The digitisation of historical documents has provided historians with unprecedented research opportunities. Yet, the conventional approach to analysing historical documents involves converting them from images to text using OCR, a process that overlooks the potential benefits of treating them as images and introduces high levels of noise. To bridge this gap, we take advantage of recent advancements in pixel-based language models trained to reconstruct masked patches of pixels instead of predicting token distributions. Due to the scarcity of real historical scans, we propose a novel method for generating synthetic scans to resemble real historical documents. We then pre-train our model, PHD, on a combination of synthetic scans and real historical newspapers from the 1700-1900 period. Through our experiments, we demonstrate that PHD exhibits high proficiency in reconstructing masked image patches and provide evidence of our model's noteworthy language understanding capabilities. Notably, we successfully apply our model to a historical QA task, highlighting its usefulness in this domain.

Bio-sequences, which include DNA, RNA, and proteins, are the molecular foundation of modern genetic research. The classification of bio-sequences based on sequence information has been a key focus in bioinformatics research. At present, with the sequential completion of genome mapping from humans to various species, we have amassed a vast amount of sequence data, creating an urgent need for computer-assisted annotation of sequence functions. Although it is statistically evident that genetic sequences determine hereditary diseases, the mechanisms by which sequence variations contribute to diseases are intricately complex. It is difficult to address and interpret all these issues through one biological experiment; hence, multiple computer predictions are needed to guide the progression of wet lab exploration. In summary, the application of information science and machine learning to bio-sequence classification is a valuable tool for assisting researchers in comprehending and analysing bio-sequences. It serves as a key driving force for advancing research in the field of bioinformatics. In the field of bio-sequence classification, machine learning methods are broadly pursued using two strategies: feature extraction combined with traditional classification methods and direct sequence classification via deep learning techniques. For bio-sequences, relevant features are mainly characterized as frequency, physicochemical, structural, and evolutionary features.

Latent diffusion models (LDMs) exhibit an impressive ability to produce realistic images, yet the inner workings of these models remain mysterious. Even when trained purely on images without explicit depth information, they typically output coherent pictures of 3D scenes. In this work, we investigate a basic interpretability question: does an LDM create and use an internal representation of simple scene geometry? Using linear probes, we find evidence that the internal activations of the LDM encode linear representations of both 3D depth data and a salient-object / background distinction. These representations appear surprisingly early in the denoising process$-$well before a human can easily make sense of the noisy images. Intervention experiments further indicate these representations play a causal role in image synthesis, and may be used for simple high-level editing of an LDM's output. Project page: https://yc015.github.io/scene-representation-diffusion-model/

Over the past few years, significant advancements have been made in the field of machine learning (ML) to address resource management, interference management, autonomy, and decision-making in wireless networks. Traditional ML approaches rely on centralized methods, where data is collected at a central server for training. However, this approach poses a challenge in terms of preserving the data privacy of devices. To address this issue, federated learning (FL) has emerged as an effective solution that allows edge devices to collaboratively train ML models without compromising data privacy. In FL, local datasets are not shared, and the focus is on learning a global model for a specific task involving all devices. However, FL has limitations when it comes to adapting the model to devices with different data distributions. In such cases, meta learning is considered, as it enables the adaptation of learning models to different data distributions using only a few data samples. In this tutorial, we present a comprehensive review of FL, meta learning, and federated meta learning (FedMeta). Unlike other tutorial papers, our objective is to explore how FL, meta learning, and FedMeta methodologies can be designed, optimized, and evolved, and their applications over wireless networks. We also analyze the relationships among these learning algorithms and examine their advantages and disadvantages in real-world applications.

This paper presents Topical, a novel deep neural network for repository level embeddings. Existing methods, reliant on natural language documentation or naive aggregation techniques, are outperformed by Topical's utilization of an attention mechanism. This mechanism generates repository-level representations from source code, full dependency graphs, and script level textual data. Trained on publicly accessible GitHub repositories, Topical surpasses multiple baselines in tasks such as repository auto-tagging, highlighting the attention mechanism's efficacy over traditional aggregation methods. Topical also demonstrates scalability and efficiency, making it a valuable contribution to repository-level representation computation. For further research, the accompanying tools, code, and training dataset are provided at: https://github.com/jpmorganchase/topical.

The integrity of training data, even when annotated by experts, is far from guaranteed, especially for non-IID datasets comprising both in- and out-of-distribution samples. In an ideal scenario, the majority of samples would be in-distribution, while samples that deviate semantically would be identified as out-of-distribution and excluded during the annotation process. However, experts may erroneously classify these out-of-distribution samples as in-distribution, assigning them labels that are inherently unreliable. This mixture of unreliable labels and varied data types makes the task of learning robust neural networks notably challenging. We observe that both in- and out-of-distribution samples can almost invariably be ruled out from belonging to certain classes, aside from those corresponding to unreliable ground-truth labels. This opens the possibility of utilizing reliable complementary labels that indicate the classes to which a sample does not belong. Guided by this insight, we introduce a novel approach, termed \textit{Gray Learning} (GL), which leverages both ground-truth and complementary labels. Crucially, GL adaptively adjusts the loss weights for these two label types based on prediction confidence levels. By grounding our approach in statistical learning theory, we derive bounds for the generalization error, demonstrating that GL achieves tight constraints even in non-IID settings. Extensive experimental evaluations reveal that our method significantly outperforms alternative approaches grounded in robust statistics.

