In this research work, probabilistic decision-making approaches are studied, e.g. Bayesian and Boltzmann strategies, along with various deterministic exploration strategies, e.g. greedy, epsilon-Greedy and random approaches. In this research work, a comparative study has been done between probabilistic and deterministic decision-making approaches, the experiments are performed in OpenAI gym environment, solving Cart Pole problem. This research work discusses about the Bayesian approach to decision-making in deep reinforcement learning, and about dropout, how it can reduce the computational cost. All the exploration approaches are compared. It also discusses about the importance of exploration in deep reinforcement learning, and how improving exploration strategies may help in science and technology. This research work shows how probabilistic decision-making approaches are better in the long run as compared to the deterministic approaches. When there is uncertainty, Bayesian dropout approach proved to be better than all other approaches in this research work.

We present a new generalization error bound, the \emph{PAC-Bayesian transportation bound}, unifying the PAC-Bayesian analysis and the generic chaining method in view of the optimal transportation. The proposed bound is the first PAC-Bayesian framework that characterizes the cost of de-randomization of stochastic predictors facing any Lipschitz loss functions. As an example, we give an upper bound on the de-randomization cost of spectrally normalized neural networks~(NNs) to evaluate how much randomness contributes to the generalization of NNs.

We propose a framework for the greedy approximation of high-dimensional Bayesian inference problems, through the composition of multiple \emph{low-dimensional} transport maps or flows. Our framework operates recursively on a sequence of ``residual'' distributions, given by pulling back the posterior through the previously computed transport maps. The action of each map is confined to a low-dimensional subspace that we identify by minimizing an error bound. At each step, our approach thus identifies (i) a relevant subspace of the residual distribution, and (ii) a low-dimensional transformation between a restriction of the residual onto this subspace and a standard Gaussian. We prove weak convergence of the approach to the posterior distribution, and we demonstrate the algorithm on a range of challenging inference problems in differential equations and spatial statistics.

Many mathematical imaging problems are posed as non-convex optimization problems. When numerically tractable global optimization procedures are not available, one is often interested in testing ex post facto whether or not a locally convergent algorithm has found the globally optimal solution. If the problem has a statistical maximum likelihood formulation, a local test of global optimality can be constructed. In this paper, we develop an improved test, based on a global maximum validation function proposed by Biernacki, under the assumption that the statistical distribution is in the generalized location family, a condition often satisfied in imaging problems. In addition, a new reparameterization and embedding procedure is presented that exploits knowledge about the forward operator to improve the global maximum validation function. Finally, the reparameterized embedding technique is applied to a physically-motivated joint-inverse problem arising in camera blur estimation. The advantages of the proposed global optimum testing techniques are numerically demonstrated in terms of increased detection accuracy and reduced computation.

In recent years, impressive progress has been made in the design of implicit probabilistic models via Generative Adversarial Networks (GAN) and its extension, the Conditional GAN (CGAN). Excellent solutions have been demonstrated mostly in image processing applications which involve large, continuous output spaces. There is almost no application of these powerful tools to problems having small dimensional output spaces. Regression problems involving the inductive learning of a map, $y=f(x,z)$, $z$ denoting noise, $f:\mathbb{R}^n\times \mathbb{R}^k \rightarrow \mathbb{R}^m$, with $m$ small (e.g., $m=1$ or just a few) is one good case in point. The standard approach to solve regression problems is to probabilistically model the output $y$ as the sum of a mean function $m(x)$ and a noise term $z$; it is also usual to take the noise to be a Gaussian. These are done for convenience sake so that the likelihood of observed data is expressible in closed form. In the real world, on the other hand, stochasticity of the output is usually caused by missing or noisy input variables. Such a real world situation is best represented using an implicit model in which an extra noise vector, $z$ is included with $x$ as input. CGAN is naturally suited to design such implicit models. This paper makes the first step in this direction. Through several artificial and real world datasets, we demonstrate CGAN to be an effective approach for solving regression problems. We compare against Gaussian Processes and show that CGAN has excellent output likelihood properties and possesses the ability to model complex noise forms in a better way.

