Structural equation models provide a quintessential framework for conducting causal inference in statistics, econometrics, machine learning (ML), and other data sciences. The package DoubleML for R (R Core Team, 2020) implements partially linear and interactive structural equation and treatment effect models with high-dimensional confounding variables as considered in Chernozhukov et al. (2018). Estimation and tuning of the machine learning models is based on the powerful functionalities provided by the mlr3 package and the mlr3 ecosystem (Lang et al., 2019). A key element of double machine learning (DML) models are score functions identifying the estimates for the target parameter. These functions play an essential role for valid inference with machine learning methods because they have to satisfy a property called Neyman orthogonality. With the score functions as key elements, DoubleML implements double machine learning in a very general way using object orientation based on the R6 package (Chang, 2020). Currently, DoubleML implements the double / debiased machine learning framework as established in Chernozhukov et al. (2018) for - partially linear regression models (PLR), - partially linear instrumental variable regression models (PLIV), - interactive regression models (IRM), and - interactive instrumental variable regression models (IIVM). The object-oriented implementation of DoubleML is very flexible. The model classes DoubleMLPLR, DoubleMLPLIV, DoubleMLIRM and DoubleIIVM implement the estimation of the nuisance functions via machine learning methods and the computation of the Neyman-orthogonal score function.

The problem of classifying high-dimensional shapes in real-world data grows in complexity as the dimension of the space increases. For the case of identifying convex shapes of different geometries, a new classification framework has recently been proposed in which the intersections of a set of one-dimensional representations, called rays, with the boundaries of the shape are used to identify the specific geometry. This ray-based classification (RBC) has been empirically verified using a synthetic dataset of two- and three-dimensional shapes [1] and, more recently, has also been validated experimentally [2]. Here, we establish a bound on the number of rays necessary for shape classification, defined by key angular metrics, for arbitrary convex shapes. For two dimensions, we derive a lower bound on the number of rays in terms of the shape's length, diameter, and exterior angles. For convex polytopes in R^N, we generalize this result to a similar bound given as a function of the dihedral angle and the geometrical parameters of polygonal faces. This result enables a different approach for estimating high-dimensional shapes using substantially fewer data elements than volumetric or surface-based approaches.

The brain performs unsupervised learning and (perhaps) simultaneous supervised learning. This raises the question as to whether a hybrid of supervised and unsupervised methods will produce better learning. Inspired by the rich space of Hebbian learning rules, we set out to directly learn the unsupervised learning rule on local information that best augments a supervised signal. We present the Hebbian-augmented training algorithm (HAT) for combining gradient-based learning with an unsupervised rule on pre-synpatic activity, post-synaptic activities, and current weights. We test HAT's effect on a simple problem (Fashion-MNIST) and find consistently higher performance than supervised learning alone. This finding provides empirical evidence that unsupervised learning on synaptic activities provides a strong signal that can be used to augment gradient-based methods. We further find that the meta-learned update rule is a time-varying function; thus, it is difficult to pinpoint an interpretable Hebbian update rule that aids in training. We do find that the meta-learner eventually degenerates into a non-Hebbian rule that preserves important weights so as not to disturb the learner's convergence.

Since its introduction a decade ago, \emph{relative entropy policy search} (REPS) has demonstrated successful policy learning on a number of simulated and real-world robotic domains, not to mention providing algorithmic components used by many recently proposed reinforcement learning (RL) algorithms. While REPS is commonly known in the community, there exist no guarantees on its performance when using stochastic and gradient-based solvers. In this paper we aim to fill this gap by providing guarantees and convergence rates for the sub-optimality of a policy learned using first-order optimization methods applied to the REPS objective. We first consider the setting in which we are given access to exact gradients and demonstrate how near-optimality of the objective translates to near-optimality of the policy. We then consider the practical setting of stochastic gradients, and introduce a technique that uses \emph{generative} access to the underlying Markov decision process to compute parameter updates that maintain favorable convergence to the optimal regularized policy.

