我们在这里采用贝叶斯非参数混合模型，以将多臂匪徒扩展到尤其是汤普森采样，以扩展到存在奖励模型不确定性的场景。在随机的多臂强盗中，播放臂的奖励是由未知分布产生的。奖励不确定性，即缺乏有关奖励生成分布的知识，引起了探索 - 开发权的权衡：强盗代理需要同时了解奖励分布的属性，并顺序决定下一步要采取哪种操作。在这项工作中，我们通过采用贝叶斯非参数高斯混合模型来进行奖励模型不确定性，将汤普森的抽样扩展到场景中，以进行灵活的奖励密度估计。提出的贝叶斯非参数混合物模型汤普森采样依次学习了奖励模型，该模型最能近似于真实但未知的每臂奖励分布，从而实现了成功的遗憾表现。我们基于基于后验分析的新颖的分析得出的，这是一种针对该方法的渐近遗憾。此外，我们从经验上评估了其在多样化和以前难以捉摸的匪徒环境中的性能，例如，在指数级的家族中，奖励不受异常值和不同的每臂奖励分布。我们表明，拟议的贝叶斯非参数汤普森取样优于表现，无论是平均累积的遗憾和遗憾的波动，最先进的替代方案。在存在强盗奖励模型不确定性的情况下，提出的方法很有价值，因为它避免了严格的逐案模型设计选择，但提供了重要的遗憾。

Well-annotated medical datasets enable deep neural networks (DNNs) to gain strong power in extracting lesion-related features. Building such large and well-designed medical datasets is costly due to the need for high-level expertise. Model pre-training based on ImageNet is a common practice to gain better generalization when the data amount is limited. However, it suffers from the domain gap between natural and medical images. In this work, we pre-train DNNs on ultrasound (US) domains instead of ImageNet to reduce the domain gap in medical US applications. To learn US image representations based on unlabeled US videos, we propose a novel meta-learning-based contrastive learning method, namely Meta Ultrasound Contrastive Learning (Meta-USCL). To tackle the key challenge of obtaining semantically consistent sample pairs for contrastive learning, we present a positive pair generation module along with an automatic sample weighting module based on meta-learning. Experimental results on multiple computer-aided diagnosis (CAD) problems, including pneumonia detection, breast cancer classification, and breast tumor segmentation, show that the proposed self-supervised method reaches state-of-the-art (SOTA). The codes are available at https://github.com/Schuture/Meta-USCL.

Understanding of the pathophysiology of obstructive lung disease (OLD) is limited by available methods to examine the relationship between multi-omic molecular phenomena and clinical outcomes. Integrative factorization methods for multi-omic data can reveal latent patterns of variation describing important biological signal. However, most methods do not provide a framework for inference on the estimated factorization, simultaneously predict important disease phenotypes or clinical outcomes, nor accommodate multiple imputation. To address these gaps, we propose Bayesian Simultaneous Factorization (BSF). We use conjugate normal priors and show that the posterior mode of this model can be estimated by solving a structured nuclear norm-penalized objective that also achieves rank selection and motivates the choice of hyperparameters. We then extend BSF to simultaneously predict a continuous or binary response, termed Bayesian Simultaneous Factorization and Prediction (BSFP). BSF and BSFP accommodate concurrent imputation and full posterior inference for missing data, including "blockwise" missingness, and BSFP offers prediction of unobserved outcomes. We show via simulation that BSFP is competitive in recovering latent variation structure, as well as the importance of propagating uncertainty from the estimated factorization to prediction. We also study the imputation performance of BSF via simulation under missing-at-random and missing-not-at-random assumptions. Lastly, we use BSFP to predict lung function based on the bronchoalveolar lavage metabolome and proteome from a study of HIV-associated OLD. Our analysis reveals a distinct cluster of patients with OLD driven by shared metabolomic and proteomic expression patterns, as well as multi-omic patterns related to lung function decline. Software is freely available at https://github.com/sarahsamorodnitsky/BSFP .

Diffusion models have quickly become the go-to paradigm for generative modelling of perceptual signals (such as images and sound) through iterative refinement. Their success hinges on the fact that the underlying physical phenomena are continuous. For inherently discrete and categorical data such as language, various diffusion-inspired alternatives have been proposed. However, the continuous nature of diffusion models conveys many benefits, and in this work we endeavour to preserve it. We propose CDCD, a framework for modelling categorical data with diffusion models that are continuous both in time and input space. We demonstrate its efficacy on several language modelling tasks.

Large language models (LLMs) have been shown to be able to perform new tasks based on a few demonstrations or natural language instructions. While these capabilities have led to widespread adoption, most LLMs are developed by resource-rich organizations and are frequently kept from the public. As a step towards democratizing this powerful technology, we present BLOOM, a 176B-parameter open-access language model designed and built thanks to a collaboration of hundreds of researchers. BLOOM is a decoder-only Transformer language model that was trained on the ROOTS corpus, a dataset comprising hundreds of sources in 46 natural and 13 programming languages (59 in total). We find that BLOOM achieves competitive performance on a wide variety of benchmarks, with stronger results after undergoing multitask prompted finetuning. To facilitate future research and applications using LLMs, we publicly release our models and code under the Responsible AI License.

