Capsule neural networks replace simple, scalar-valued neurons with vector-valued capsules. They are motivated by the pattern recognition system in the human brain, where complex objects are decomposed into a hierarchy of simpler object parts. Such a hierarchy is referred to as a parse-tree. Conceptually, capsule neural networks have been defined to mimic this behavior. The capsule neural network (CapsNet), by Sabour, Frosst, and Hinton, is the first actual implementation of the conceptual idea of capsule neural networks. CapsNets achieved state-of-the-art performance on simple image recognition tasks with fewer parameters and greater robustness to affine transformations than comparable approaches. This sparked extensive follow-up research. However, despite major efforts, no work was able to scale the CapsNet architecture to more reasonable-sized datasets. Here, we provide a reason for this failure and argue that it is most likely not possible to scale CapsNets beyond toy examples. In particular, we show that the concept of a parse-tree, the main idea behind capsule neuronal networks, is not present in CapsNets. We also show theoretically and experimentally that CapsNets suffer from a vanishing gradient problem that results in the starvation of many capsules during training.

The Gaussian mixture model (GMM) describes the distribution of random variables from several different populations. GMMs have widespread applications in probability theory, statistics, machine learning for unsupervised cluster analysis and topic modeling, as well as in deep learning pipelines. So far, few efforts have been made to explore the underlying point distribution in combination with the GMMs, in particular when the data becomes high-dimensional and when the GMMs are composed of many Gaussians. We present an analysis tool comprising various GPU-based visualization techniques to explore such complex GMMs. To facilitate the exploration of high-dimensional data, we provide a novel navigation system to analyze the underlying data. Instead of projecting the data to 2D, we utilize interactive 3D views to better support users in understanding the spatial arrangements of the Gaussian distributions. The interactive system is composed of two parts: (1) raycasting-based views that visualize cluster memberships, spatial arrangements, and support the discovery of new modes. (2) overview visualizations that enable the comparison of Gaussians with each other, as well as small multiples of different choices of basis vectors. Users are supported in their exploration with customization tools and smooth camera navigations. Our tool was developed and assessed by five domain experts, and its usefulness was evaluated with 23 participants. To demonstrate the effectiveness, we identify interesting features in several data sets.

Topic models are characterized by a latent class variable that represents the different topics. Traditionally, their observable variables are modeled as discrete variables like, for instance, in the prototypical latent Dirichlet allocation (LDA) topic model. In LDA, words in text documents are encoded by discrete count vectors with respect to some dictionary. The classical approach for learning topic models optimizes a likelihood function that is non-concave due to the presence of the latent variable. Hence, this approach mostly boils down to using search heuristics like the EM algorithm for parameter estimation. Recently, it was shown that topic models can be learned with strong algorithmic and statistical guarantees through Pearson's method of moments. Here, we extend this line of work to topic models that feature discrete as well as continuous observable variables (features). Moving beyond discrete variables as in LDA allows for more sophisticated features and a natural extension of topic models to other modalities than text, like, for instance, images. We provide algorithmic and statistical guarantees for the method of moments applied to the extended topic model that we corroborate experimentally on synthetic data. We also demonstrate the applicability of our model on real-world document data with embedded images that we preprocess into continuous state-of-the-art feature vectors.

Most problems from classical machine learning can be cast as an optimization problem. We introduce GENO (GENeric Optimization), a framework that lets the user specify a constrained or unconstrained optimization problem in an easy-to-read modeling language. GENO then generates a solver, i.e., Python code, that can solve this class of optimization problems. The generated solver is usually as fast as hand-written, problem-specific, and well-engineered solvers. Often the solvers generated by GENO are faster by a large margin compared to recently developed solvers that are tailored to a specific problem class.An online interface to our framework can be found at http://www.geno-project.org.

Computing derivatives of tensor expressions, also known as tensor calculus, is a fundamental task in machine learning. A key concern is the efficiency of evaluating the expressions and their derivatives that hinges on the representation of these expressions. Recently, an algorithm for computing higher order derivatives of tensor expressions like Jacobians or Hessians has been introduced that is a few orders of magnitude faster than previous state-of-the-art approaches. Unfortunately, the approach is based on Ricci notation and hence cannot be incorporated into automatic differentiation frameworks like TensorFlow, PyTorch, autograd, or JAX that use the simpler Einstein notation. This leaves two options, to either change the underlying tensor representation in these frameworks or to develop a new, provably correct algorithm based on Einstein notation. Obviously, the first option is impractical. Hence, we pursue the second option. Here, we show that using Ricci notation is not necessary for an efficient tensor calculus and develop an equally efficient method for the simpler Einstein notation. It turns out that turning to Einstein notation enables further improvements that lead to even better efficiency.

Computing derivatives of tensor expressions, also known as tensor calculus, is a fundamental task in machine learning. A key concern is the efficiency of evaluating the expressions and their derivatives that hinges on the representation of these expressions. Recently, an algorithm for computing higher order derivatives of tensor expressions like Jacobians or Hessians has been introduced that is a few orders of magnitude faster than previous state-of-the-art approaches. Unfortunately, the approach is based on Ricci notation and hence cannot be incorporated into automatic differentiation frameworks from deep learning like TensorFlow, PyTorch, autograd, or JAX that use the simpler Einstein notation. This leaves two options, to either change the underlying tensor representation in these frameworks or to develop a new, provably correct algorithm based on Einstein notation. Obviously, the first option is impractical. Hence, we pursue the second option. Here, we show that using Ricci notation is not necessary for an efficient tensor calculus and develop an equally efficient method for the simpler Einstein notation. It turns out that turning to Einstein notation enables further improvements that lead to even better efficiency. The methods that are described in this paper for computing derivatives of matrix and tensor expressions have been implemented in the online tool www.MatrixCalculus.org .

Although optimization is the longstanding, algorithmic backbone of machine learning new models still require the time-consuming implementation of new solvers. As a result, there are thousands of implementations of optimization algorithms for machine learning problems. A natural question is, if it is always necessary to implement a new solver, or is there one algorithm that is sufficient for most models. Common belief suggests that such a one-algorithm-fits-all approach cannot work, because this algorithm cannot exploit model specific structure. At least, a generic algorithm cannot be efficient and robust on a wide variety of problems. Here, we challenge this common belief. We have designed and implemented the optimization framework GENO (GENeric Optimization) that combines a modeling language with a generic solver. GENO takes the declaration of an optimization problem and generates a solver for the specified problem class. The framework is flexible enough to encompass most of the classical machine learning problems. We show on a wide variety of classical but also some recently suggested problems that the automatically generated solvers are (1) as efficient as well engineered, specialized solvers, (2) more efficient by a decent margin than recent state-of-the-art solvers, and (3) orders of magnitude more efficient than classical modeling language plus solver approaches.

Optimization is an integral part of most machine learning systems and most numerical optimization schemes rely on the computation of derivatives. Therefore, frameworks for computing derivatives are an active area of machine learning research. Surprisingly, as of yet, no existing framework is capable of computing higher order matrix and tensor derivatives directly. Here, we close this fundamental gap and present an algorithmic framework for computing matrix and tensor derivatives that extends seamlessly to higher order derivatives. The framework can be used for symbolic as well as for forward and reverse mode automatic differentiation. Experiments show a speedup between one and four orders of magnitude over state-of-the-art frameworks when evaluating higher order derivatives.