This paper deals with resource constrained autonomous robots commonly found in factories, hospitals, and education laboratories, which popularly use learning enabled components (LEC) to make control actions. However, these LECs do not provide any safety guarantees, and testing them is challenging. To overcome these challenges, we introduce a framework that performs confidence estimation, resource management, and supervised safety control of autonomous systems with LECs. Using this framework, we make the following contributions: (1) allow for seamless integration of safety controllers and different simplex strategies to aid the LEC, (2) introduce RL-Simplex and illustrate the use of Q-learning to learn the optimal weights for the arbitration logic of the Simplex Architecture, (3) design a system level monitor that uses the current state information and a discrete Bayesian network model learned from past data to estimate a metric, which indicates if the car will remain in the safe region, and (4) a Resource Manager which performs dynamic task offloading depending on the resource temperature and CPU utilization while continually adjusting vehicle speed to compensate for the latency overhead. We compare the speed, steering and safety performance of the different controllers and simplex strategies, and we find RL-Simplex to have 60\% fewer safety violations and higher optimized speed during indoor driving ($\sim\,0.40\,m/s$) than the original system (using only LEC).

In this paper, we study the accuracy of values aggregated over classes predicted by a classification algorithm. The problem is that the resulting aggregates (e.g., sums of a variable) are known to be biased. The bias can be large even for highly accurate classification algorithms, in particular when dealing with class-imbalanced data. To correct this bias, the algorithm's classification error rates have to be estimated. In this estimation, two issues arise when applying existing bias correction methods. First, inaccuracies in estimating classification error rates have to be taken into account. Second, impermissible estimates, such as a negative estimate for a positive value, have to be dismissed. We show that both issues are relevant in applications where the true labels are known only for a small set of data points. We propose a novel bias correction method using Bayesian inference. The novelty of our method is that it imposes constraints on the model parameters. We show that our method solves the problem of biased classification-based aggregates as well as the two issues above, in the general setting of multi-class classification. In the empirical evaluation, using a binary classifier on a real-world dataset of company tax returns, we show that our method outperforms existing methods in terms of mean squared error.

Though the convergence of major reinforcement learning algorithms has been extensively studied, the finite-sample analysis to further characterize the convergence rate in terms of the sample complexity for problems with continuous state space is still very limited. Such a type of analysis is especially challenging for algorithms with dynamically changing learning policies and under non-i.i.d.\ sampled data. In this paper, we present the first finite-sample analysis for the SARSA algorithm and its minimax variant (for zero-sum Markov games), with a single sample path and linear function approximation. To establish our results, we develop a novel technique to bound the gradient bias for dynamically changing learning policies, which can be of independent interest. We further provide finite-sample bounds for Q-learning and its minimax variant. Comparison of our result with the existing finite-sample bound indicates that linear function approximation achieves order-level lower sample complexity than the nearest neighbor approach.

Generative modeling is a fundamental problem in machine learning with many potential applications. Efficient learning of generative models requires available prior knowledge to be exploited as much as possible. In this paper, we propose a method to exploit prior knowledge of relative dependence between features for learning generative models. Such knowledge is available, for example, when side-information on features is present. We incorporate the prior knowledge by forcing marginals of the learned generative model to follow a prescribed relative feature dependence. To this end, we formulate a regularization term using a kernel-based dependence criterion. The proposed method can be incorporated straightforwardly into many optimization-based learning schemes of generative models, including variational autoencoders and generative adversarial networks. We show the effectiveness of the proposed method in experiments with multiple types of datasets and models.

We propose a MAP Bayesian approach to perform and evaluate a co-clustering of mixed-type data tables. The proposed model infers an optimal segmentation of all variables then performs a co-clustering by minimizing a Bayesian model selection cost function. One advantage of this approach is that it is user parameter-free. Another main advantage is the proposed criterion which gives an exact measure of the model quality, measured by probability of fitting it to the data. Continuous optimization of this criterion ensures finding better and better models while avoiding data over-fitting. The experiments conducted on real data show the interest of this co-clustering approach in exploratory data analysis of large data sets.

