With the rise of the popularity and usage of neural networks, trustworthy uncertainty estimation is becoming increasingly essential. One of the most prominent uncertainty estimation methods is Deep Ensembles (Lakshminarayanan et al., 2017) . A classical parametric model has uncertainty in the parameters due to the fact that the data on which the model is build is a random sample. A modern neural network has an additional uncertainty component since the optimization of the network is random. Lakshminarayanan et al. (2017) noted that Deep Ensembles do not incorporate the classical uncertainty induced by the effect of finite data. In this paper, we present a computationally cheap extension of Deep Ensembles for the regression setting, called Bootstrapped Deep Ensembles, that explicitly takes this classical effect of finite data into account using a modified version of the parametric bootstrap. We demonstrate through an experimental study that our method significantly improves upon standard Deep Ensembles

In this paper we present a practical Bayesian self-supervised learning method with Cyclical Stochastic Gradient Hamiltonian Monte Carlo (cSGHMC). Within this framework, we place a prior over the parameters of a self-supervised learning model and use cSGHMC to approximate the high dimensional and multimodal posterior distribution over the embeddings. By exploring an expressive posterior over the embeddings, Bayesian self-supervised learning produces interpretable and diverse representations. Marginalizing over these representations yields a significant gain in performance, calibration and out-of-distribution detection on a variety of downstream classification tasks. We provide experimental results on multiple classification tasks on four challenging datasets. Moreover, we demonstrate the effectiveness of the proposed method in out-of-distribution detection using the SVHN and CIFAR-10 datasets.

Machine learning (ML) is a promising approach for predicting small molecule properties in drug discovery. Here, we provide a comprehensive overview of various ML methods introduced for this purpose in recent years. We review a wide range of properties, including binding affinities, solubility, and ADMET (Absorption, Distribution, Metabolism, Excretion, and Toxicity). We discuss existing popular datasets and molecular descriptors and embeddings, such as chemical fingerprints and graph-based neural networks. We highlight also challenges of predicting and optimizing multiple properties during hit-to-lead and lead optimization stages of drug discovery and explore briefly possible multi-objective optimization techniques that can be used to balance diverse properties while optimizing lead candidates. Finally, techniques to provide an understanding of model predictions, especially for critical decision-making in drug discovery are assessed. Overall, this review provides insights into the landscape of ML models for small molecule property predictions in drug discovery. So far, there are multiple diverse approaches, but their performances are often comparable. Neural networks, while more flexible, do not always outperform simpler models. This shows that the availability of high-quality training data remains crucial for training accurate models and there is a need for standardized benchmarks, additional performance metrics, and best practices to enable richer comparisons between the different techniques and models that can shed a better light on the differences between the many techniques.

The benefits of ADSs can be guaranteed by making the driving experience in complex driving environments more comfortable and safer (Sarker et al., 2019). New perception technologies enable ADSs to detect the surrounding traffic. When surrounding traffic, such as other vehicles, pedestrians, and cyclists, is detected, a motion-planning algorithm can generate a safe path for the ADS (Frazzoli, 2000; Shiller and Gwo, 1991). The generated path is continuously updated using decision and control technologies based on the surrounding environment. One of the greatest challenges for ADSs is the uncertainty of the surrounding dynamic environment (González et al., 2016). An ADS must adapt to these changing conditions and make decisions that prioritize safety and efficiency.

Temporal point processes (TPP) are a natural tool for modeling event-based data. Among all TPP models, Hawkes processes have proven to be the most widely used, mainly due to their adequate modeling for various applications, particularly when considering exponential or non-parametric kernels. Although non-parametric kernels are an option, such models require large datasets. While exponential kernels are more data efficient and relevant for specific applications where events immediately trigger more events, they are ill-suited for applications where latencies need to be estimated, such as in neuroscience. This work aims to offer an efficient solution to TPP inference using general parametric kernels with finite support. The developed solution consists of a fast $\ell_2$ gradient-based solver leveraging a discretized version of the events. After theoretically supporting the use of discretization, the statistical and computational efficiency of the novel approach is demonstrated through various numerical experiments. Finally, the method's effectiveness is evaluated by modeling the occurrence of stimuli-induced patterns from brain signals recorded with magnetoencephalography (MEG). Given the use of general parametric kernels, results show that the proposed approach leads to an improved estimation of pattern latency than the state-of-the-art.

