Publications
Results
- Showing results for:
- Reset all filters
Search results
-
Journal articleKupcsik A, Deisenroth MP, Peters J, et al., 2017,
Model-based contextual policy search for data-efficient generalization of robot skills
, Artificial Intelligence, Vol: 247, Pages: 415-439, ISSN: 0004-3702© 2014 Elsevier B.V. In robotics, lower-level controllers are typically used to make the robot solve a specific task in a fixed context. For example, the lower-level controller can encode a hitting movement while the context defines the target coordinates to hit. However, in many learning problems the context may change between task executions. To adapt the policy to a new context, we utilize a hierarchical approach by learning an upper-level policy that generalizes the lower-level controllers to new contexts. A common approach to learn such upper-level policies is to use policy search. However, the majority of current contextual policy search approaches are model-free and require a high number of interactions with the robot and its environment. Model-based approaches are known to significantly reduce the amount of robot experiments, however, current model-based techniques cannot be applied straightforwardly to the problem of learning contextual upper-level policies. They rely on specific parametrizations of the policy and the reward function, which are often unrealistic in the contextual policy search formulation. In this paper, we propose a novel model-based contextual policy search algorithm that is able to generalize lower-level controllers, and is data-efficient. Our approach is based on learned probabilistic forward models and information theoretic policy search. Unlike current algorithms, our method does not require any assumption on the parametrization of the policy or the reward function. We show on complex simulated robotic tasks and in a real robot experiment that the proposed learning framework speeds up the learning process by up to two orders of magnitude in comparison to existing methods, while learning high quality policies.
-
Journal articleJahani E, Sundsøy P, Bjelland J, et al., 2017,
Improving official statistics in emerging markets using machine learning and mobile phone data
, EPJ Data Science, Vol: 6, ISSN: 2193-1127Mobile phones are one of the fastest growing technologies in the developing world with global penetration rates reaching 90%. Mobile phone data, also called CDR, are generated everytime phones are used and recorded by carriers at scale. CDR have generated groundbreaking insights in public health, official statistics, and logistics. However, the fact that most phones in developing countries are prepaid means that the data lacks key information about the user, including gender and other demographic variables. This precludes numerous uses of this data in social science and development economic research. It furthermore severely prevents the development of humanitarian applications such as the use of mobile phone data to target aid towards the most vulnerable groups during crisis. We developed a framework to extract more than 1400 features from standard mobile phone data and used them to predict useful individual characteristics and group estimates. We here present a systematic cross-country study of the applicability of machine learning for dataset augmentation at low cost. We validate our framework by showing how it can be used to reliably predict gender and other information for more than half a million people in two countries. We show how standard machine learning algorithms trained on only 10,000 users are sufficient to predict individual’s gender with an accuracy ranging from 74.3 to 88.4% in a developed country and from 74.5 to 79.7% in a developing country using only metadata. This is significantly higher than previous approaches and, once calibrated, gives highly accurate estimates of gender balance in groups. Performance suffers only marginally if we reduce the training size to 5,000, but significantly decreases in a smaller training set. We finally show that our indicators capture a large range of behavioral traits using factor analysis and that the framework can be used to predict other indicators of vulnerability such as age or socio-economic status. M
-
Conference paperTiwari K, Honore V, Jeong S, et al., 2017,
Resource-constrained decentralized active sensing for multi-robot systems using distributed Gaussian processes
, 2016 16th International Conference on Control, Automation and Systems (ICCAS), Publisher: IEEE, Pages: 13-18, ISSN: 1598-7833We consider the problem of area coverage for robot teams operating under resource constraints, while modeling spatio-temporal environmental phenomena. The aim of the mobile robot team is to avoid exhaustive search and only visit the most important locations that can improve the prediction accuracy of a spatio-temporal model. We use a Gaussian Process (GP) to model spatially varying and temporally evolving dynamics of the target phenomenon. Each robot of the team is allocated a dedicated search area wherein the robot autonomously optimizes its prediction accuracy. We present this as a Decentralized Computation and Centralized Data Fusion approach wherein the trajectory sampled by the robot is generated using our proposed Resource-Constrained Decentralized Active Sensing (RC-DAS). Since each robot possesses its own independent prediction model, at the end of robot's mission time, we fuse all the prediction models from all robots to have a global model of the spatio-temporal phenomenon. Previously, all robots and GPs needed to be synchronized, such that the GPs can be jointly trained. However, doing so defeats the purpose of a fully decentralized mobile robot team. Thus, we allow the robots to independently gather new measurements and update their model parameters irrespective of other members of the team. To evaluate the performance of our model, we compare the trajectory traced by the robot using active and passive (e.g., nearest neighbor selection) sensing. We compare the performance and cost incurred by a resource constrained optimization with the unconstrained entropy maximization version.
-
Journal articleZhang Q, Filippi S, Gretton A, et al., 2017,
Large-Scale Kernel Methods for Independence Testing
, Statistics and Computing, Vol: 28, Pages: 113-130, ISSN: 1573-1375Representations of probability measures in reproducing kernel Hilbert spacesprovide a flexible framework for fully nonparametric hypothesis tests ofindependence, which can capture any type of departure from independence,including nonlinear associations and multivariate interactions. However, theseapproaches come with an at least quadratic computational cost in the number ofobservations, which can be prohibitive in many applications. Arguably, it isexactly in such large-scale datasets that capturing any type of dependence isof interest, so striking a favourable tradeoff between computational efficiencyand test performance for kernel independence tests would have a direct impacton their applicability in practice. In this contribution, we provide anextensive study of the use of large-scale kernel approximations in the contextof independence testing, contrasting block-based, Nystrom and random Fourierfeature approaches. Through a variety of synthetic data experiments, it isdemonstrated that our novel large scale methods give comparable performancewith existing methods whilst using significantly less computation time andmemory.