Bias in training datasets must be managed for various groups in classification tasks to ensure parity or equal treatment. With the recent growth in artificial intelligence models and their expanding role in automated decision-making, ensuring that these models are not biased is vital. There is an abundance of evidence suggesting that these models could contain or even amplify the bias present in the data on which they are trained, inherent to their objective function and learning algorithms; Many researchers direct their attention to this issue in different directions, namely, changing data to be statistically independent, adversarial training for restricting the capabilities of a particular competitor who aims to maximize parity, etc. These methods result in information loss and do not provide a suitable balance between accuracy and fairness or do not ensure limiting the biases in training. To this end, we propose a powerful strategy for training deep learning models called the Distraction module, which can be theoretically proven effective in controlling bias from affecting the classification results. This method can be utilized with different data types (e.g., Tabular, images, graphs, etc.). We demonstrate the potency of the proposed method by testing it on UCI Adult and Heritage Health datasets (tabular), POKEC-Z, POKEC-N and NBA datasets (graph), and CelebA dataset (vision). Using state-of-the-art methods proposed in the fairness literature for each dataset, we exhibit our model is superior to these proposed methods in minimizing bias and maintaining accuracy.

Maximizing the log-likelihood is a crucial aspect of learning latent variable models, and variational inference (VI) stands as the commonly adopted method. However, VI can encounter challenges in achieving a high log-likelihood when dealing with complicated posterior distributions. In response to this limitation, we introduce a novel variational importance sampling (VIS) approach that directly estimates and maximizes the log-likelihood. VIS leverages the optimal proposal distribution, achieved by minimizing the forward $\chi^2$ divergence, to enhance log-likelihood estimation. We apply VIS to various popular latent variable models, including mixture models, variational auto-encoders, and partially observable generalized linear models. Results demonstrate that our approach consistently outperforms state-of-the-art baselines, both in terms of log-likelihood and model parameter estimation.

Sampling a target probability distribution with an unknown normalization constant is a fundamental challenge in computational science and engineering. Recent work shows that algorithms derived by considering gradient flows in the space of probability measures open up new avenues for algorithm development. This paper makes three contributions to this sampling approach by scrutinizing the design components of such gradient flows. Any instantiation of a gradient flow for sampling needs an energy functional and a metric to determine the flow, as well as numerical approximations of the flow to derive algorithms. Our first contribution is to show that the Kullback-Leibler divergence, as an energy functional, has the unique property (among all f-divergences) that gradient flows resulting from it do not depend on the normalization constant of the target distribution. Our second contribution is to study the choice of metric from the perspective of invariance. The Fisher-Rao metric is known as the unique choice (up to scaling) that is diffeomorphism invariant. As a computationally tractable alternative, we introduce a relaxed, affine invariance property for the metrics and gradient flows. In particular, we construct various affine invariant Wasserstein and Stein gradient flows. Affine invariant gradient flows are shown to behave more favorably than their non-affine-invariant counterparts when sampling highly anisotropic distributions, in theory and by using particle methods. Our third contribution is to study, and develop efficient algorithms based on Gaussian approximations of the gradient flows; this leads to an alternative to particle methods. We establish connections between various Gaussian approximate gradient flows, discuss their relation to gradient methods arising from parametric variational inference, and study their convergence properties both theoretically and numerically.

The rapid spread of COVID-19 and the emergence of new variants underscore the importance of effective screening measures. Rapid diagnosis and subsequent quarantine of infected individuals can prevent further spread of the virus in society. While PCR tests are the gold standard for COVID-19 diagnosis, they are costly and time-consuming. In contrast, urine test strips are an inexpensive, non-invasive, and rapidly obtainable screening method that can provide important information about a patient's health status. In this study, we collected a new dataset and used the RGB (Red Green Blue) color space of urine test strips parameters to detect the health status of individuals. To improve the accuracy of our model, we converted the RGB space to 10 additional color spaces. After evaluating four different machine learning models, we proposed a new ensemble model based on a multi-layer perceptron neural network. Although the initial results were not strong, we were able to improve the model's screening performance for COVID-19 by removing uncertain regions of the model space. Ultimately, our model achieved a screening accuracy of 80% based on urine parameters. Our results suggest that urine test strips can be a useful tool for COVID-19 screening, particularly in resource-constrained settings where PCR testing may not be feasible. Further research is needed to validate our findings and explore the potential role of urine test strips in COVID-19 diagnosis and management.