Natural policy gradient (NPG) methods with function approximation achieve impressive empirical success in reinforcement learning problems with large state-action spaces. However, theoretical understanding of their convergence behaviors remains limited in the function approximation setting. In this paper, we perform a finite-time analysis of NPG with linear function approximation and softmax parameterization, and prove for the first time that widely used entropy regularization method, which encourages exploration, leads to linear convergence rate. We adopt a Lyapunov drift analysis to prove the convergence results and explain the effectiveness of entropy regularization in improving the convergence rates.

We present the Multiple Criteria Decision Analysis Methods Selection Software (MCDA-MSS). This decision support system helps analysts answering a recurring question in decision science: Which is the most suitable Multiple Criteria Decision Analysis method (or a subset of MCDA methods) that should be used for a given Decision-Making Problem (DMP)?. The MCDA-MSS includes guidance to lead decision-making processes and choose among an extensive collection (over 200) of MCDA methods. These are assessed according to an original comprehensive set of problem characteristics. The accounted features concern problem formulation, preference elicitation and types of preference information, desired features of a preference model, and construction of the decision recommendation. The applicability of the MCDA-MSS has been tested on several case studies. The MCDA-MSS includes the capabilities of (i) covering from very simple to very complex DMPs, (ii) offering recommendations for DMPs that do not match any method from the collection, (iii) helping analysts prioritize efforts for reducing gaps in the description of the DMPs, and (iv) unveiling methodological mistakes that occur in the selection of the methods. A community-wide initiative involving experts in MCDA methodology, analysts using these methods, and decision-makers receiving decision recommendations will contribute to expansion of the MCDA-MSS.

In a typical supervised machine learning setting, the predictions on all test instances are based on a common subset of features discovered during model training. However, using a different subset of features that is most informative for each test instance individually may not only improve prediction accuracy, but also the overall interpretability of the model. At the same time, feature selection methods for classification have been known to be the most effective when many features are irrelevant and/or uncorrelated. In fact, feature selection ignoring correlations between features can lead to poor classification performance. In this work, a Bayesian network is utilized to model feature dependencies. Using the dependency network, a new method is proposed that sequentially selects the best feature to evaluate for each test instance individually, and stops the selection process to make a prediction once it determines that no further improvement can be achieved with respect to classification accuracy. The optimum number of features to acquire and the optimum classification strategy are derived for each test instance. The theoretical properties of the optimum solution are analyzed, and a new algorithm is proposed that takes advantage of these properties to implement a robust and scalable solution for high dimensional settings. The effectiveness, generalizability, and scalability of the proposed method is illustrated on a variety of real-world datasets from diverse application domains.

This Overview, Design Concepts, and Details Protocol (ODD) provides a detailed description of an agent-based model (ABM) that was developed to simulate hospitalizations during the COVID-19 pandemic. Using the descriptions of submodels, provided parameters, and the links to data sources, modelers will be able to replicate the creation and results of this model.

Overlap functions are a class of aggregation functions that measure the overlapping degree between two values. Interval-valued overlap functions were defined as an extension to express the overlapping of interval-valued data, and they have been usually applied when there is uncertainty regarding the assignment of membership degrees. The choice of a total order for intervals can be significant, which motivated the recent developments on interval-valued aggregation functions and interval-valued overlap functions that are increasing to a given admissible order, that is, a total order that refines the usual partial order for intervals. Also, width preservation has been considered on these recent works, in an intent to avoid the uncertainty increase and guarantee the information quality, but no deeper study was made regarding the relation between the widths of the input intervals and the output interval, when applying interval-valued functions, or how one can control such uncertainty propagation based on this relation. Thus, in this paper we: (i) introduce and develop the concepts of width-limited interval-valued functions and width limiting functions, presenting a theoretical approach to analyze the relation between the widths of the input and output intervals of bivariate interval-valued functions, with special attention to interval-valued aggregation functions; (ii) introduce the concept of $(a,b)$-ultramodular aggregation functions, a less restrictive extension of one-dimension convexity for bivariate aggregation functions, which have an important predictable behaviour with respect to the width when extended to the interval-valued context; (iii) define width-limited interval-valued overlap functions, taking into account a function that controls the width of the output interval; (iv) present and compare three construction methods for these width-limited interval-valued overlap functions.

Time series forecasting is a relevant task that is performed in several real-world scenarios such as product sales analysis and prediction of energy demand. Given their accuracy performance, currently, Recurrent Neural Networks (RNNs) are the models of choice for this task. Despite their success in time series forecasting, less attention has been paid to make the RNNs trustworthy. For example, RNNs can not naturally provide an uncertainty measure to their predictions. This could be extremely useful in practice in several cases e.g. to detect when a prediction might be completely wrong due to an unusual pattern in the time series. Whittle Sum-Product Networks (WSPNs), prominent deep tractable probabilistic circuits (PCs) for time series, can assist an RNN with providing meaningful probabilities as uncertainty measure. With this aim, we propose RECOWN, a novel architecture that employs RNNs and a discriminant variant of WSPNs called Conditional WSPNs (CWSPNs). We also formulate a Log-Likelihood Ratio Score as better estimation of uncertainty that is tailored to time series and Whittle likelihoods. In our experiments, we show that RECOWNs are accurate and trustworthy time series predictors, able to "know when they do not know".

