Hypothesis testing is an important problem with applications in target localization, clinical trials etc. Many active hypothesis testing strategies operate in two phases: an exploration phase and a verification phase. In the exploration phase, selection of experiments is such that a moderate level of confidence on the true hypothesis is achieved. Subsequent experiment design aims at improving the confidence level on this hypothesis to the desired level. In this paper, the focus is on the verification phase. A confidence measure is defined and active hypothesis testing is formulated as a confidence maximization problem in an infinite-horizon average-reward Partially Observable Markov Decision Process (POMDP) setting. The problem of maximizing confidence conditioned on a particular hypothesis is referred to as the hypothesis verification problem. The relationship between hypothesis testing and verification problems is established. The verification problem can be formulated as a Markov Decision Process (MDP). Optimal solutions for the verification MDP are characterized and a simple heuristic adaptive strategy for verification is proposed based on a zero-sum game interpretation of Kullback-Leibler divergences. It is demonstrated through numerical experiments that the heuristic performs better in some scenarios compared to existing methods in literature.

Markov networks are widely used in many Machine Learning applications including natural language processing, computer vision, and bioinformatics . Learning Markov networks have many complications ranging from intractable computations involved to the possibility of learning a model with a huge number of parameters. In this report, we provide a computationally tractable greedy heuristic for learning Markov networks structure. The proposed heuristic results in a model with a limited predefined number of parameters. We ran our method on 3 fully-observed real datasets, and we observed that our method is doing comparably good to the state of the art methods.

An agent with an inaccurate model of its environment faces a difficult choice: it can ignore the errors in its model and act in the real world in whatever way it determines is optimal with respect to its model. Alternatively, it can take a more conservative stance and eschew its model in favor of optimizing its behavior solely via real-world interaction. This latter approach can be exceedingly slow to learn from experience, while the former can lead to "planner overfitting" - aspects of the agent's behavior are optimized to exploit errors in its model. This paper explores an intermediate position in which the planner seeks to avoid overfitting through a kind of regularization of the plans it considers. We present three different approaches that demonstrably mitigate planner overfitting in reinforcement-learning environments.

We introduce a genetic algorithm that designs quantum optics experiments for engineering quantum states with specific properties. Our algorithm is powerful and flexible, and can easily be modified to find methods of engineering states for a range of applications. Here we focus on quantum metrology. First, we consider the noise-free case, and use the algorithm to find quantum states with a large quantum Fisher information (QFI). We find methods, which only involve experimental elements that are available with current technology, for engineering quantum states with up to a 100-fold improvement over the best classical state, and a 20-fold improvement over the optimal Gaussian state. Such states are a superposition of the vacuum with a large number of photons (around 80), and can hence be seen as Schr\"odinger-cat-like states. We then apply the two most dominant noise sources in our setting -- photon loss and imperfect heralding -- and use the algorithm to find quantum states that still improve over the optimal Gaussian state with realistic levels of noise. This will open up experimental and technological work in using exotic non-Gaussian states for quantum-enhanced phase measurements. Finally, we use the Bayesian mean square error to look beyond the regime of validity of the QFI, finding quantum states with precision enhancements over the alternatives even when the experiment operates in the regime of limited data.

The ability for autonomous agents to learn and conform to human norms is crucial for their safety and effectiveness in social environments. While recent work has led to frameworks for the representation and inference of simple social rules, research into norm learning remains at an exploratory stage. Here, we present a robotic system capable of representing, learning, and inferring ownership relations and norms. Ownership is represented as a graph of probabilistic relations between objects and their owners, along with a database of predicate-based norms that constrain the actions permissible on owned objects. To learn these norms and relations, our system integrates (i) a novel incremental norm learning algorithm capable of both one-shot learning and induction from specific examples, (ii) Bayesian inference of ownership relations in response to apparent rule violations, and (iii) percept-based prediction of an object's likely owners. Through a series of simulated and real-world experiments, we demonstrate the competence and flexibility of the system in performing object manipulation tasks that require a variety of norms to be followed, laying the groundwork for future research into the acquisition and application of social norms.

Recently, compression and acceleration of deep neural networks are in critic need. Bayesian generalization of structured pruning represents an important research direction to solve the above problem. However, the existing Bayesian methods ignore the dependency among neurons and filters for computational simplicity. In this study, we explore, under Bayesian framework, a structured pruning method with layer-wise sequential dependency assumed, a more general learning setting. Based on the property of Dirac distribution, we further derive a new dropout noise, which makes it possible to approximate the posterior of dropout noise knowing that of the previous layer. With the Dirac-like dropout noise, we further propose a recursive strategy, named \emph{Recursive Bayesian Pruning} (RBP), to train and prune networks in a layer-by-layer fashion. The unimportant neurons and filters are directly targeted and removed, taking the influence from the previous layer. Experiments on typical neural networks LeNet-300-100, LeNet-5 and VGG-16 have demonstrated the proposed method are competitive with or even outperform the state-of-the-art methods in several compression and acceleration metrics.

Labeling training data is one of the most costly bottlenecks in developing or modifying machine learning-based applications. We survey how resources from across an organization can be used as weak supervision sources for three classification tasks at Google, in order to bring development time and cost down by an order of magnitude. We build on the Snorkel framework, extending it as a new system, Snorkel DryBell, which integrates with Google's distributed production systems and enables engineers to develop and execute weak supervision strategies over millions of examples in less than thirty minutes. We find that Snorkel DryBell creates classifiers of comparable quality to ones trained using up to tens of thousands of hand-labeled examples, in part by leveraging organizational resources not servable in production which contribute an average 52% performance improvement to the weakly supervised classifiers.

Modeling disease progression in healthcare administrative databases is complicated by the fact that patients are observed only at irregular intervals when they seek healthcare services. In a longitudinal cohort of 76,888 patients with chronic obstructive pulmonary disease (COPD), we used a continuous-time hidden Markov model with a generalized linear model to model healthcare utilization events. We found that the fitted model provides interpretable results suitable for summarization and hypothesis generation.

The ability to learn and act in novel situations is still a prerogative of animate intelligence, as current machine learning methods mostly fail when moving beyond the standard i.i.d. setting. What is the reason for this discrepancy? Most machine learning tasks are anti-causal, i.e., we infer causes (labels) from effects (observations). Typically, in supervised learning we build systems that try to directly invert causal mechanisms. Instead, in this paper we argue that strong generalization capabilities crucially hinge on searching and validating meaningful hypotheses, requiring access to a causal model. In such a framework, we want to find a cause that leads to the observed effect. Anti-causal models are used to drive this search, but a causal model is required for validation. We investigate the fundamental differences between causal and anti-causal tasks, discuss implications for topics ranging from adversarial attacks to disentangling factors of variation, and provide extensive evidence from the literature to substantiate our view. We advocate for incorporating causal models in supervised learning to shift the paradigm from inference only, to search and validation.

Early detection of Alzheimer's disease (AD) and identification of potential risk/beneficial factors are important for planning and administering timely interventions or preventive measures. In this paper, we learn a disease model for AD that combines genotypic and phenotypic profiles, and cognitive health metrics of patients. We propose a probabilistic generative subspace that describes the correlative, complementary and domain-specific semantics of the dependencies in multi-view, multi-modality medical data. Guided by domain knowledge and using the latent consensus between abstractions of multi-view data, we model the fusion as a data generating process. We show that our approach can potentially lead to i) explainable clinical predictions and ii) improved AD diagnoses.