The fuzzy quantification model FA has been identified as one of the best behaved quantification models in several revisions of the field of fuzzy quantification. This model is, to our knowledge, the unique one fulfilling the strict Determiner Fuzzification Scheme axiomatic framework that does not induce the standard min and max operators. The main contribution of this paper is the proof of a convergence result that links this quantification model with the Zadeh's model when the size of the input sets tends to infinite. The convergence proof is, in any case, more general than the convergence to the Zadeh's model, being applicable to any quantitative quantifier. In addition, recent revisions papers have presented some doubts about the existence of suitable computational implementations to evaluate the FA model in practical applications. In order to prove that this model is not only a theoretical approach, we show exact algorithmic solutions for the most common linguistic quantifiers as well as an approximate implementation by means of Monte Carlo. Additionally, we will also give a general overview of the main properties fulfilled by the FA model, as a single compendium integrating the whole set of properties fulfilled by it has not been previously published.

This is an integrative review that address the question, "What makes for a good explanation?" with reference to AI systems. Pertinent literatures are vast. Thus, this review is necessarily selective. That said, most of the key concepts and issues are expressed in this Report. The Report encapsulates the history of computer science efforts to create systems that explain and instruct (intelligent tutoring systems and expert systems). The Report expresses the explainability issues and challenges in modern AI, and presents capsule views of the leading psychological theories of explanation. Certain articles stand out by virtue of their particular relevance to XAI, and their methods, results, and key points are highlighted. It is recommended that AI/XAI researchers be encouraged to include in their research reports fuller details on their empirical or experimental methods, in the fashion of experimental psychology research reports: details on Participants, Instructions, Procedures, Tasks, Dependent Variables (operational definitions of the measures and metrics), Independent Variables (conditions), and Control Conditions.

In this work, we fill a substantial void in machine learning and statistical methodology by developing extensive generative density estimation techniques for exchangeable non-iid data. We do so through the use of permutation invariant likelihoods and permutation equivariant transformations of variables. These methods exploit the intradependencies within sets in ways that are independent of ordering (for likelihoods) or order preserving (for transformations). The proposed techniques are able to directly model exchangeable data (such as sets) without the need to account for permutations or assume independence of elements. We consider applications to point clouds and provide several interesting experiments on both synthetic and real-world datasets.

How can we learn to do probabilistic inference in a way that generalizes between models? Amortized variational inference learns for a single model, sharing statistical strength across observations. This benefits scalability and model learning, but does not help with generalization to new models. We propose meta-amortized variational inference, a framework that amortizes the cost of inference over a family of generative models. We apply this approach to deep generative models by introducing the MetaVAE: a variational autoencoder that learns to generalize to new distributions and rapidly solve new unsupervised learning problems using only a small number of target examples. Empirically, we validate the approach by showing that the MetaVAE can: (1) capture relevant sufficient statistics for inference, (2) learn useful representations of data for downstream tasks such as clustering, and (3) perform meta-density estimation on unseen synthetic distributions and out-of-sample Omniglot alphabets.

In this work, we study consistency properties of $\alpha$-R\'enyi approximate posteriors, a class of variational Bayesian methods that approximate an intractable Bayesian posterior with a member of a tractable family of distributions, the latter chosen to minimize the $\alpha$-R\'enyi divergence from the true posterior. Unique to our work is that we consider settings with $\alpha > 1$, resulting in approximations that upperbound the log-likelihood, and result in approximations with a wider spread than traditional variational approaches that minimize the Kullback-Liebler divergence from the posterior. We provide sufficient conditions under which consistency holds, centering around the existence of a 'good' sequence of distributions in the approximating family. We discuss examples where this holds and show how the existence of such a good sequence implies posterior consistency in the limit of an infinite number of observations.