Specifying a Reinforcement Learning (RL) task involves choosing a suitable planning horizon, which is typically modeled by a discount factor. It is known that applying RL algorithms with a lower discount factor can act as a regularizer, improving performance in the limited data regime. Yet the exact nature of this regularizer has not been investigated. In this work, we fill in this gap. For several Temporal-Difference (TD) learning methods, we show an explicit equivalence between using a reduced discount factor and adding an explicit regularization term to the algorithm's loss. Motivated by the equivalence, we empirically study this technique compared to standard $L_2$ regularization by extensive experiments in discrete and continuous domains, using tabular and functional representations. Our experiments suggest the regularization effectiveness is strongly related to properties of the available data, such as size, distribution, and mixing rate.

We propose and study Collpasing Bandits, a new restless multi-armed bandit (RMAB) setting in which each arm follows a binary-state Markovian process with a special structure: when an arm is played, the state is fully observed, thus "collapsing" any uncertainty, but when an arm is passive, no observation is made, thus allowing uncertainty to evolve. The goal is to keep as many arms in the "good" state as possible by planning a limited budget of actions per round. Such Collapsing Bandits are natural models for many healthcare domains in which workers must simultaneously monitor patients and deliver interventions in a way that maximizes the health of their patient cohort. Our main contributions are as follows: (i) Building on the Whittle index technique for RMABs, we derive conditions under which the Collapsing Bandits problem is indexable. Our derivation hinges on novel conditions that characterize when the optimal policies may take the form of either "forward" or "reverse" threshold policies. (ii) We exploit the optimality of threshold policies to build fast algorithms for computing the Whittle index, including a closed-form. (iii) We evaluate our algorithm on several data distributions including data from a real-world healthcare task in which a worker must monitor and deliver interventions to maximize their patients' adherence to tuberculosis medication. Our algorithm achieves a 3-order-of-magnitude speedup compared to state-of-the-art RMAB techniques while achieving similar performance.

Modern genomic studies are increasingly focused on identifying more and more genes clinically associated with a health response. Commonly used Bayesian shrinkage priors are designed primarily to detect only a handful of signals when the dimension of the predictors is very high. In this article, we investigate the performance of a popular continuous shrinkage prior in the presence of relatively large number of true signals. We draw attention to an undesirable phenomenon; the posterior mean is rendered very close to a null vector, caused by a sharp underestimation of the global-scale parameter. The phenomenon is triggered by the absence of a tail-index controlling mechanism in the Bayesian shrinkage priors. We provide a remedy by developing a global-local-tail shrinkage prior which can automatically learn the tail-index and can provide accurate inference even in the presence of moderately large number of signals. The collapsing behavior of the Horseshoe with its remedy is exemplified in numerical examples and in two gene expression datasets.

We are all familiar with the dictum that "correlation does not imply causation". Furthermore, given a data file with samples of two variables x and z, we all know how to calculate the correlation between x and z. But it's only an elite minority, the few, the proud, the Bayesian Network aficionados, that know how to calculate the causal connection between x and z. Neural Net aficionados are incapable of doing this. Their Neural nets are just too wimpy to cut it.

Humans learn all their life long. They accumulate knowledge from a sequence of learning experiences and remember the essential concepts without forgetting what they have learned previously. Artificial neural networks struggle to learn similarly. They often rely on data rigorously preprocessed to learn solutions to specific problems such as classification or regression. In particular, they forget their past learning experiences if trained on new ones. Therefore, artificial neural networks are often inept to deal with real-life settings such as an autonomous-robot that has to learn on-line to adapt to new situations and overcome new problems without forgetting its past learning-experiences. Continual learning (CL) is a branch of machine learning addressing this type of problem. Continual algorithms are designed to accumulate and improve knowledge in a curriculum of learning-experiences without forgetting. In this thesis, we propose to explore continual algorithms with replay processes. Replay processes gather together rehearsal methods and generative replay methods. Generative Replay consists of regenerating past learning experiences with a generative model to remember them. Rehearsal consists of saving a core-set of samples from past learning experiences to rehearse them later. The replay processes make possible a compromise between optimizing the current learning objective and the past ones enabling learning without forgetting in sequences of tasks settings. We show that they are very promising methods for continual learning. Notably, they enable the re-evaluation of past data with new knowledge and the confrontation of data from different learning-experiences. We demonstrate their ability to learn continually through unsupervised learning, supervised learning and reinforcement learning tasks.

Human learning and intelligence work differently from the supervised pattern recognition approach adopted in most deep learning architectures. Humans seem to learn rich representations by exploration and imitation, build causal models of the world, and use both to flexibly solve new tasks. We suggest a simple but effective unsupervised model which develops such characteristics. The agent learns to represent the dynamical physical properties of its environment by intrinsically motivated exploration, and performs inference on this representation to reach goals. For this, a set of self-organizing maps which represent state-action pairs is combined with a causal model for sequence prediction. The proposed system is evaluated in the cartpole environment. After an initial phase of playful exploration, the agent can execute kinematic simulations of the environment's future, and use those for action planning. We demonstrate its performance on a set of several related, but different one-shot imitation tasks, which the agent flexibly solves in an active inference style.

Variational Bayes (VB) has been used to facilitate the calculation of the posterior distribution in the context of Bayesian inference of the parameters of nonlinear models from data. Previously an analytical formulation of VB has been derived for nonlinear model inference on data with additive gaussian noise as an alternative to nonlinear least squares. Here a stochastic solution is derived that avoids some of the approximations required of the analytical formulation, offering a solution that can be more flexibly deployed for nonlinear model inference problems. The stochastic VB solution was used for inference on a biexponential toy case and the algorithmic parameter space explored, before being deployed on real data from a magnetic resonance imaging study of perfusion. The new method was found to achieve comparable parameter recovery to the analytic solution and be competitive in terms of computational speed despite being reliant on sampling.

Bayesian network (BN) structure learning from complete data has been extensively studied in the literature. However, fewer theoretical results are available for incomplete data, and most are based on the use of the Expectation-Maximisation (EM) algorithm. Balov (2013) proposed an alternative approach called Node-Average Likelihood (NAL) that is competitive with EM but computationally more efficient; and proved its consistency and model identifiability for discrete BNs. In this paper, we give general sufficient conditions for the consistency of NAL; and we prove consistency and identifiability for conditional Gaussian BNs, which include discrete and Gaussian BNs as special cases. Hence NAL has a wider applicability than originally stated in Balov (2013).

We present a new method for linear and nonlinear, lagged and contemporaneous constraint-based causal discovery from observational time series in the presence of latent confounders. We show that existing causal discovery methods such as FCI and variants suffer from low recall in the autocorrelated time series case and identify low effect size of conditional independence tests as the main reason. Information-theoretical arguments show that effect size can often be increased if causal parents are included in the conditioning sets. To identify parents early on, we suggest an iterative procedure that utilizes novel orientation rules to determine ancestral relationships already during the edge removal phase. We prove that the method is order-independent, and sound and complete in the oracle case. Extensive simulation studies for different numbers of variables, time lags, sample sizes, and further cases demonstrate that our method indeed achieves much higher recall than existing methods while keeping false positives at the desired level. This performance gain grows with stronger autocorrelation. Our method also covers causal discovery for non-time series data as a special case. We provide Python code for all methods involved in the simulation studies.

We first consider the sources of uncertainty in NNs, and briefly review Bayesian Neural Networks (BNN), the group of Bayesian approaches to tackle uncertainties in NNs. After presenting mathematical formulation of MC dropout, we proceed to suggesting potential benefits and associated costs for using MC dropout in typical NN models, with the results from our experiments.