This article is the rejoinder for the paper "Probabilistic Integration: A Role in Statistical Computation?" to appear in Statistical Science with discussion [Briol et al., 2015]. We would first like to thank the reviewers and many of our colleagues who helped shape this paper, the editor for selecting our paper for discussion, and of course all of the discussants for their thoughtful, insightful and constructive comments. In this rejoinder, we respond to some of the points raised by the discussants and comment further on the fundamental questions underlying the paper: - Should Bayesian ideas be used in numerical analysis? Numerical analysis is concerned with the approximation of typically high or infinite-dimensional mathematical quantities using discretisations of the space on which these are defined. Different discretisation schemes lead to different numerical algorithms, whose stability and convergence properties need to be carefully assessed.

Food packaging labels provide important information for public health, such as allergens and use-by dates. Off-the-shelf Optical Character Verification (OCV) systems are good solutions for automating food label quality assessments, but are known to under perform on complex data. This paper proposes a Deep Learning based system that can identify inadequate images for OCV, due to their poor label quality, by employing state-of-the-art Convolutional Neural Network (CNN) architectures, and practical Bayesian inference techniques for automatic self-annotation. We propose a practical domain adaptation procedure based on k-means clustering of CNN latent variables, followed by a k-Nearest Neighbour classification for handling high label variability between different dataset distributions. Moreover, Supervised Learning has proven useful in such systems but manual annotation of large amounts of data is usually required. This is practically intractable in most real world problems due to time/labour constraints. In an attempt to address this issue, we introduce a self-annotating prediction model based on Self-Training of a Bayesian CNN, that leverages modern variational inference methods of deep models. In this context, we propose a new inverse uncertainty weighting technique that encourages the Self-Training model to learn from more informative data over time, potentially preventing it from becoming lazy by only selecting easy examples to learn from. An experimental study is presented illustrating the superior performance of the proposed approach over standard Self-Training, and highlighting the importance of predictive uncertainty estimates in safety-critical domains.

Deep neural networks (DNNs) provide state-of-the-art results for a multitude of applications, but the use of DNNs for multimodal audiovisual applications is still an unsolved problem. The current approaches that combine audiovisual information do not consider inherent uncertainty or leverage true classification confidence associated with each modality in the final decision. Our contribution in this work is to apply Bayesian variational inference to DNNs for audiovisual activity recognition and quantify model uncertainty along with principled confidence. We propose a novel approach that combines deterministic and variational layers to estimate model uncertainty and principled confidence. Our experiments with in- and out-of-distribution samples selected from a subset of the Moments-in-Time (MiT) dataset show more reliable confidence measure as compared to the non-Bayesian baseline. We also demonstrate the uncertainty estimates obtained from this framework can identify out-of-distribution data on the UCF101 and MiT datasets. In the multimodal setting, the proposed framework improved precision-recall AUC by 14.4% on the subset of MiT dataset as compared to non-Bayesian baseline.

Two major classes of numerical problems that arise in data analysis procedures are optimization and integration problems. It is not always possible to analytically compute the estimators associated with a given model, and we are often led to consider numerical solutions. One way to avoid that problem is to use simulation. Monte Carlo estimation refers to simulating hypothetical draws from a probability distribution, in order to calculate significant quantities of that distribution. The basic idea of Monte Carlo consist of writing the integral as an expected value with respect to some probability distribution, and then approximated using the method of moment estimator ($E[g(X)] \approx \overline{g(X)} \dfrac{1}{n}\sum g(X_{i})$).

In this work, we present our various contributions to the objective of building a decision support tool for the diagnosis of rare diseases. Our goal is to achieve a state of knowledge where the uncertainty about the patient's disease is below a predetermined threshold. We aim to reach such states while minimizing the average number of medical tests to perform. In doing so, we take into account the need, in many medical applications, to avoid, as much as possible, any misdiagnosis. To solve this optimization task, we investigate several reinforcement learning algorithm and make them operable in our high-dimensional and sparse-reward setting. We also present a way to combine expert knowledge, expressed as conditional probabilities, with real clinical data. This is crucial because the scarcity of data in the field of rare diseases prevents any approach based solely on clinical data. Finally we show that it is possible to integrate the ontological information about symptoms while remaining in our probabilistic reasoning. It enables our decision support tool to process information given at different level of precision by the user.

