We describe techniques for training high-quality image denoising models that require only single instances of corrupted images as training data. Inspired by a recent technique that removes the need for supervision through image pairs by employing networks with a "blind spot" in the receptive field, we address two of its shortcomings: inefficient training and somewhat disappointing final denoising performance. This is achieved through a novel blind-spot convolutional network architecture that allows efficient self-supervised training, as well as application of Bayesian distribution prediction on output colors. Together, they bring the self-supervised model on par with fully supervised deep learning techniques in terms of both quality and training speed in the case of i.i.d. Gaussian noise.

Recent developments in differentially private (DP) machine learning and DP Bayesian learning have enabled learning under strong privacy guarantees for the training data subjects. In this paper, we further extend the applicability of DP Bayesian learning by presenting the first general DP Markov chain Monte Carlo (MCMC) algorithm whose privacy-guarantees are not subject to unrealistic assumptions on Markov chain convergence and that is applicable to posterior inference in arbitrary models. Our algorithm is based on a decomposition of the Barker acceptance test that allows evaluating the R\'enyi DP privacy cost of the accept-reject choice. We further show how to improve the DP guarantee through data subsampling and approximate acceptance tests.

We present a novel family of deep neural architectures, named partially exchangeable networks (PENs) that leverage probabilistic symmetries. By design, PENs are invariant to block-switch transformations, which characterize the partial exchangeability properties of conditionally Markovian processes. Moreover, we show that any block-switch invariant function has a PEN-like representation. The DeepSets architecture is a special case of PEN and we can therefore also target fully exchangeable data. We employ PENs to learn summary statistics in approximate Bayesian computation (ABC). When comparing PENs to previous deep learning methods for learning summary statistics, our results are highly competitive, both considering time series and static models. Indeed, PENs provide more reliable posterior samples even when using less training data.

Recent studies have shown that imbalance ratio is not the only cause of the performance loss of a classifier in imbalanced data classification. In fact, other data factors, such as small disjuncts, noises and overlapping, also play the roles in tandem with imbalance ratio, which makes the problem difficult. Thus far, the empirical studies have demonstrated the relationship between the imbalance ratio and other data factors only. To the best of our knowledge, there is no any measurement about the extent of influence of class imbalance on the classification performance of imbalanced data. Further, it is also unknown for a dataset which data factor is actually the main barrier for classification. In this paper, we focus on Bayes optimal classifier and study the influence of class imbalance from a theoretical perspective. Accordingly, we propose an instance measure called Individual Bayes Imbalance Impact Index ($IBI^3$) and a data measure called Bayes Imbalance Impact Index ($BI^3$). $IBI^3$ and $BI^3$ reflect the extent of influence purely by the factor of imbalance in terms of each minority class sample and the whole dataset, respectively. Therefore, $IBI^3$ can be used as an instance complexity measure of imbalance and $BI^3$ is a criterion to show the degree of how imbalance deteriorates the classification. As a result, we can therefore use $BI^3$ to judge whether it is worth using imbalance recovery methods like sampling or cost-sensitive methods to recover the performance loss of a classifier. The experiments show that $IBI^3$ is highly consistent with the increase of prediction score made by the imbalance recovery methods and $BI^3$ is highly consistent with the improvement of F1 score made by the imbalance recovery methods on both synthetic and real benchmark datasets.

Crowdsourcing has become widely used in supervised scenarios where training sets are scarce and difficult to obtain. Most crowdsourcing models in the literature assume labelers can provide answers to full questions. In classification contexts, full questions require a labeler to discern among all possible classes. Unfortunately, discernment is not always easy in realistic scenarios. Labelers may not be experts in differentiating all classes. In this work, we provide a full probabilistic model for a shorter type of queries. Our shorter queries only require "yes" or "no" responses. Our model estimates a joint posterior distribution of matrices related to labelers' confusions and the posterior probability of the class of every object. We developed an approximate inference approach, using Monte Carlo Sampling and Black Box Variational Inference, which provides the derivation of the necessary gradients. We built two realistic crowdsourcing scenarios to test our model. The first scenario queries for irregular astronomical time-series. The second scenario relies on the image classification of animals. We achieved results that are comparable with those of full query crowdsourcing. Furthermore, we show that modeling labelers' failures plays an important role in estimating true classes. Finally, we provide the community with two real datasets obtained from our crowdsourcing experiments. All our code is publicly available.

