ABSTRACT We consider statistical learning problems, when the distribution P ′ of the training observations Z ′ 1,..., Z′ n differs from the distribution P involved in the risk one seeks to minimize (referred to as the test distribution) but is still defined on the same measurable space as P and dominates it. In the unrealistic case where the likelihood ratio Φ(z) dP/dP ′ (z) is known, one may straightforwardly extends the Empirical Risk Minimization (ERM) approach to this specific transfer learning setup using the same idea as that behind Importance Sampling, by minimizing a weighted version of the empirical risk functional computed from the'biased' training data Zi ′ with weights Φ(Zi ′). Although the importance function Φ(z) is generally unknown in practice, we show that, in various situations frequently encountered in practice, it takes a simple form and can be directly estimated from the Zi ′ 's and some auxiliary information on the statistical population P. By means of linearization techniques, we then prove that the generalization capacity of the approach aforementioned is preserved when plugging the resulting estimates of the Φ(Zi ′)'s into the weighted empirical risk. Beyond these theoretical guarantees, numerical results provide strong empirical evidence of the relevance of the approach promoted in this article. Keywords: Statistical Learning Theory, Importance Sampling, Transfer Learning. 1 Introduction Prediction problems are of major importance in statistical learning. The main paradigm of predictive learning is Empirical Risk Minimization (ERM in abbreviated form), see e.g. In the standard setup, Z is a random variable (r.v. in short) that takes its values in a feature space Z with distribution P, Θ is a parameter space and l: Θ Z R is a (measurable) loss function. The risk is then defined by: θ Θ, R P (θ) E P [l(θ, Z)], (1) and more generally for any measure Q on Z: R Q (θ) l(θ, z)dQ(z).

Transfer Learning (TL) has shown great potential to accelerate Reinforcement Learning (RL) by leveraging prior knowledge from past learned policies of relevant tasks. Existing transfer approaches either explicitly computes the similarity between tasks or select appropriate source policies to provide guided explorations for the target task. However, how to directly optimize the target policy by alternatively utilizing knowledge from appropriate source policies without explicitly measuring the similarity is currently missing. In this paper, we propose a novel Policy Transfer Framework (PTF) to accelerate RL by taking advantage of this idea. Our framework learns when and which source policy is the best to reuse for the target policy and when to terminate it by modeling multi-policy transfer as the option learning problem. PTF can be easily combined with existing deep RL approaches. Experimental results show it significantly accelerates the learning process and surpasses state-of-the-art policy transfer methods in terms of learning efficiency and final performance in both discrete and continuous action spaces.

Recent research in artificial intelligence and machine learning has largely emphasized general-purpose learning and ever-larger training sets and more and more compute. In contrast, I propose a hybrid, knowledge-driven, reasoning-based approach, centered around cognitive models, that could provide the substrate for a richer, more robust AI than is currently possible.

We see the growth of people analytics at first-hand at Insight222, where we are now working with over 60 global organisations to help them put people analytics at the centre of business. In tandem we have also created a digital learning academy with myHRfuture to upskill HR in digital and analytics. For the last six years I have collated and published a collection of the'best' articles of the preceding 12 months – see 2014, 2015, 2016 2017 and 2018, and following are my choices for the 50 best articles of 2019. Those who have read the previous annual collections may note that the number of articles that make the cut has steadily risen. This is partly down to my inability to prune down to 30 or 20 - although it was hard enough to get it down to 50! Mainly though this recognises the increased number, variety and quality of people analytics and data-driven HR material now being published, which is another indicator of progress in the field. I hope that the articles selected will act as a venerable resource library for those working, researching or interested in the people analytics space. That is certainly the intention. I have arranged the 50 articles into twelve topics: i) Driving business value, ii) the future of work, iii) the future of the HR function, iv) ethics and trust, v) employee experience, vi) strategic workforce planning, vii) ONA, viii) diversity and inclusion, ix) organisational culture, perspectives and case studies from people analytics leaders, x) retention, xi) assessment and xii) getting started, as well as highlighting a few of my own articles from 2019 at the end. I hope you enjoy the articles selected, and if you do, please subscribe to my weekly Digital HR Leaders newsletter. Ultimately, people analytics should be about creating value – for leaders, for managers and for the workforce. So, where better to start than with seven articles that collectively provide insights on how to create value and/or give examples of where organisations have created value from people analytics.

