Missing data is an expected issue when large amounts of data is collected, and several imputation techniques have been proposed to tackle this problem. Beneath classical approaches such as MICE, the application of Machine Learning techniques is tempting. Here, the recently proposed missForest imputation method has shown high imputation accuracy under the Missing (Completely) at Random scheme with various missing rates. In its core, it is based on a random forest for classification and regression, respectively. In this paper we study whether this approach can even be enhanced by other methods such as the stochastic gradient tree boosting method, the C5.0 algorithm or modified random forest procedures. In particular, other resampling strategies within the random forest protocol are suggested. In an extensive simulation study, we analyze their performances for continuous, categorical as well as mixed-type data. Therein, MissBooPF, a combination of the stochastic gradient tree boosting method together with the parametrically bootstrapped random forest method, appeared to be promising. Finally, an empirical analysis focusing on credit information and Facebook data is conducted.

The Humanoids 2017 conference earlier this month hosted an excellent photo competition. I was lucky to be one of the judges, along with Erico Guizzo from IEEE Spectrum, and Giorgio Metta as awards chair. The decision, which was tough given the excellent submissions, was based on social media votes and scores for originality, creativity, photo structure, and tech or fun factor. The overall winner for Best Humanoid Photo featured a pensive iCub and was entitled "To be, or not to be" by Pedro Vicente from the Vislab in Lisbon. The winner for Best Funny Humanoid was this picture of a frustrated SABIAN entitled "If only I had a self-driving car" by Marco Moscato at the Biorobotics Institute, Scuola Superiore Sant'Anna.

A significant number of jobs could be completed by robots as early as 2030, according to a new report published Tuesday by the McKinsey Global Institute. The transition into a heavily automated workplace wouldn't arrive right away, but it may affect up to 375 million workers globally. The workforce has already begun to accommodate technological advancements, with robotics being no exception to this. Statistics have proven the potential benefits to automated workers, including its positive effects on the global economy. McKinsey suggested that physical laborers are most at risk of losing their positions with the rise of automation, which includes food preppers and machine operators, among other similar workers.

On December 1st 2017, idalab will host a talk by Jeremiah Lewis and Edouard Malet from N26: 'Lean' Training Data: An Incremental Approach to Supervised Machine Learning. Machine learning in a young start up does not look like a Kaggle competition. Data science projects start with a more extensive roadmap than dataset. In the absence of data, subject-matter knowledge makes heuristic solutions a tempting first step for all stakeholders involved. While rules-based algorithms are not the glamorous side of data science, they need not be a dead end and can form the basis for increasingly sophisticated labeled data.

We develop Riemannian Stein Variational Gradient Descent (RSVGD), a Bayesian inference method that generalizes Stein Variational Gradient Descent (SVGD) to Riemann manifold. The benefits are two-folds: (i) for inference tasks in Euclidean spaces, RSVGD has the advantage over SVGD of utilizing information geometry, and (ii) for inference tasks on Riemann manifolds, RSVGD brings the unique advantages of SVGD to the Riemannian world. To appropriately transfer to Riemann manifolds, we conceive novel and non-trivial techniques for RSVGD, which are required by the intrinsically different characteristics of general Riemann manifolds from Euclidean spaces. We also discover Riemannian Stein's Identity and Riemannian Kernelized Stein Discrepancy. Experimental results show the advantages over SVGD of exploring distribution geometry and the advantages of particle-efficiency, iteration-effectiveness and approximation flexibility over other inference methods on Riemann manifolds.

We introduce a framework using Generative Adversarial Networks (GANs) for likelihood--free inference (LFI) and Approximate Bayesian Computation (ABC). Our approach addresses both the key problems in likelihood--free inference, namely how to compare distributions and how to efficiently explore the parameter space. Our framework allows one to use the simulator model as a black box and leverage the power of deep networks to generate a rich set of features in a data driven fashion (as opposed to previous ad hoc approaches). Thereby it is a step towards a powerful alternative approach to LFI and ABC. On benchmark data sets, our approach improves on others with respect to scalability, ability to handle high dimensional data and complex probability distributions.

Dialogue assistants are rapidly becoming an indispensable daily aid. To avoid the significant effort needed to hand-craft the required dialogue flow, the Dialogue Management (DM) module can be cast as a continuous Markov Decision Process (MDP) and trained through Reinforcement Learning (RL). Several RL models have been investigated over recent years. However, the lack of a common benchmarking framework makes it difficult to perform a fair comparison between different models and their capability to generalise to different environments. Therefore, this paper proposes a set of challenging simulated environments for dialogue model development and evaluation. To provide some baselines, we investigate a number of representative parametric algorithms, namely deep reinforcement learning algorithms - DQN, A2C and Natural Actor-Critic and compare them to a non-parametric model, GP-SARSA. Both the environments and policy models are implemented using the publicly available PyDial toolkit and released on-line, in order to establish a testbed framework for further experiments and to facilitate experimental reproducibility.

Rainfall ensemble forecasts have to be skillful for both low precipitation and extreme events. We present statistical post-processing methods based on Quantile Regression Forests (QRF) and Gradient Forests (GF) with a parametric extension for heavy-tailed distributions. Our goal is to improve ensemble quality for all types of precipitation events, heavy-tailed included, subject to a good overall performance. Our hybrid proposed methods are applied to daily 51-h forecasts of 6-h accumulated precipitation from 2012 to 2015 over France using the M{\'e}t{\'e}o-France ensemble prediction system called PEARP. They provide calibrated pre-dictive distributions and compete favourably with state-of-the-art methods like Analogs method or Ensemble Model Output Statistics. In particular, hybrid forest-based procedures appear to bring an added value to the forecast of heavy rainfall.

Independent Component Analysis (ICA) is a technique for unsupervised exploration of multi-channel data widely used in observational sciences. In its classical form, ICA relies on modeling the data as a linear mixture of non-Gaussian independent sources. The problem can be seen as a likelihood maximization problem. We introduce Picard-O, a preconditioned L-BFGS strategy over the set of orthogonal matrices, which can quickly separate both super- and sub-Gaussian signals. It returns the same set of sources as the widely used FastICA algorithm. Through numerical experiments, we show that our method is faster and more robust than FastICA on real data.

This paper studies directed exploration for reinforcement learning agents by tracking uncertainty about the value of each available action. We identify two sources of uncertainty that are relevant for exploration. The first originates from limited data (parametric uncertainty), while the second originates from the distribution of the returns (return uncertainty). We identify methods to learn these distributions with deep neural networks, where we estimate parametric uncertainty with Bayesian drop-out, while return uncertainty is propagated through the Bellman equation as a Gaussian distribution. Then, we identify that both can be jointly estimated in one network, which we call the Double Uncertain Value Network. The policy is directly derived from the learned distributions based on Thompson sampling. Experimental results show that both types of uncertainty may vastly improve learning in domains with a strong exploration challenge.