The acquisition of labels for supervised learning can be expensive. To improve the sample efficiency of neural network regression, we study active learning methods that adaptively select batches of unlabeled data for labeling. We present a framework for constructing such methods out of (network-dependent) base kernels, kernel transformations, and selection methods. Our framework encompasses many existing Bayesian methods based on Gaussian process approximations of neural networks as well as non-Bayesian methods. Additionally, we propose to replace the commonly used last-layer features with sketched finite-width neural tangent kernels and to combine them with a novel clustering method. To evaluate different methods, we introduce an open-source benchmark consisting of 15 large tabular regression data sets. Our proposed method outperforms the state-of-the-art on our benchmark, scales to large data sets, and works out-of-the-box without adjusting the network architecture or training code. We provide open-source code that includes efficient implementations of all kernels, kernel transformations, and selection methods, and can be used for reproducing our results.

Depression is a common disease worldwide. It is difficult to diagnose and continues to be underdiagnosed. Because depressed patients constantly share their symptoms, major life events, and treatments on social media, researchers are turning to user-generated digital traces on social media for depression detection. Such methods have distinct advantages in combating depression because they can facilitate innovative approaches to fight depression and alleviate its social and economic burden. However, most existing studies lack effective means to incorporate established medical domain knowledge in depression detection or suffer from feature extraction difficulties that impede greater performance. Following the design science research paradigm, we propose a Deep Knowledge-aware Depression Detection (DKDD) framework to accurately detect social media users at risk of depression and explain the critical factors that contribute to such detection. Extensive empirical studies with real-world data demonstrate that, by incorporating domain knowledge, our method outperforms existing state-of-the-art methods. Our work has significant implications for IS research in knowledge-aware machine learning, digital traces utilization, and NLP research in IS. Practically, by providing early detection and explaining the critical factors, DKDD can supplement clinical depression screening and enable large-scale evaluations of a population's mental health status.

Collective motion is ubiquitous in nature; groups of animals, such as fish, birds, and ungulates appear to move as a whole, exhibiting a rich behavioral repertoire that ranges from directed movement to milling to disordered swarming. Typically, such macroscopic patterns arise from decentralized, local interactions among constituent components (e.g., individual fish in a school). Preeminent models of this process describe individuals as self-propelled particles, subject to self-generated motion and 'social forces' such as short-range repulsion and long-range attraction or alignment. However, organisms are not particles; they are probabilistic decision-makers. Here, we introduce an approach to modelling collective behavior based on active inference. This cognitive framework casts behavior as the consequence of a single imperative: to minimize surprise. We demonstrate that many empirically-observed collective phenomena, including cohesion, milling and directed motion, emerge naturally when considering behavior as driven by active Bayesian inference -- without explicitly building behavioral rules or goals into individual agents. Furthermore, we show that active inference can recover and generalize the classical notion of social forces as agents attempt to suppress prediction errors that conflict with their expectations. By exploring the parameter space of the belief-based model, we reveal non-trivial relationships between the individual beliefs and group properties like polarization and the tendency to visit different collective states. We also explore how individual beliefs about uncertainty determine collective decision-making accuracy. Finally, we show how agents can update their generative model over time, resulting in groups that are collectively more sensitive to external fluctuations and encode information more robustly.

Graphical models and factor analysis are well-established tools in multivariate statistics. While these models can be both linked to structures exhibited by covariance and precision matrices, they are generally not jointly leveraged within graph learning processes. This paper therefore addresses this issue by proposing a flexible algorithmic framework for graph learning under low-rank structural constraints on the covariance matrix. The problem is expressed as penalized maximum likelihood estimation of an elliptical distribution (a generalization of Gaussian graphical models to possibly heavy-tailed distributions), where the covariance matrix is optionally constrained to be structured as low-rank plus diagonal (low-rank factor model). The resolution of this class of problems is then tackled with Riemannian optimization, where we leverage geometries of positive definite matrices and positive semi-definite matrices of fixed rank that are well suited to elliptical models. Numerical experiments on synthetic and real-world data sets illustrate the effectiveness of the proposed approach.

Neural networks have proven to be effective at solving machine learning tasks but it is unclear whether they learn any relevant causal relationships, while their black-box nature makes it difficult for modellers to understand and debug them. We propose a novel method overcoming these issues by allowing a two-way interaction whereby neural-network-empowered machines can expose the underpinning learnt causal graphs and humans can contest the machines by modifying the causal graphs before re-injecting them into the machines. The learnt models are guaranteed to conform to the graphs and adhere to expert knowledge, some of which can also be given up-front. By building a window into the model behaviour and enabling knowledge injection, our method allows practitioners to debug networks based on the causal structure discovered from the data and underpinning the predictions. Experiments with real and synthetic tabular data show that our method improves predictive performance up to 2.4x while producing parsimonious networks, up to 7x smaller in the input layer, compared to SOTA regularised networks.