Participants in the study consistently reported the benefits, especially in relation to the student learning experience. Responses highlight the importance of strong partnerships between stakeholders to facilitate effective learning outcomes and a range of issues that shape the quality of approaches and models being adopted, in promoting professional learning.

Work integrated learning for life : encouraging agentic engagement

In a rapidly changing world where new work patterns impact on our health, relationships and social fabric, it is critical that we reconsider the role universities could or should play in helping students prepare for the complexities of the 21st century. Efforts to respond to economic imperatives such as the skills shortage have seen a rush to embed work integrated and career development learning in the curriculum as well as a strengthening of the discourse that the university’s role is primarily to produce industry ready or ‘oven ready and self basting’ graduates (Atkins, 1999). This narrow focus on ‘giving industry what industry wants’ (Patrick, Peach & Pocknee, 2009) ignores the importance of helping students develop the types of skills and dispositions they will need. To enable students to thrive not just survive socially and economically in a radically unknowable world, where knowledge becomes obsolete, we need to be ready to develop new futures (Barnett, 2004). This paper considers the concept of ‘work’, the role it plays in our lives, and our aspirations to build sustainable, socially connected communities. We revisit the assumptions underlying the employability argument (Atkins, 1999) in the light of changing notions of work (Hagel, Seely Brown & Davison, 2010), and the need for higher education to contribute to a better and more sustainable society (Pocock, 2003). Specifically we present initiatives developed from work integrated learning (WIL) programs in the United Kingdom and Australia, where WIL programs are framed within the broader context of real world and life-wide curriculum (Jackson, 2010), and where transferable skills and elements of work-related learning programs prepare students for less certain job futures. Such approaches encourage students to take an agentic role (Billett & Pavlova, 2005) in selecting their work possibilities to develop resilience and capabilities to deal with new and challenging situations, assisting students to become who they want to be not just what they want to be. The theoretical and operational implications and challenges of shaping real world and life-wide curriculum will be investigated in more depth in the next phase of this research.

The WIL (Work Integrated Learning) report : a national scoping study [Final Report]

This report provides an account of the first large-scale scoping study of work integrated learning (WIL) in contemporary Australian higher education. The explicit aim of the project was to identify issues and map a broad and growing picture of WIL across Australia and to identify ways of improving the student learning experience in relation to WIL. The project was undertaken in response to high levels of interest in WIL, which is seen by universities both as a valid pedagogy and as a means to respond to demands by employers for work-ready graduates, and demands by students for employable knowledge and skills. Over a period of eight months of rapid data collection, 35 universities and almost 600 participants contributed to the project. Participants consistently reported the positive benefits of WIL and provided evidence of commitment and innovative practice in relation to enhancing student learning experiences. Participants provided evidence of strong partnerships between stakeholders and highlighted the importance of these relationships in facilitating effective learning outcomes for students. They also identified a range of issues and challenges that face the sector in growing WIL opportunities; these issues and challenges will shape the quality of WIL experiences. While the majority of comments focused on issues involved in ensuring quality placements, it was recognised that placements are just one way to ensure the integration of work with learning. Also, the WIL experience is highly contextualised and impacted by the expectations of students, employers, the professions, the university and government policy.