Wearing a mask is one of the important measures to prevent infectious diseases. However, it is difficult to detect people's mask-wearing situation in public places with high traffic flow. To address the above problem, this paper proposes a mask-wearing face detection model based on YOLOv5l. Firstly, Multi-Head Attentional Self-Convolution not only improves the convergence speed of the model but also enhances the accuracy of the model detection. Secondly, the introduction of Swin Transformer Block is able to extract more useful feature information, enhance the detection ability of small targets, and improve the overall accuracy of the model. Our designed I-CBAM module can improve target detection accuracy. In addition, using enhanced feature fusion enables the model to better adapt to object detection tasks of different scales. In the experimentation on the MASK dataset, the results show that the model proposed in this paper achieved a 1.1% improvement in mAP(0.5) and a 1.3% improvement in mAP(0.5:0.95) compared to the YOLOv5l model. Our proposed method significantly enhances the detection capability of mask-wearing.

Mutual information quantifies the dependence between two random variables and remains invariant under diffeomorphisms. In this paper, we explore the pointwise mutual information profile, an extension of mutual information that maintains this invariance. We analytically describe the profiles of multivariate normal distributions and introduce the family of fine distributions, for which the profile can be accurately approximated using Monte Carlo methods. We then show how fine distributions can be used to study the limitations of existing mutual information estimators, investigate the behavior of neural critics used in variational estimators, and understand the effect of experimental outliers on mutual information estimation. Finally, we show how fine distributions can be used to obtain model-based Bayesian estimates of mutual information, suitable for problems with available domain expertise in which uncertainty quantification is necessary.

Directed acyclic graph (DAG) has been widely employed to represent directional relationships among a set of collected nodes. Yet, the available data in one single study is often limited for accurate DAG reconstruction, whereas heterogeneous data may be collected from multiple relevant studies. It remains an open question how to pool the heterogeneous data together for better DAG structure reconstruction in the target study. In this paper, we first introduce a novel set of structural similarity measures for DAG and then present a transfer DAG learning framework by effectively leveraging information from auxiliary DAGs of different levels of similarities. Our theoretical analysis shows substantial improvement in terms of DAG reconstruction in the target study, even when no auxiliary DAG is overall similar to the target DAG, which is in sharp contrast to most existing transfer learning methods. The advantage of the proposed transfer DAG learning is also supported by extensive numerical experiments on both synthetic data and multi-site brain functional connectivity network data.

The elusive nature of gradient-based optimization in neural networks is tied to their loss landscape geometry, which is poorly understood. However recent work has brought solid evidence that there is essentially no loss barrier between the local solutions of gradient descent, once accounting for weight-permutations that leave the network's computation unchanged. This raises questions for approximate inference in Bayesian neural networks (BNNs), where we are interested in marginalizing over multiple points in the loss landscape. In this work, we first extend the formalism of marginalized loss barrier and solution interpolation to BNNs, before proposing a matching algorithm to search for linearly connected solutions. This is achieved by aligning the distributions of two independent approximate Bayesian solutions with respect to permutation matrices. We build on the results of Ainsworth et al. (2023), reframing the problem as a combinatorial optimization one, using an approximation to the sum of bilinear assignment problem. We then experiment on a variety of architectures and datasets, finding nearly zero marginalized loss barriers for linearly connected solutions.

Learning from label proportions (LLP) is a generalization of supervised learning in which the training data is available as sets or bags of feature-vectors (instances) along with the average instance-label of each bag. The goal is to train a good instance classifier. While most previous works on LLP have focused on training models on such training data, computational learnability of LLP was only recently explored by [Saket'21, Saket'22] who showed worst case intractability of properly learning linear threshold functions (LTFs) from label proportions. However, their work did not rule out efficient algorithms for this problem on natural distributions. In this work we show that it is indeed possible to efficiently learn LTFs using LTFs when given access to random bags of some label proportion in which feature-vectors are, conditioned on their labels, independently sampled from a Gaussian distribution $N(\mathbf{\mu}, \mathbf{\Sigma})$. Our work shows that a certain matrix -- formed using covariances of the differences of feature-vectors sampled from the bags with and without replacement -- necessarily has its principal component, after a transformation, in the direction of the normal vector of the LTF. Our algorithm estimates the means and covariance matrices using subgaussian concentration bounds which we show can be applied to efficiently sample bags for approximating the normal direction. Using this in conjunction with novel generalization error bounds in the bag setting, we show that a low error hypothesis LTF can be identified. For some special cases of the $N(\mathbf{0}, \mathbf{I})$ distribution we provide a simpler mean estimation based algorithm. We include an experimental evaluation of our learning algorithms along with a comparison with those of [Saket'21, Saket'22] and random LTFs, demonstrating the effectiveness of our techniques.