Bayesian optimization usually assumes that a Bayesian prior is given. However, the strong theoretical guarantees in Bayesian optimization are often regrettably compromised in practice because of unknown parameters in the prior. In this paper, we adopt a variant of empirical Bayes and show that, by estimating the Gaussian process prior from offline data sampled from the same prior and constructing unbiased estimators of the posterior, variants of both GP-UCB and probability of improvement achieve a near-zero regret bound, which decreases to a constant proportional to the observational noise as the number of offline data and the number of online evaluations increase. Empirically, we have verified our approach on challenging simulated robotic problems featuring task and motion planning.

In one perspective, the main theme of this research revolves around the inverse problem in the context of general rough sets that concerns the existence of rough basis for given approximations in a context. Granular operator spaces and variants were recently introduced by the present author as an optimal framework for anti-chain based algebraic semantics of general rough sets and the inverse problem. In the framework, various sub-types of crisp and non-crisp objects are identifiable that may be missed in more restrictive formalism. This is also because in the latter cases concepts of complementation and negation are taken for granted - while in reality they have a complicated dialectical basis. This motivates a general approach to dialectical rough sets building on previous work of the present author and figures of opposition. In this paper dialectical rough logics are invented from a semantic perspective, a concept of dialectical predicates is formalised, connection with dialetheias and glutty negation are established, parthood analyzed and studied from the viewpoint of classical and dialectical figures of opposition by the present author. Her methods become more geometrical and encompass parthood as a primary relation (as opposed to roughly equivalent objects) for algebraic semantics.

Parallel tempering addresses some of the drawbacks of canonical Markov Chain Monte-Carlo methods for Bayesian neural learning with the ability to utilize high performance computing. However, certain challenges remain given the large range of network parameters and big data. Surrogate-assisted optimization considers the estimation of an objective function for models given computational inefficiency or difficulty to obtain clear results. We address the inefficiency of parallel tempering for large-scale problems by combining parallel computing features with surrogate assisted estimation of likelihood function that describes the plausibility of a model parameter value, given specific observed data. In this paper, we present surrogate-assisted parallel tempering for Bayesian neural learning where the surrogates are used to estimate the likelihood. The estimation via the surrogate becomes useful rather than evaluating computationally expensive models that feature large number of parameters and datasets. Our results demonstrate that the methodology significantly lowers the computational cost while maintaining quality in decision making using Bayesian neural learning. The method has applications for a Bayesian inversion and uncertainty quantification for a broad range of numerical models.

Likelihood-free inference refers to inference when a likelihood function cannot be explicitly evaluated, which is often the case for models based on simulators. While much of the literature is concerned with sample-based'Approximate Bayesian Computation' methods, recent work suggests that approaches relying on deep neural conditional density estimators can obtain state-of-the-art results with fewer simulations. The neural approaches vary in how they choose which simulations to run and what they learn: an approximate posterior or a surrogate likelihood. This work provides some direct controlled comparisons between these choices.

Scalable Bayesian sampling is playing an important role in modern machine learning, especially in the fast-developed unsupervised-(deep)-learning models. While tremendous progresses have been achieved via scalable Bayesian sampling such as stochastic gradient MCMC (SG-MCMC) and Stein variational gradient descent (SVGD), the generated samples are typically highly correlated. Moreover, their sample-generation processes are often criticized to be inefficient. In this paper, we propose a novel self-adversarial learning framework that automatically learns a conditional generator to mimic the behavior of a Markov kernel (transition kernel). High-quality samples can be efficiently generated by direct forward passes though a learned generator. Most importantly, the learning process adopts a self-learning paradigm, requiring no information on existing Markov kernels, e.g., knowledge of how to draw samples from them. Specifically, our framework learns to use current samples, either from the generator or pre-provided training data, to update the generator such that the generated samples progressively approach a target distribution, thus it is called self-learning. Experiments on both synthetic and real datasets verify advantages of our framework, outperforming related methods in terms of both sampling efficiency and sample quality.