Neural networks utilize the softmax as a building block in classification tasks, which contains an overconfidence problem and lacks an uncertainty representation ability. As a Bayesian alternative to the softmax, we consider a random variable of a categorical probability over class labels. In this framework, the prior distribution explicitly models the presumed noise inherent in the observed label, which provides consistent gains in generalization performance in multiple challenging tasks. The proposed method inherits advantages of Bayesian approaches that achieve better uncertainty estimation and model calibration. Our method can be implemented as a plug-and-play loss function with negligible computational overhead compared to the softmax with the cross-entropy loss function.

A novel gradient boosting framework is proposed where shallow neural networks are employed as "weak learners". General loss functions are considered under this unified framework with specific examples presented for classification, regression and learning to rank. A fully corrective step is incorporated to remedy the pitfall of greedy function approximation of classic gradient boosting decision tree. The proposed model rendered state-of-the-art results in all three tasks on multiple datasets. An ablation study is performed to shed light on the effect of each model components and model hyperparameters.

Learning often occurs sequentially, as opposed to in batch, and from data provided by other agents, as opposed to from a fixed random sampling process. The canonical example of sequential learning from an agent occurs in educational contexts where the other agent is a teacher whose goal is to help the learner. However, instances appear across a wide range of contexts including informal learning, language, and robotics. In contrast with typical contexts considered in machine learning, it is reasonable to expect the cooperative agent to adapt their sampling process after each trial, consistent with the goal of helping the learner learn more quickly. It is also reasonable to expect that learners, in dealing with such cooperative agents, would know the other agent intends to cooperate and incorporate that knowledge when updating their beliefs.

A fundamental question in modern machine learning is how deep neural networks can generalize. We address this question using 1) an equivalence between training infinitely wide neural networks and performing kernel regression with a deterministic kernel called the Neural Tangent Kernel (NTK) (Jacot et al. 2018), and 2) theoretical tools from statistical physics. We derive analytical expressions for learning curves for kernel regression, and use them to evaluate how the test loss of a trained neural network depends on the number of samples. Our approach allows us not only to compute the total test risk but also the decomposition of the risk due to different spectral components of the kernel. Complementary to recent results showing that during gradient descent, neural networks fit low frequency components first, we identify a new type of frequency principle: as the size of the training set size grows, kernel machines and neural networks begin to fit successively higher frequency modes of the target function. We verify our theory with simulations of kernel regression and training wide artificial neural networks.

Empirical networks are often globally sparse, with a small average number of connections per node, when compared to the total size of the network. However this sparsity tends not to be homogeneous, and networks can also be locally dense, for example with a few nodes connecting to a large fraction of the rest of the network, or with small groups of nodes with a large probability of connections between them. Here we show how latent Poisson models which generate hidden multigraphs can be effective at capturing this density heterogeneity, while being more tractable mathematically than some of the alternatives that model simple graphs directly. We show how these latent multigraphs can be reconstructed from data on simple graphs, and how this allows us to disentangle dissortative degree-degree correlations from the constraints of imposed degree sequences, and to improve the identification of community structure in empirically relevant scenarios.

Calibration and equal error rates are fundamental conditions for algorithmic fairness that have been shown to conflict with each other, suggesting that they cannot be satisfied simultaneously. This paper shows that the two are in fact compatible and presents a method for reconciling them. In particular, we derive necessary and sufficient conditions for the existence of calibrated scores that yield classifications achieving equal error rates. We then present an algorithm that searches for the most informative score subject to both calibration and minimal error rate disparity. Applied empirically to credit lending, our algorithm provides a solution that is more fair and profitable than a common alternative that omits sensitive features.