In the task of Learning from Label Proportions (LLP), a model is trained on groups (a.k.a bags) of instances and their corresponding label proportions to predict labels for individual instances. LLP has been applied pre-dominantly on two types of datasets - image and tabular. In image LLP, bags of fixed size are created by randomly sampling instances from an underlying dataset. Bags created via this methodology are called random bags. Experimentation on Image LLP has been mostly on random bags on CIFAR-* and MNIST datasets. Despite being a very crucial task in privacy sensitive applications, tabular LLP does not yet have a open, large scale LLP benchmark. One of the unique properties of tabular LLP is the ability to create feature bags where all the instances in a bag have the same value for a given feature. It has been shown in prior research that feature bags are very common in practical, real world applications [Chen et. al '23, Saket et. al. '22]. In this paper, we address the lack of a open, large scale tabular benchmark. First we propose LLP-Bench, a suite of 56 LLP datasets (52 feature bag and 4 random bag datasets) created from the Criteo CTR prediction dataset consisting of 45 million instances. The 56 datasets represent diverse ways in which bags can be constructed from underlying tabular data. To the best of our knowledge, LLP-Bench is the first large scale tabular LLP benchmark with an extensive diversity in constituent datasets. Second, we propose four metrics that characterize and quantify the hardness of a LLP dataset. Using these four metrics we present deep analysis of the 56 datasets in LLP-Bench. Finally we present the performance of 9 SOTA and popular tabular LLP techniques on all the 56 datasets. To the best of our knowledge, our study consisting of more than 2500 experiments is the most extensive study of popular tabular LLP techniques in literature.

The optimal number of clusters is one of the main concerns when applying cluster analysis. Several cluster validity indexes have been introduced to address this problem. However, in some situations, there is more than one option that can be chosen as the final number of clusters. This aspect has been overlooked by most of the existing works in this area. In this study, we introduce a correlation-based fuzzy cluster validity index known as the Wiroonsri-Preedasawakul (WP) index. This index is defined based on the correlation between the actual distance between a pair of data points and the distance between adjusted centroids with respect to that pair. We evaluate and compare the performance of our index with several existing indexes, including Xie-Beni, Pakhira-Bandyopadhyay-Maulik, Tang, Wu-Li, generalized C, and Kwon2. We conduct this evaluation on four types of datasets: artificial datasets, real-world datasets, simulated datasets with ranks, and image datasets, using the fuzzy c-means algorithm. Overall, the WP index outperforms most, if not all, of these indexes in terms of accurately detecting the optimal number of clusters and providing accurate secondary options. Moreover, our index remains effective even when the fuzziness parameter $m$ is set to a large value. Our R package called UniversalCVI used in this work is available at https://CRAN.R-project.org/package=UniversalCVI.

Mutual information is a general statistical dependency measure which has found applications in representation learning, causality, domain generalization and computational biology. However, mutual information estimators are typically evaluated on simple families of probability distributions, namely multivariate normal distribution and selected distributions with one-dimensional random variables. In this paper, we show how to construct a diverse family of distributions with known ground-truth mutual information and propose a language-independent benchmarking platform for mutual information estimators. We discuss the general applicability and limitations of classical and neural estimators in settings involving high dimensions, sparse interactions, long-tailed distributions, and high mutual information. Finally, we provide guidelines for practitioners on how to select appropriate estimator adapted to the difficulty of problem considered and issues one needs to consider when applying an estimator to a new data set.

Eigen and singular decompositions are ubiquitous in applied mathematics. They can serve as a basis to define good features in machine learning pipelines (Belkin and Niyogi, 2003; Coifman and Lafon, 2006; Balestriero and LeCun, 2022), while a set of good features naturally define pullback distances on the original data. Those features and distances are naturally referred to as "spectral embeddings" and "spectral distances". The latter are thought to provide meaningful geometries on the data, which explain their uses for clustering (Belkin and Niyogi, 2004; Schubert et al., 2018), as well as diffusion models (Chen and Lipman, 2023). In the machine learning community, spectral decompositions are usually derived from the eigen decompositions of different graph Laplacians built on top of the data (Chung, 1997; Zhu et al., 2003; Ham et al., 2004). However, those methods are known to scale poorly with the input dimension (Bengio et al., 2006; Singer, 2006; Hein et al., 2007), although they had applications in many different fields, such as molecular simulation (Glielmo et al., 2021), acoustics (Bianco et al., 2019) or the study of gene interaction (van Dijk et al., 2018). In this paper, we suggest a different approach to approximate the spectral decompositions of a large class of operators. Our method consists in restricting the study of infinite-dimensional operators on a basis of simple functions, which is usually referred to as Galerkin, Ritz or Raleigh methods (Singer, 1962), if not Bubnov or Petrov (Fluid Dynamics, 2012), depending on the research community. We make the following contributions.

A core principle in statistical learning is that smoothness of target functions allows to break the curse of dimensionality. However, learning a smooth function seems to require enough samples close to one another to get meaningful estimate of high-order derivatives, which would be hard in machine learning problems where the ratio between number of data and input dimension is relatively small. By deriving new lower bounds on the generalization error, this paper formalizes such an intuition, before investigating the role of constants and transitory regimes which are usually not depicted beyond classical learning theory statements while they play a dominant role in practice.