Recent works in Generative Adversarial Networks (GANs) are actively revisiting various data augmentation techniques as an effective way to prevent discriminator overfitting. It is still unclear, however, that which augmentations could actually improve GANs, and in particular, how to apply a wider range of augmentations in training. In this paper, we propose a novel way to address these questions by incorporating a recent contrastive representation learning scheme into the GAN discriminator, coined ContraD. This "fusion" enables the discriminators to work with much stronger augmentations without increasing their training instability, thereby preventing the discriminator overfitting issue in GANs more effectively. Even better, we observe that the contrastive learning itself also benefits from our GAN training, i.e., by maintaining discriminative features between real and fake samples, suggesting a strong coherence between the two worlds: good contrastive representations are also good for GAN discriminators, and vice versa. Our experimental results show that GANs with ContraD consistently improve FID and IS compared to other recent techniques incorporating data augmentations, still maintaining highly discriminative features in the discriminator in terms of the linear evaluation. Finally, as a byproduct, we also show that our GANs trained in an unsupervised manner (without labels) can induce many conditional generative models via a simple latent sampling, leveraging the learned features of ContraD. Generative adversarial networks (GANs) (Goodfellow et al., 2014) have become one of the most prominent approaches for generative modeling with a wide range of applications (Ho & Ermon, 2016; Zhu et al., 2017; Karras et al., 2019; Rott Shaham et al., 2019). In general, a GAN is defined by a minimax game between two neural networks: a generator network that maps a random vector into the data domain, and a discriminator network that classifies whether a given sample is real (from the training dataset) or fake (from the generator).

This paper proposes a new distance metric function, called Z distance, for KNN classification. The Z distance function is not a geometric direct-line distance between two data points. It gives a consideration to the class attribute of a training dataset when measuring the affinity between data points. Concretely speaking, the Z distance of two data points includes their class center distance and real distance. And its shape looks like "Z". In this way, the affinity of two data points in the same class is always stronger than that in different classes. Or, the intraclass data points are always closer than those interclass data points. We evaluated the Z distance with experiments, and demonstrated that the proposed distance function achieved better performance in KNN classification.

Machine learning on sets towards sequential output is an important and ubiquitous task, with applications ranging from language modelling and meta-learning to multi-agent strategy games and power grid optimization. Combining elements of representation learning and structured prediction, its two primary challenges include obtaining a meaningful, permutation invariant set representation and subsequently utilizing this representation to output a complex target permutation. This paper provides a comprehensive introduction to the field as well as an overview of important machine learning methods tackling both of these key challenges, with a detailed qualitative comparison of selected model architectures.

Researchers at Tampere University have successfully used artificial intelligence to predict nonlinear dynamics that take place when ultrashort light pulses interact with matter. This novel solution can be used for efficient and fast numerical modeling, for example, in imaging, manufacturing and surgery. The findings were published in the prestigious Nature Machine Intelligence journal. Artificial intelligence can distinguish different types of laser pulse propagation, just as it recognizes subtle differences of expression in facial recognition. The newly found solution can make it simpler to design experiments in fundamental research and will allow algorithms to be embedded in the next generation of laser systems to ensure real-time optimization.

Motivated by the real-world applications such as recommendation systems, image recognition, and conversational AI, it has become crucial to implement learning algorithms in a distributed fashion. In a commonly used framework, namely data-parallelism, large data-sets are distributed among several worker machines for parallel processing. In many applications, like Federated Learning [KMRR16], data is stored in user devices such as mobile phones and personal computers, and in these applications, fully utilizing the on-device machine intelligence is an important direction for next-generation distributed learning. In a standard distributed framework, several worker machines store data, perform local computations and communicate to the center machine (a parameter server), and the center machine aggregates the local information from worker machines and broadcasts updated parameters iteratively. In this setting, it is well-known that one of the major challenges is to tackle the behavior of the Byzantine machines [LSP82]. This can happen owing to software or hardware crashes, poor communication link between the worker and the center machine, stalled computations, and even co-ordinated or malicious attacks by a third party. In this setup, it is generally assumed (see [YCKB18, BMGS17] that a subset of worker machines behave completely arbitrarily--even in a way that depends on the algorithm used and the data on the other machines, thereby capturing the unpredictable nature of the errors.

$K$-means clustering is one of the most widely-used partitioning algorithm in cluster analysis due to its simplicity and computational efficiency. However, $K$-means does not provide an appropriate clustering result when applying to data with non-spherically shaped clusters. We propose a novel partitioning clustering algorithm based on expectiles. The cluster centers are defined as multivariate expectiles and clusters are searched via a greedy algorithm by minimizing the within cluster '$\tau$ -variance'. We suggest two schemes: fixed $\tau$ clustering, and adaptive $\tau$ clustering. Validated by simulation results, this method beats both $K$-means and spectral clustering on data with asymmetric shaped clusters, or clusters with a complicated structure, including asymmetric normal, beta, skewed $t$ and $F$ distributed clusters. Applications of adaptive $\tau$ clustering on crypto-currency (CC) market data are provided. One finds that the expectiles clusters of CC markets show the phenomena of an institutional investors dominated market. The second application is on image segmentation. compared to other center based clustering methods, the adaptive $\tau$ cluster centers of pixel data can better capture and describe the features of an image. The fixed $\tau$ clustering brings more flexibility on segmentation with a decent accuracy.