我们考虑具有稀疏限制的缓慢变化回归模型中参数估计问题。我们将问题标制作混合整数优化问题，并证明可以通过新颖的精确放松来完全作为二元凸优化问题的重整。放松利用摩洛队的逆转录的新平等渗透了非凸面目标函数，同时与所有可行的二进制点上的原始目标重合。这使我们能够通过切割平面型算法更有效地更有效地解决问题并以优化的优化。我们开发了一种高度优化的这种算法的实现，这基本上提高了直接实现的渐近计算复杂性。我们进一步开发了一种启发式方法，保证生产可行的解决方案，并且正如我们经验说明的那样，为二进制优化问题产生高质量的热启动解决方案。我们在合成和现实世界数据集上展示了所得算法优于各种度量的可比时期的竞争配方，包括采样超出预测性能，支持恢复精度和假阳性率。该算法使我们能够培训具有10,000个参数的模型，对噪声具有鲁棒，并且能够有效地捕获数据生成过程的潜在缓慢改变支持。

Modern speech recognition systems exhibits rapid performance degradation under domain shift. This issue is especially prevalent in data-scarce settings, such as low-resource languages, where diversity of training data is limited. In this work we propose M2DS2, a simple and sample-efficient finetuning strategy for large pretrained speech models, based on mixed source and target domain self-supervision. We find that including source domain self-supervision stabilizes training and avoids mode collapse of the latent representations. For evaluation, we collect HParl, a $120$ hour speech corpus for Greek, consisting of plenary sessions in the Greek Parliament. We merge HParl with two popular Greek corpora to create GREC-MD, a test-bed for multi-domain evaluation of Greek ASR systems. In our experiments we find that, while other Unsupervised Domain Adaptation baselines fail in this resource-constrained environment, M2DS2 yields significant improvements for cross-domain adaptation, even when a only a few hours of in-domain audio are available. When we relax the problem in a weakly supervised setting, we find that independent adaptation for audio using M2DS2 and language using simple LM augmentation techniques is particularly effective, yielding word error rates comparable to the fully supervised baselines.

Iterative regularization is a classic idea in regularization theory, that has recently become popular in machine learning. On the one hand, it allows to design efficient algorithms controlling at the same time numerical and statistical accuracy. On the other hand it allows to shed light on the learning curves observed while training neural networks. In this paper, we focus on iterative regularization in the context of classification. After contrasting this setting with that of regression and inverse problems, we develop an iterative regularization approach based on the use of the hinge loss function. More precisely we consider a diagonal approach for a family of algorithms for which we prove convergence as well as rates of convergence. Our approach compares favorably with other alternatives, as confirmed also in numerical simulations.

Artificial Intelligence (AI) systems have been increasingly used to make decision-making processes faster, more accurate, and more efficient. However, such systems are also at constant risk of being attacked. While the majority of attacks targeting AI-based applications aim to manipulate classifiers or training data and alter the output of an AI model, recently proposed Sponge Attacks against AI models aim to impede the classifier's execution by consuming substantial resources. In this work, we propose \textit{Dual Denial of Decision (DDoD) attacks against collaborative Human-AI teams}. We discuss how such attacks aim to deplete \textit{both computational and human} resources, and significantly impair decision-making capabilities. We describe DDoD on human and computational resources and present potential risk scenarios in a series of exemplary domains.

Numerical association rule mining offers a very efficient way of mining association rules, where algorithms can operate directly with categorical and numerical attributes. These methods are suitable for mining different transaction databases, where data are entered sequentially. However, little attention has been paid to the time series numerical association rule mining, which offers a new technique for extracting association rules from time series data. This paper presents a new algorithmic method for time series numerical association rule mining and its application in smart agriculture. We offer a concept of a hardware environment for monitoring plant parameters and a novel data mining method with practical experiments. The practical experiments showed the method's potential and opened the door for further extension.

Text detection in natural scenes has been a significant and active research subject in computer vision and document analysis because of its wide range of applications as evidenced by the emergence of the Robust Reading Competition. One of the algorithms which has good text detection performance in the said competition is the Character Region Awareness for Text Detection (CRAFT). Employing the ICDAR 2013 dataset, this study investigates the impact of automatic image classification and blind deconvolution as image pre-processing steps to further enhance the text detection performance of CRAFT. The proposed technique automatically classifies the scene images into two categories, blurry and non-blurry, by utilizing of a Laplacian operator with 100 as threshold. Prior to applying the CRAFT algorithm, images that are categorized as blurry are further pre-processed using blind deconvolution to reduce the blur. The results revealed that the proposed method significantly enhanced the detection performance of CRAFT, as demonstrated by its IoU h-mean of 94.47% compared to the original 91.42% h-mean of CRAFT and this even outperformed the top-ranked SenseTime, whose h-mean is 93.62%.

