Many numerical algorithms and learning tasks rest on solution of the Monge-Kantorovich problem and corresponding Wasserstein distances. While the natural approach is to treat the problem as an infinite-dimensional linear programming, such a methodology severely limits the computational performance due to the polynomial scaling with respect to the sample size along with intensive memory requirements. We propose a novel alternative framework to address the Monge-Kantorovich problem based on a projection type gradient descent scheme. The micro-dynamics is built on the notion of the conditional expectation, where the connection with the opinion dynamics is explored and leveraged to build compact numerical schemes. We demonstrate that the devised dynamics recovers random maps with favourable computational performance. Along with the theoretical insight, the provided dynamics paves the way for innovative approaches to construct numerical schemes for computing optimal transport maps as well as Wasserstein distances.

Labeling data via rules-of-thumb and minimal label supervision is central to Weak Supervision, a paradigm subsuming subareas of machine learning such as crowdsourced learning and semi-supervised ensemble learning. By using this labeled data to train modern machine learning methods, the cost of acquiring large amounts of hand labeled data can be ameliorated. Approaches to combining the rules-of-thumb falls into two camps, reflecting different ideologies of statistical estimation. The most common approach, exemplified by the Dawid-Skene model, is based on probabilistic modeling. The other, developed in the work of Balsubramani-Freund and others, is adversarial and game-theoretic. We provide a variety of statistical results for the adversarial approach under log-loss: we characterize the form of the solution, relate it to logistic regression, demonstrate consistency, and give rates of convergence. On the other hand, we find that probabilistic approaches for the same model class can fail to be consistent. Experimental results are provided to corroborate the theoretical results.

Obsessive-compulsive disorder (OCD) presents itself as a highly debilitating disorder. The disorder has common associations with the prefrontal cortex and the glutamate receptor known as Metabotropic Glutamate Receptor 5 (mGluR5). This receptor has been observed to demonstrate higher levels of signaling from positron emission tomography scans measured by its distribution volume ratios in mice. Despite this evidence, studies are unable to fully verify the involvement of mGluR5 as more empirical data is needed. Computational modeling methods were used as a means of validation for previous hypotheses involving mGluR5. The inadequacies in relation to the causal factor of OCD were answered by utilizing T1 resting-state magnetic resonance imaging (TRS-MRI) scans of patients suffering from schizophrenia, major depressive disorder, and obsessive-compulsive disorder. Because comorbid cases often occur within these disorders, cross-comparative abilities become necessary to find distinctive characteristics. Two-dimensional convolutional neural networks alongside ResNet50 and MobileNet models were constructed and evaluated for efficiency. Activation heatmaps of TRS-MRI scans were outputted, allowing for transcriptomics analysis. Though, a lack of ability to predict OCD cases prevented gene expression analysis. Across all models, there was an 88.75% validation accuracy for MDD, and 82.08% validation accuracy for SZD under the framework of ResNet50 as well as novel computation. OCD yielded an accuracy rate of around 54.4%. These results provided further evidence for the p-factor theory regarding mental disorders. Future work involves the application of alternate transfer learning networks than those used in this paper to bolster accuracy rates.

We present a dynamic model in which the weights are conditioned on an input sample x and are learned to match those that would be obtained by finetuning a base model on x and its label y. This mapping between an input sample and network weights is approximated by a denoising diffusion model. The diffusion model we employ focuses on modifying a single layer of the base model and is conditioned on the input, activations, and output of this layer. Since the diffusion model is stochastic in nature, multiple initializations generate different networks, forming an ensemble, which leads to further improvements. Our experiments demonstrate the wide applicability of the method for image classification, 3D reconstruction, tabular data, speech separation, and natural language processing. Our code is available at https://github.com/ShaharLutatiPersonal/OCD

Every hour a child spends playing video games pre day raises their risk of obsessive-compulsive disorder (OCD) by 13 percent, a study suggests. There was also a correlation between watching YouTube content and OCD - with every hour spent streaming videos associated with an 11 percent raised risk. Yet, unlike other studies, the latest research found no association between watching films or movies or playing on cell phones. The researchers blamed YouTube algorithms and addictive video game content for fostering compulsive feelings in preteens. Scientists at the University of California, San Francisco, recruited 9,204 children aged nine to 10.

Causal discovery for purely observational, categorical data is a long-standing challenging problem. Unlike continuous data, the vast majority of existing methods for categorical data focus on inferring the Markov equivalence class only, which leaves the direction of some causal relationships undetermined. This paper proposes an identifiable ordinal causal discovery method that exploits the ordinal information contained in many real-world applications to uniquely identify the causal structure. The proposed method is applicable beyond ordinal data via data discretization. Through real-world and synthetic experiments, we demonstrate that the proposed ordinal causal discovery method combined with simple score-and-search algorithms has favorable and robust performance compared to state-of-the-art alternative methods in both ordinal categorical and non-categorical data. An accompanied R package OCD is freely available at https://web.stat.tamu.edu/

Modern technology has not only allowed the collection of data sets of unprecedented size, but has also facilitated the real-time monitoring of many types of evolving processes of interest. Wearable health devices, astronomical survey telescopes, self-driving cars and transport network load-tracking systems are just a few examples of new technologies that collect large quantities of streaming data, and that provide new challenges and opportunities for statisticians. Very often, a key feature of interest in the monitoring of a data stream is a changepoint; that is, a moment in time at which the data generating mechanism undergoes a change. Such times often represent events of interest, e.g. a change in heart function, and moreover, the accurate identification of changepoints often facilitates the decomposition of a data stream into stationary segments. Historically, it has tended to be univariate time series that have been monitored and studied, within the well-established field of statistical process control (e.g.

Multi-label classification (MLC) assigns multiple labels to each sample. Prior studies show that MLC can be transformed to a sequence prediction problem with a recurrent neural network (RNN) decoder to model the label dependency. However, training a RNN decoder requires a predefined order of labels, which is not directly available in the MLC specification. Besides, RNN thus trained tends to overfit the label combinations in the training set and have difficulty generating unseen label sequences. In this paper, we propose a new framework for MLC which does not rely on a predefined label order and thus alleviates exposure bias. The experimental results on three multi-label classification benchmark datasets show that our method outperforms competitive baselines by a large margin. We also find the proposed approach has a higher probability of generating label combinations not seen during training than the baseline models. The result shows that the proposed approach has better generalization capability.

We present Optimal Completion Distillation (OCD), a training procedure for optimizing sequence to sequence models based on edit distance. OCD is efficient, has no hyper-parameters of its own, and does not require pretraining or joint optimization with conditional log-likelihood. Given a partial sequence generated by the model, we first identify the set of optimal suffixes that minimize the total edit distance, using an efficient dynamic programming algorithm. Then, for each position of the generated sequence, we use a target distribution that puts equal probability on the first token of all the optimal suffixes. OCD achieves the state-of-the-art performance on end-to-end speech recognition, on both Wall Street Journal and Librispeech datasets, achieving $9.3\%$ WER and $4.5\%$ WER respectively.

Spending so much time perfecting schoolwork that it never gets turned in. These are typical behaviors for people with obsessive compulsive disorder, or OCD, a lifelong illness marked by repetitive thoughts and actions that can seriously impair work performance, relationships and quality of life. OCD is most commonly treated with medication and a form of psychotherapy called cognitive behavioral therapy. Unfortunately, cognitive behavioral therapy does not help everyone with OCD, and the treatment can be expensive and time-consuming. Now, UCLA researchers have developed a way to use brain scans and machine learning -- a form of artificial intelligence -- to predict whether people with OCD will benefit from cognitive behavior therapy.