-
Conference paperChamberlain BP, Humby C, Deisenroth MP, 2017,
Probabilistic Inference of Twitter Users' Age Based on What They Follow.
, Publisher: Springer, Pages: 191-203 -
Conference paperEleftheriadis S, Rudovic O, Deisenroth MP, et al., 2016,
Variational Gaussian Process Auto-Encoder for Ordinal Prediction of Facial Action Units
, 13th Asian Conference on Computer Vision (ACCV’16), Publisher: Springer, Pages: 154-170, ISSN: 0302-9743We address the task of simultaneous feature fusion and modelingof discrete ordinal outputs. We propose a novel Gaussian process(GP) auto-encoder modeling approach. In particular, we introduce GPencoders to project multiple observed features onto a latent space, whileGP decoders are responsible for reconstructing the original features. Inferenceis performed in a novel variational framework, where the recoveredlatent representations are further constrained by the ordinal outputlabels. In this way, we seamlessly integrate the ordinal structure in thelearned manifold, while attaining robust fusion of the input features.We demonstrate the representation abilities of our model on benchmarkdatasets from machine learning and affect analysis. We further evaluatethe model on the tasks of feature fusion and joint ordinal predictionof facial action units. Our experiments demonstrate the benefits of theproposed approach compared to the state of the art.
-
Conference paperJoulani P, Gyorgy A, Szepesvari C, 2016,
A unified modular analysis of online and stochastic optimization: adaptivity, optimism, non-convexity
, 9th NIPS Workshop on Optimization for Machine LearningWe present a simple unified analysis of adaptive Mirror Descent (MD) and Follow-the-Regularized-Leader (FTRL) algorithms for online and stochastic optimizationin (possibly infinite-dimensional) Hilbert spaces. The analysis is modular inthe sense that it completely decouples the effect of possible assumptions on theloss functions (such as smoothness, strong convexity, and non-convexity) andon the optimization regularizers (such as strong convexity, non-smooth penaltiesin composite-objective learning, and non-monotone step-size sequences). Wedemonstrate the power of this decoupling by obtaining generalized algorithms andimproved regret bounds for the so-called “adaptive optimistic online learning” set-ting. In addition, we simplify and extend a large body of previous work, includingseveral various AdaGrad formulations, composite-objective and implicit-updatealgorithms. In all cases, the results follow as simple corollaries within few linesof algebra. Finally, the decomposition enables us to obtain preliminary globalguarantees for limited classes of non-convex problems.
-
Conference paperShaloudegi K, Gyorgy A, Szepesvari C, et al., 2016,
SDP relaxation with randomized rounding for energy disaggregation
, The Thirtieth Annual Conference on Neural Information Processing Systems (NIPS), Publisher: Neutral Information Processing Systems Foundation, Inc.We develop a scalable, computationally efficient method for the task of energydisaggregation for home appliance monitoring. In this problem the goal is toestimate the energy consumption of each appliance over time based on the totalenergy-consumption signal of a household. The current state of the art is to modelthe problem as inference in factorial HMMs, and use quadratic programming tofind an approximate solution to the resulting quadratic integer program. Here wetake a more principled approach, better suited to integer programming problems,and find an approximate optimum by combining convex semidefinite relaxationsrandomized rounding, as well as a scalable ADMM method that exploits the specialstructure of the resulting semidefinite program. Simulation results both in syntheticand real-world datasets demonstrate the superiority of our method.
-
Conference paperHuang R, Lattimore T, Gyorgy A, et al., 2016,
Following the Leader and Fast Rates in Linear Prediction: Curved Constraint Sets and Other Regularities
, Advances in Neural Information Processing Systems 29 (NIPS 2016), Publisher: Neutral Information Processing Systems Foundation, Inc.The follow the leader (FTL) algorithm, perhaps the simplest of all online learningalgorithms, is known to perform well when the loss functions it is used on are positivelycurved. In this paper we ask whether there are other “lucky” settings whenFTL achieves sublinear, “small” regret. In particular, we study the fundamentalproblem of linear prediction over a non-empty convex, compact domain. Amongstother results, we prove that the curvature of the boundary of the domain can act asif the losses were curved: In this case, we prove that as long as the mean of the lossvectors have positive lengths bounded away from zero, FTL enjoys a logarithmicgrowth rate of regret, while, e.g., for polyhedral domains and stochastic data itenjoys finite expected regret. Building on a previously known meta-algorithm, wealso get an algorithm that simultaneously enjoys the worst-case guarantees and thebound available for FTL.
-
Journal articleFilippi S, Holmes CC, Nieto-Barajas LE, 2016,
Scalable Bayesian nonparametric measures for exploring pairwise dependence via Dirichlet Process Mixtures
, Electronic Journal of Statistics, Vol: 10, Pages: 3338-3354, ISSN: 1935-7524In this article we propose novel Bayesian nonparametric methods using Dirichlet Process Mixture (DPM) models for detecting pairwise dependence between random variables while accounting for uncertainty in the form of the underlying distributions. A key criteria is that the procedures should scale to large data sets. In this regard we find that the formal calculation of the Bayes factor for a dependent-vs.-independent DPM joint probability measure is not feasible computationally. To address this we present Bayesian diagnostic measures for characterising evidence against a “null model” of pairwise independence. In simulation studies, as well as for a real data analysis, we show that our approach provides a useful tool for the exploratory nonparametric Bayesian analysis of large multivariate data sets.
This data is extracted from the Web of Science and reproduced under a licence from Thomson Reuters. You may not copy or re-distribute this data in whole or in part without the written consent of the Science business of Thomson Reuters.