Accurately predicting interactive road agents' future trajectories and planning a socially compliant and human-like trajectory accordingly are important for autonomous vehicles. In this paper, we propose a planning-centric prediction neural network, which takes surrounding agents' historical states and map context information as input, and outputs the joint multi-modal prediction trajectories for surrounding agents, as well as a sequence of control commands for the ego vehicle by imitation learning. An agent-agent interaction module along the time axis is proposed in our network architecture to better comprehend the relationship among all the other intelligent agents on the road. To incorporate the map's topological information, a Dynamic Graph Convolutional Neural Network (DGCNN) is employed to process the road network topology. Besides, the whole architecture can serve as a backbone for the Differentiable Integrated motion Prediction with Planning (DIPP) method by providing accurate prediction results and initial planning commands. Experiments are conducted on real-world datasets to demonstrate the improvements made by our proposed method in both planning and prediction accuracy compared to the previous state-of-the-art methods.

Pre-trained protein language models have demonstrated significant applicability in different protein engineering task. A general usage of these pre-trained transformer models latent representation is to use a mean pool across residue positions to reduce the feature dimensions to further downstream tasks such as predicting bio-physics properties or other functional behaviours. In this paper we provide a two-fold contribution to machine learning (ML) driven drug design. Firstly, we demonstrate the power of sparsity by promoting penalization of pre-trained transformer models to secure more robust and accurate melting temperature (Tm) prediction of single-chain variable fragments with a mean absolute error of 0.23C. Secondly, we demonstrate the power of framing our prediction problem in a probabilistic framework. Specifically, we advocate for the need of adopting probabilistic frameworks especially in the context of ML driven drug design.

Federated learning (FL) has emerged as an instance of distributed machine learning paradigm that avoids the transmission of data generated on the users' side. Although data are not transmitted, edge devices have to deal with limited communication bandwidths, data heterogeneity, and straggler effects due to the limited computational resources of users' devices. A prominent approach to overcome such difficulties is FedADMM, which is based on the classical two-operator consensus alternating direction method of multipliers (ADMM). The common assumption of FL algorithms, including FedADMM, is that they learn a global model using data only on the users' side and not on the edge server. However, in edge learning, the server is expected to be near the base station and have direct access to rich datasets. In this paper, we argue that leveraging the rich data on the edge server is much more beneficial than utilizing only user datasets. Specifically, we show that the mere application of FL with an additional virtual user node representing the data on the edge server is inefficient. We propose FedTOP-ADMM, which generalizes FedADMM and is based on a three-operator ADMM-type technique that exploits a smooth cost function on the edge server to learn a global model parallel to the edge devices. Our numerical experiments indicate that FedTOP-ADMM has substantial gain up to 33\% in communication efficiency to reach a desired test accuracy with respect to FedADMM, including a virtual user on the edge server.

图像分类的深卷卷神经网络（CNN）依次交替交替进行卷积和下采样操作，例如合并层或陷入困境的卷积，从而导致较低的分辨率特征网络越深。这些降采样操作节省了计算资源，并在下一层提供了一些翻译不变性以及更大的接收领域。但是，这样做的固有副作用是，在网络深端产生的高级特征始终以低分辨率特征图捕获。逆也是如此，因为浅层总是包含小规模的特征。在生物医学图像分析中，工程师通常负责对仅包含有限信息的非常小的图像贴片进行分类。从本质上讲，这些补丁甚至可能不包含对象，而分类取决于图像纹理中未知量表的微妙基础模式的检测。在这些情况下，每一个信息都是有价值的。因此，重要的是要提取最大数量的信息功能。在这些考虑因素的推动下，我们引入了一种新的CNN体​​系结构，该体系结构可通过利用跳过连接以及连续的收缩和特征图的扩展来保留深，中间和浅层层的多尺度特征。使用来自胰腺导管腺癌（PDAC）CT扫描的非常低分辨率斑块的数据集，我们证明我们的网络可以超越最新模型的当前状态。