我们介绍了第一个机器学习引力波搜索模拟数据挑战（MLGWSC-1）的结果。在这一挑战中，参与的小组必须从二进制黑洞合并中识别出复杂性和持续时间逐渐嵌入在逐渐更现实的噪声中的引力波信号。 4个提供的数据集中的决赛包含O3A观察的真实噪声，并发出了20秒的持续时间，其中包含进动效应和高阶模式。我们介绍了在提交前从参与者未知的1个月的测试数据中得出的6个输入算法的平均灵敏度距离和运行时。其中4个是机器学习算法。我们发现，最好的基于机器学习的算法能够以每月1个的错误警报率（FAR）的速度（FAR）实现基于匹配过滤的生产分析的敏感距离的95％。相反，对于真实的噪音，领先的机器学习搜索获得了70％。为了更高的范围，敏感距离缩小的差异缩小到某些数据集上选择机器学习提交的范围$ \ geq 200 $以优于传统搜索算法的程度。我们的结果表明，当前的机器学习搜索算法可能已经在有限的参数区域中对某些生产设置有用。为了改善最新的技术，机器学习算法需要降低他们能够检测信号并将其有效性扩展到参数空间区域的虚假警报率，在这些区域中，建模的搜索在计算上很昂贵。根据我们的发现，我们汇编了我们认为，将机器学习搜索提升到重力波信号检测中的宝贵工具，我们认为这是最重要的研究领域。

Many different machine learning algorithms exist; taking into account each algorithm's hyperparameters, there is a staggeringly large number of possible alternatives overall. We consider the problem of simultaneously selecting a learning algorithm and setting its hyperparameters, going beyond previous work that addresses these issues in isolation. We show that this problem can be addressed by a fully automated approach, leveraging recent innovations in Bayesian optimization. Specifically, we consider a wide range of feature selection techniques (combining 3 search and 8 evaluator methods) and all classification approaches implemented in WEKA, spanning 2 ensemble methods, 10 meta-methods, 27 base classifiers, and hyperparameter settings for each classifier. On each of 21 popular datasets from the UCI repository, the KDD Cup 09, variants of the MNIST dataset and CIFAR-10, we show classification performance often much better than using standard selection/hyperparameter optimization methods. We hope that our approach will help non-expert users to more effectively identify machine learning algorithms and hyperparameter settings appropriate to their applications, and hence to achieve improved performance.

Automatic music generation with artificial intelligence typically requires a large amount of data which is hard to obtain for many less common genres and musical instruments. To tackle this issue, we present ongoing work and preliminary findings on the possibility for deep models to transfer knowledge from language to music, by finetuning large language models pre-trained on a massive text corpus on only hundreds of MIDI files of drum performances. We show that by doing so, one of the largest, state-of-the-art models (GPT3) is capable of generating reasonable drum grooves, while models that are not pre-trained (Transformer) shows no such ability beyond naive repetition. Evaluating generated music is a challenging task, more so is evaluating drum grooves with little precedence in literature. Hence, we propose a tailored structural evaluation method and analyze drum grooves produced by GPT3 compared to those played by human professionals, exposing the strengths and weaknesses of such generation by language-to-music transfer. Our findings suggest that language-to-music transfer learning with large language models is viable and promising.

Making histopathology image classifiers robust to a wide range of real-world variability is a challenging task. Here, we describe a candidate deep learning solution for the Mitosis Domain Generalization Challenge 2022 (MIDOG) to address the problem of generalization for mitosis detection in images of hematoxylin-eosin-stained histology slides under high variability (scanner, tissue type and species variability). Our approach consists in training a rotation-invariant deep learning model using aggressive data augmentation with a training set enriched with hard negative examples and automatically selected negative examples from the unlabeled part of the challenge dataset. To optimize the performance of our models, we investigated a hard negative mining regime search procedure that lead us to train our best model using a subset of image patches representing 19.6% of our training partition of the challenge dataset. Our candidate model ensemble achieved a F1-score of .697 on the final test set after automated evaluation on the challenge platform, achieving the third best overall score in the MIDOG 2022 Challenge.

Reading comprehension of legal text can be a particularly challenging task due to the length and complexity of legal clauses and a shortage of expert-annotated datasets. To address this challenge, we introduce the Merger Agreement Understanding Dataset (MAUD), an expert-annotated reading comprehension dataset based on the American Bar Association's 2021 Public Target Deal Points Study, with over 39,000 examples and over 47,000 total annotations. Our fine-tuned Transformer baselines show promising results, with models performing well above random on most questions. However, on a large subset of questions, there is still room for significant improvement. As the only expert-annotated merger agreement dataset, MAUD is valuable as a benchmark for both the legal profession and the NLP community.