In this work, we propose to learn a generative model using both learned features (through a latent space) and memories (through neighbors). Although human learning makes seamless use of both learned perceptual features and instance recall, current generative learning paradigms only make use of one of these two components. Take, for instance, flow models, which learn a latent space of invertible features that follow a simple distribution. Conversely, kernel density techniques use instances to shift a simple distribution into an aggregate mixture model. Here we propose multiple methods to enhance the latent space of a flow model with neighborhood information. Not only does our proposed framework represent a more human-like approach by leveraging both learned features and memories, but it may also be viewed as a step forward in non-parametric methods. The efficacy of our model is shown empirically with standard image datasets. We observe compelling results and a significant improvement over baselines.

Euler-Maruyama and Ozaki discretization of a continuous time diffusion process is a popular technique for sampling, that uses (upto) gradient and Hessian information of the density respectively. The Euler-Maruyama discretization has been used particularly for sampling under the name of Langevin Monte Carlo (LMC) for sampling from strongly log-concave densities. In this work, we make several theoretical contributions to the literature on such sampling techniques. Specifically, we first provide a Randomized Coordinate wise LMC algorithm suitable for large-scale sampling problem and provide a theoretical analysis. We next consider the case of zeroth-order or black-box sampling where one only obtains evaluates of the density. Based on Gaussian Stein's identities we then estimate the gradient and Hessian information and leverage it in the context of black-box sampling. We provide a theoretical analysis of the proposed sampling algorithm quantifying the non-asymptotic accuracy. We also consider high-dimensional black-box sampling under the assumption that the density depends only on a small subset of the entire coordinates. We propose a variable selection technique based on zeroth-order gradient estimates and establish its theoretical guarantees. Our theoretical contribution extend the practical applicability of sampling algorithms to the large-scale, black-box and high-dimensional settings.

Like most learning algorithms, the multilayer perceptrons (MLP) is designed to learn a vector of parameters from data. However, in certain scenarios we are interested in learning structured parameters (predictions) in the form of symmetric positive definite matrices. Here, we introduce a variant of the MLP, referred to as the matrix MLP, that is specialized at learning symmetric positive definite matrices. We also present an application of the model within the context of the variational autoencoder (VAE). Our formulation of the VAE extends the vanilla formulation to the cases where the recognition and the generative networks can be from the parametric family of distributions with dense covariance matrices. Two specific examples are discussed in more detail: the dense covariance Gaussian and its generalization, the power exponential distribution. Our new developments are illustrated using both synthetic and real data.

This paper investigates the theory of robustness against adversarial attacks. It focuses on the family of randomization techniques that consist in injecting noise in the network at inference time. These techniques have proven effective in many contexts, but lack theoretical arguments. We close this gap by presenting a theoretical analysis of these approaches, hence explaining why they perform well in practice. More precisely, we provide the first result relating the randomization rate to robustness to adversarial attacks. This result applies for the general family of exponential distributions, and thus extends and unifies the previous approaches. We support our theoretical claims with a set of experiments.

Adaptive stochastic gradient algorithms in the Euclidean space have attracted much attention lately. Such explorations on Riemannian manifolds, on the other hand, are relatively new, limited, and challenging. This is because of the intrinsic non-linear structure of the underlying manifold and the absence of a canonical coordinate system. In machine learning applications, however, most manifolds of interest are represented as matrices with notions of row and column subspaces. In addition, the implicit manifold-related constraints may also lie on such subspaces. For example, the Grassmann manifold is the set of column subspaces. To this end, such a rich structure should not be lost by transforming matrices into just a stack of vectors while developing optimization algorithms on manifolds. We propose novel stochastic gradient algorithms for problems on Riemannian manifolds by adapting the row and column subspaces of gradients. Our algorithms are provably convergent and they achieve the convergence rate of order ${O}(\log (T)/\sqrt{T})$, where $T$ is the number of iterations. Our experiments illustrate that the proposed algorithms outperform existing Riemannian adaptive stochastic algorithms.