The Helsinki Doctoral Education Network in Information and Communications Technology (HICT) is a joint initiative by Aalto University and the University of Helsinki, the two leading universities within this area in Finland. The network involves at present over 60 professors and over 200 doctoral students, and the participating units graduate altogether more than 40 new doctors each year. The quality of research and education in both HICT universities is world-class, and the education is practically free as there are no tuition fees for doctoral students in the Finnish university system. In terms of the living environment, Helsinki has been ranked as one of the world's top-10 most livable cities (Economist, 2017), and Finland is among the best countries in the world with respect to many quality of life indicators, including being the overall #1 country in human wellbeing. Helsinki is in the second place in the world's startup city comparison (Valuer, 2018) and is also the Mobile Data Capital of the World (IEEE Spectrum, 2018). The participating units of HICT have currently funding available for exceptionally qualified doctoral students. We offer the possibility to join world-class research groups, with multiple interesting research projects to choose from. If you wish to be considered as a potential new doctoral student in HICT you can apply to one or a number of doctoral student positions (listed below).

The aim of this paper is to provide new theoretical and computational understanding on two loss regularizations employed in deep learning, known as local entropy and heat regularization. For both regularized losses we introduce variational characterizations that naturally suggest a two-step scheme for their optimization, based on the iterative shift of a probability density and the calculation of a best Gaussian approximation in Kullback-Leibler divergence. Under this unified light, the optimization schemes for local entropy and heat regularized loss differ only over which argument of the Kullback-Leibler divergence is used to find the best Gaussian approximation. Local entropy corresponds to minimizing over the second argument, and the solution is given by moment matching. This allows to replace traditional back-propagation calculation of gradients by sampling algorithms, opening an avenue for gradient-free, parallelizable training of neural networks.

We propose a general test of conditional independence. The conditional predictive impact (CPI) is a provably consistent and unbiased estimator of one or several features' association with a given outcome, conditional on a (potentially empty) reduced feature set. The measure can be calculated using any supervised learning algorithm and loss function. It relies on no parametric assumptions and applies equally well to continuous and categorical predictors and outcomes. The CPI can be efficiently computed for low- or high-dimensional data without any sparsity constraints. We illustrate PAC-Bayesian convergence rates for the CPI and develop statistical inference procedures for evaluating its magnitude, significance, and precision. These tests aid in feature and model selection, extending traditional frequentist and Bayesian techniques to general supervised learning tasks. The CPI may also be used in conjunction with causal discovery algorithms to identify underlying graph structures for multivariate systems. We test our method in conjunction with various algorithms, including linear regression, neural networks, random forests, and support vector machines. Empirical results show that the CPI compares favorably to alternative variable importance measures and other nonparametric tests of conditional independence on a diverse array of real and simulated datasets. Simulations confirm that our inference procedures successfully control Type I error and achieve nominal coverage probability. Our method has been implemented in an R package, cpi, which can be downloaded from https://github.com/dswatson/cpi.

We consider the problem of differential privacy accounting, i.e. estimation of privacy loss bounds, in machine learning in a broad sense. We propose two versions of a generic privacy accountant suitable for a wide range of learning algorithms. Both versions are derived in a simple and principled way using well-known tools from probability theory, such as concentration inequalities. We demonstrate that our privacy accountant is able to achieve state-of-the-art estimates of DP guarantees and can be applied to new areas like variational inference. Moreover, we show that the latter enjoys differential privacy at minor cost.

The notion of flat minima has played a key role in the generalization studies of deep learning models. However, existing definitions of the flatness are known to be sensitive to the rescaling of parameters. The issue suggests that the previous definitions of the flatness might not be a good measure of generalization, because generalization is invariant to such rescalings. In this paper, from the PAC-Bayesian perspective, we scrutinize the discussion concerning the flat minima and introduce the notion of normalized flat minima, which is free from the known scale dependence issues. Additionally, we highlight the scale dependence of existing matrix-norm based generalization error bounds similar to the existing flat minima definitions. Our modified notion of the flatness does not suffer from the insufficiency, either, suggesting it might provide better hierarchy in the hypothesis class.