We introduce and analyze Structured Stochastic Zeroth order Descent (S-SZD), a finite difference approach which approximates a stochastic gradient on a set of $l\leq d$ orthogonal directions, where $d$ is the dimension of the ambient space. These directions are randomly chosen, and may change at each step. For smooth convex functions we prove almost sure convergence of the iterates and a convergence rate on the function values of the form $O(d/l k^{-c})$ for every $c<1/2$, which is arbitrarily close to the one of Stochastic Gradient Descent (SGD) in terms of number of iterations. Our bound also shows the benefits of using $l$ multiple directions instead of one. For non-convex functions satisfying the Polyak-{\L}ojasiewicz condition, we establish the first convergence rates for stochastic zeroth order algorithms under such an assumption. We corroborate our theoretical findings in numerical simulations where assumptions are satisfied and on the real-world problem of hyper-parameter optimization, observing that S-SZD has very good practical performances.

The Kremlin has said Patriot missile defence systems would be a legitimate target if sent to Ukraine to intercept the barrage of incoming Russian missiles that have crippled the war-torn country's power infrastructure. Former Russian President Dmitry Medvedev on Wednesday warned NATO against equipping Kyiv with Patriot missile batteries. It is likely the Kremlin will view the move as an escalation. The comments come as Moscow said no "Christmas ceasefire" was on the cards after nearly 10 months of the war in Ukraine, even as the release of dozens more prisoners, including a United States national, showed some contact between the two sides remained. Russia and Ukraine are not currently engaged in talks to end the fighting, which is raging in Ukraine's east and south while Moscow has carried out missile and drone strikes on power and water facilities across the country, including the capital city Kyiv.

MIT Sloan Management Review and BCG have assembled an international panel of AI experts that includes academics and practitioners to help us gain insights into how responsible artificial intelligence (RAI) is being implemented in organizations worldwide. This month's question for our panelists: Should RAI be a top management agenda item at organizations across industries and geographies?1 Eighty-six percent of them (18 out of 21) agree or strongly agree that it should be. In aggregate, their replies offer a compelling rationale for top management to oversee RAI efforts. We distill and explain this rationale below. We also conducted a global survey of more than 1,000 executives that generated similar findings: Eighty-two percent of managers in companies with at least $100 million in annual revenues agree or strongly agree that RAI should be part of their company's top management agenda.

The world is making rapid progress in the areas of Big Data, Artificial Intelligence and Machine Learning. These are the core drivers of what many analysts have come to refer to as the Fourth Industrial Revolution, epitomized by the increased whittling away of the boundaries that hitherto existed between the physical, digital and biological worlds. There is a clear imperative for pharmacists, pharmaceutical scientists and medical professionals in the field of research and development in developing countries like Nigeria, to increasingly tap into this world of big data, artificial intelligence and machine learning and partake of the revolution that is happening before our very eyes. And the reason is simple. Artificial intelligence is helping to make pharmaceutical research and new drug discovery less expensive and definitely more productive.

The second day of the World Cup 2022 semifinals will pit two-time champions and holders France against Morocco. Kashef, our artificial intelligence (AI) robot, has analysed more than 200 metrics, including the number of wins, goals scored and FIFA rankings, from matches played over the past century to see who is most likely to win on Wednesday. Morocco are currently unbeaten in this tournament and have stunned the footballing world – not once or twice but three times – by beating Belgium, Spain and Portugal. On every occasion, Kashef was left stunned. The only remaining Arab and African team are now just two wins away from lifting the World Cup trophy.

Methods of pattern recognition and machine learning are applied extensively in science, technology, and society. Hence, any advances in related theory may translate into large-scale impact. Here we explore how algorithmic information theory, especially algorithmic probability, may aid in a machine learning task. We study a multiclass supervised classification problem, namely learning the RNA molecule sequence-to-shape map, where the different possible shapes are taken to be the classes. The primary motivation for this work is a proof of concept example, where a concrete, well-motivated machine learning task can be aided by approximations to algorithmic probability. Our approach is based on directly estimating the class (i.e., shape) probabilities from shape complexities, and using the estimated probabilities as a prior in a Gaussian process learning problem. Naturally, with a large amount of training data, the prior has no significant influence on classification accuracy, but in the very small training data regime, we show that using the prior can substantially improve classification accuracy. To our knowledge, this work is one of the first to demonstrate how algorithmic probability can aid in a concrete, real-world, machine learning problem.

The challenges of collecting medical data on neurological disorder diagnosis problems paved the way for learning methods with scarce number of samples. Due to this reason, one-shot learning still remains one of the most challenging and trending concepts of deep learning as it proposes to simulate the human-like learning approach in classification problems. Previous studies have focused on generating more accurate fingerprints of the population using graph neural networks (GNNs) with connectomic brain graph data. Thereby, generated population fingerprints named connectional brain template (CBTs) enabled detecting discriminative bio-markers of the population on classification tasks. However, the reverse problem of data augmentation from single graph data representing brain connectivity has never been tackled before. In this paper, we propose an augmentation pipeline in order to provide improved metrics on our binary classification problem. Divergently from the previous studies, we examine augmentation from a single population template by utilizing graph-based generative adversarial network (gGAN) architecture for a classification problem. We benchmarked our proposed solution on AD/LMCI dataset consisting of brain connectomes with Alzheimer's Disease (AD) and Late Mild Cognitive Impairment (LMCI). In order to evaluate our model's generalizability, we used cross-validation strategy and randomly sampled the folds multiple times. Our results on classification not only provided better accuracy when augmented data generated from one sample is introduced, but yields more balanced results on other metrics as well.

Gaussian process state-space model (GPSSM) is a fully probabilistic state-space model that has attracted much attention over the past decade. However, the outputs of the transition function in the existing GPSSMs are assumed to be independent, meaning that the GPSSMs cannot exploit the inductive biases between different outputs and lose certain model capacities. To address this issue, this paper proposes an output-dependent and more realistic GPSSM by utilizing the well-known, simple yet practical linear model of coregionalization (LMC) framework to represent the output dependency. To jointly learn the output-dependent GPSSM and infer the latent states, we propose a variational sparse GP-based learning method that only gently increases the computational complexity. Experiments on both synthetic and real datasets demonstrate the superiority of the output-dependent GPSSM in terms of learning and inference performance.

Most regularized tensor regression research focuses on tensors predictors with scalars responses or vectors predictors to tensors responses. We consider the sparse low rank tensor on tensor regression where predictors $\mathcal{X}$ and responses $\mathcal{Y}$ are both high-dimensional tensors. By demonstrating that the general inner product or the contracted product on a unit rank tensor can be decomposed into standard inner products and outer products, the problem can be simply transformed into a tensor to scalar regression followed by a tensor decomposition. So we propose a fast solution based on stagewise search composed by contraction part and generation part which are optimized alternatively. We successfully demonstrate our method can out perform current methods in terms of accuracy and predictors selection by effectively incorporating the structural information.

We propose a fully unsupervised method to detect bias in contextualized embeddings. The method leverages the assortative information latently encoded by social networks and combines orthogonality regularization, structured sparsity learning, and graph neural networks to find the embedding subspace capturing this information. As a concrete example, we focus on the phenomenon of ideological bias: we introduce the concept of an ideological subspace, show how it can be found by applying our method to online discussion forums, and present techniques to probe it. Our experiments suggest that the ideological subspace encodes abstract evaluative semantics and reflects changes in the political left-right spectrum during the presidency of Donald Trump.