The random coefficient logistic demand model of Berry et al. (1995) (henceforth BLP) has been a workhorse of the New Empirical Industrial Organization literature, allowing for varied substitution patterns across products, and accounting for endogeneity of price. The reliability of its estimation has been the subject of rigorous debate (Nevo, 2000; Conlon and Gortmaker, 2020; Knittel and Metaxoglou, 2014), and the estimator itself has been the study of many proposed advances in econometric techniques as a sophisticated yet widely used structural model (Hong et al., 2020; Forneron and Ng, 2020). The most common implementation of the BLP estimator involves the use of a nested fixed point (NFP) as an inner loop within an outer loop of GMM estimation, although we acknowledge the Mathematical Programming with Equilibrium Constraints (MPEC) approach of Dubé et al. (2012), which is beyond the scope of this paper. Dubé et al. (2012) and Conlon and Gortmaker (2020) find that derivative-free optimization algorithms such as the Nelder-Meade or simplex algorithms often fail to converge or converge to the wrong solution. As such, the literature has settled on the use of analytical derivatives with a derivative-based optimization algorithm such as L-BFGS. Nevo (2000) provides the analytical derivative for demand-only (DO) BLP in detail, and Conlon and Gortmaker (2020) indicate that the same is possible for demand-and-supply (DS) BLP, although it involves tensor products.

Although deep learning models have driven state-of-the-art performance on a wide array of tasks, they are prone to learning spurious correlations that should not be learned as predictive clues. To mitigate this problem, we propose a causality-based training framework to reduce the spurious correlations caused by observable confounders. We give theoretical analysis on the underlying general Structural Causal Model (SCM) and propose to perform Maximum Likelihood Estimation (MLE) on the interventional distribution instead of the observational distribution, namely Counterfactual Maximum Likelihood Estimation (CMLE). As the interventional distribution, in general, is hidden from the observational data, we then derive two different upper bounds of the expected negative log-likelihood and propose two general algorithms, Implicit CMLE and Explicit CMLE, for causal predictions of deep learning models using observational data. We conduct experiments on two real-world tasks: Natural Language Inference (NLI) and Image Captioning. The results show that CMLE methods outperform the regular MLE method in terms of out-of-domain generalization performance and reducing spurious correlations, while maintaining comparable performance on the regular evaluations.

In this paper, we investigate the question: Given a small number of datapoints, for example N = 30, how tight can PAC-Bayes and test set bounds be made? For such small datasets, test set bounds adversely affect generalisation performance by discarding data. In this setting, PAC-Bayes bounds are especially attractive, due to their ability to use all the data to simultaneously learn a posterior and bound its generalisation risk. We focus on the case of i.i.d. data with a bounded loss and consider the generic PAC-Bayes theorem of Germain et al. (2009) and Begin et al. (2016). While their theorem is known to recover many existing PAC-Bayes bounds, it is unclear what the tightest bound derivable from their framework is. Surprisingly, we show that for a fixed learning algorithm and dataset, the tightest bound of this form coincides with the tightest bound of the more restrictive family of bounds considered in Catoni (2007). In contrast, in the more natural case of distributions over datasets, we give examples (both analytic and numerical) showing that the family of bounds in Catoni (2007) can be suboptimal. Within the proof framework of Germain et al. (2009) and Begin et al. (2016), we establish a lower bound on the best bound achievable in expectation, which recovers the Chernoff test set bound in the case when the posterior is equal to the prior. Finally, to illustrate how tight these bounds can potentially be, we study a synthetic one-dimensional classification task in which it is feasible to meta-learn both the prior and the form of the bound to obtain the tightest PAC-Bayes and test set bounds possible. We find that in this simple, controlled scenario, PAC-Bayes bounds are surprisingly competitive with comparable, commonly used Chernoff test set bounds. However, the sharpest test set bounds still lead to better guarantees on the generalisation error than the PAC-Bayes bounds we consider.

Motivated by problems of learning to rank long item sequences, we introduce a variant of the cascading bandit model that considers flexible length sequences with varying rewards and losses. We formulate two generative models for this problem within the generalized linear setting, and design and analyze upper confidence algorithms for it. Our analysis delivers tight regret bounds which, when specialized to vanilla cascading bandits, results in sharper guarantees than previously available in the literature. We evaluate our algorithms on a number of real-world datasets, and show significantly improved empirical performance as compared to known cascading bandit baselines.