We present a novel approach for motion planning in mobile robotics under sensing and motion uncertainty based on state lattices with graduated fidelity. The probability of collision is reliably estimated considering the robot shape, and the fidelity adapts to the complexity of the environment, improving the planning efficiency while maintaining the performance. Safe and optimal paths are found with an informed search algorithm, for which a novel multi-resolution heuristic is presented. Results for different scenarios and robot shapes are given, showing the validity of the proposed methods.

The ability of overparameterized deep networks to generalize well has been linked to the fact that stochastic gradient descent (SGD) finds solutions that lie in flat, wide minima in the training loss -- minima where the output of the network is resilient to small random noise added to its parameters. So far this observation has been used to provide generalization guarantees only for neural networks whose parameters are either \textit{stochastic} or \textit{compressed}. In this work, we present a general PAC-Bayesian framework that leverages this observation to provide a bound on the original network learned -- a network that is deterministic and uncompressed. What enables us to do this is a key novelty in our approach: our framework allows us to show that if on training data, the interactions between the weight matrices satisfy certain conditions that imply a wide training loss minimum, these conditions themselves {\em generalize} to the interactions between the matrices on test data, thereby implying a wide test loss minimum. We then apply our general framework in a setup where we assume that the pre-activation values of the network are not too small (although we assume this only on the training data). In this setup, we provide a generalization guarantee for the original (deterministic, uncompressed) network, that does not scale with product of the spectral norms of the weight matrices -- a guarantee that would not have been possible with prior approaches.

Given unpaired data from multiple domains, a key challenge is to efficiently exploit these data sources for modeling a target domain. Variants of this problem have been studied in many contexts, such as cross-domain translation and domain adaptation. We propose AlignFlow, a generative modeling framework for learning from multiple domains via normalizing flows. The use of normalizing flows in AlignFlow allows for a) flexibility in specifying learning objectives via adversarial training, maximum likelihood estimation, or a hybrid of the two methods; and b) exact inference of the shared latent factors across domains at test time. We derive theoretical results for the conditions under which AlignFlow guarantees marginal consistency for the different learning objectives. Furthermore, we show that AlignFlow guarantees exact cycle consistency in mapping datapoints from one domain to another. Empirically, AlignFlow can be used for data-efficient density estimation given multiple data sources and shows significant improvements over relevant baselines on unsupervised domain adaptation.

Active learning (AL) concerns itself with learning a model from as few labelled data as possible through actively and iteratively querying an oracle with selected unlabelled samples. In this paper, we focus on a popular type of AL in which the utility of a sample is measured by a specified goal achieved by the retrained model after accounting for the sample's marginal influence. Such AL strategies attract a lot of attention thanks to their intuitive motivations, yet they typically suffer from impractically high computational costs due to their need for many iterations of model retraining. With the help of influence functions, we present an effective approximation that bypasses model retraining altogether, and propose a general efficient implementation that makes such AL strategies applicable in practice, both in the serial and the more challenging batch-mode setting. Additionally, we present theoretical analyses which call into question a common practice widely adopted in the field. Finally, we carry out empirical studies with both synthetic and real-world datasets to validate our discoveries as well as showcase the potentials and issues with such goal-oriented AL strategies.

We show that deep networks are better than shallow networks at approximating functions that can be expressed as a composition of functions described by a directed acyclic graph, because the deep networks can be designed to have the same compositional structure, while a shallow network cannot exploit this knowledge. Thus, the blessing of compositionality mitigates the curse of dimensionality. On the other hand, a theorem called good propagation of errors allows to `lift' theorems about shallow networks to those about deep networks with an appropriate choice of norms, smoothness, etc. We illustrate this in three contexts where each channel in the deep network calculates a spherical polynomial, a non-smooth ReLU network, or another zonal function network related closely with the ReLU network.