In the advent of big data era, interactive visualization of large data sets consisting of M*10^5+ high-dimensional feature vectors of length N (N ~ 10^3+), is an indispensable tool for data exploratory analysis. The state-of-the-art data embedding (DE) methods of N-D data into 2-D (3-D) visually perceptible space (e.g., based on t-SNE concept) are too demanding computationally to be efficiently employed for interactive data analytics of large and high-dimensional datasets. Herein we present a simple method, ivhd (interactive visualization of high-dimensional data tool), which radically outperforms the modern data-embedding algorithms in both computational and memory loads, while retaining high quality of N-D data embedding in 2-D (3-D). We show that DE problem is equivalent to the nearest neighbor nn-graph visualization, where only indices of a few nearest neighbors of each data sample has to be known, and binary distance between data samples -- 0 to the nearest and 1 to the other samples -- is defined. These improvements reduce the time-complexity and memory load from O(M log M) to O(M), and ensure minimal O(M) proportionality coefficient as well. We demonstrate high efficiency, quality and robustness of ivhd on popular benchmark datasets such as MNIST, 20NG, NORB and RCV1.

Despite the huge success of deep neural networks (NNs), finding good mechanisms for quantifying their prediction uncertainty is still an open problem. Bayesian neural networks are one of the most popular approaches to uncertainty quantification. On the other hand, it was recently shown that ensembles of NNs, which belong to the class of mixture models, can be used to quantify prediction uncertainty. In this paper, we build upon these two approaches. First, we increase the mixture model's flexibility by replacing the fixed mixing weights by an adaptive, input-dependent distribution (specifying the probability of each component) represented by NNs, and by considering uncountably many mixture components. The resulting class of models can be seen as the continuous counterpart to mixture density networks and is therefore referred to as compound density networks (CDNs). We employ both maximum likelihood and variational Bayesian inference to train CDNs, and empirically show that they yield better uncertainty estimates on out-of-distribution data and are more robust to adversarial examples than the previous approaches.

We consider the problem of online multiclass classification with partial feedback, where an algorithm predicts a class for a new instance in each round and only receives its correctness. Although several methods have been developed for this problem, recent challenging real-world applications require further performance improvement. In this paper, we propose a novel online learning algorithm inspired by recent work on learning from complementary labels, where a complementary label indicates a class to which an instance does not belong. This allows us to handle partial feedback deterministically in a margin-based way, where the prediction margin has been recognized as a key to superior empirical performance. We provide a theoretical guarantee based on a cumulative loss bound and experimentally demonstrate that our method outperforms existing methods which are non-margin-based and stochastic.

We propose to meta-learn causal structures based on how fast a learner adapts to new distributions arising from sparse distributional changes, e.g. due to interventions, actions of agents and other sources of non-stationarities. We show that under this assumption, the correct causal structural choices lead to faster adaptation to modified distributions because the changes are concentrated in one or just a few mechanisms when the learned knowledge is modularized appropriately. This leads to sparse expected gradients and a lower effective number of degrees of freedom needing to be relearned while adapting to the change. It motivates using the speed of adaptation to a modified distribution as a meta-learning objective. We demonstrate how this can be used to determine the cause-effect relationship between two observed variables. The distributional changes do not need to correspond to standard interventions (clamping a variable), and the learner has no direct knowledge of these interventions. We show that causal structures can be parameterized via continuous variables and learned end-to-end. We then explore how these ideas could be used to also learn an encoder that would map low-level observed variables to unobserved causal variables leading to faster adaptation out-of-distribution, learning a representation space where one can satisfy the assumptions of independent mechanisms and of small and sparse changes in these mechanisms due to actions and non-stationarities.

The electroencephalogram (EEG) provides a non-invasive, minimally restrictive, and relatively low cost measure of mesoscale brain dynamics with high temporal resolution. Although signals recorded in parallel by multiple, near-adjacent EEG scalp electrode channels are highly-correlated and combine signals from many different sources, biological and non-biological, independent component analysis (ICA) has been shown to isolate the various source generator processes underlying those recordings. Independent components (IC) found by ICA decomposition can be manually inspected, selected, and interpreted, but doing so requires both time and practice as ICs have no particular order or intrinsic interpretations and therefore require further study of their properties. Alternatively, sufficiently-accurate automated IC classifiers can be used to classify ICs into broad source categories, speeding the analysis of EEG studies with many subjects and enabling the use of ICA decomposition in near-real-time applications. While many such classifiers have been proposed recently, this work presents the ICLabel project comprised of (1) an IC dataset containing spatiotemporal measures for over 200,000 ICs from more than 6,000 EEG recordings, (2) a website for collecting crowdsourced IC labels and educating EEG researchers and practitioners about IC interpretation, and (3) the automated ICLabel classifier. The classifier improves upon existing methods in two ways: by improving the accuracy of the computed label estimates and by enhancing its computational efficiency. The ICLabel classifier outperforms or performs comparably to the previous best publicly available method for all measured IC categories while computing those labels ten times faster than that classifier as shown in a rigorous comparison against all other publicly available EEG IC classifiers.