Proper hyperparameter tuning is essential for achieving optimal performance of modern machine learning (ML) methods in predictive tasks. While there is an extensive literature on tuning ML learners for prediction, there is only little guidance available on tuning ML learners for causal machine learning and how to select among different ML learners. In this paper, we empirically assess the relationship between the predictive performance of ML methods and the resulting causal estimation based on the Double Machine Learning (DML) approach by Chernozhukov et al. (2018). DML relies on estimating so-called nuisance parameters by treating them as supervised learning problems and using them as plug-in estimates to solve for the (causal) parameter. We conduct an extensive simulation study using data from the 2019 Atlantic Causal Inference Conference Data Challenge. We provide empirical insights on the role of hyperparameter tuning and other practical decisions for causal estimation with DML. First, we assess the importance of data splitting schemes for tuning ML learners within Double Machine Learning. Second, we investigate how the choice of ML methods and hyperparameters, including recent AutoML frameworks, impacts the estimation performance for a causal parameter of interest. Third, we assess to what extent the choice of a particular causal model, as characterized by incorporated parametric assumptions, can be based on predictive performance metrics.

Prediction of angler behaviors, such as catch rates and angler pressure, is essential to maintaining fish populations and ensuring angler satisfaction. Angler behavior can partly be tracked by online platforms and mobile phone applications that provide fishing activities reported by recreational anglers. Moreover, angler behavior is known to be driven by local site attributes. Here, the prediction of citizen-reported angler behavior was investigated by machine-learning methods using auxiliary data on the environment, socioeconomics, fisheries management objectives, and events at a freshwater body. The goal was to determine whether auxiliary data alone could predict the reported behavior. Different spatial and temporal extents and temporal resolutions were considered. Accuracy scores averaged 88% for monthly predictions at single water bodies and 86% for spatial predictions on a day in a specific region across Canada. At other resolutions and scales, the models only achieved low prediction accuracy of around 60%. The study represents a first attempt at predicting angler behavior in time and space at a large scale and establishes a foundation for potential future expansions in various directions.

In this paper, a new system based on combinations of a shape descriptor and a contour descriptor has been proposed for classifying inserts in milling processes according to their wear level following a computer vision based approach. To describe the wear region shape we have proposed a new descriptor called ShapeFeat and its contour has been characterized using the method BORCHIZ that, to the best of our knowledge, achieves the best performance for tool wear monitoring following a computer vision-based approach. Results show that the combination of BORCHIZ with ShapeFeat using a late fusion method improves the classification performance significantly, obtaining an accuracy of 91.44% in the binary classification (i.e. the classification of the wear as high or low) and 82.90% using three target classes (i.e. classification of the wear as high, medium or low). These results outperform the ones obtained by both descriptors used on their own, which achieve accuracies of 88.70 and 80.67% for two and three classes, respectively, using ShapeFeat and 87.06 and 80.24% with B-ORCHIZ. This study yielded encouraging results for the manufacturing community in order to classify automatically the inserts in terms of their wear for milling processes.

In this work we propose a new online, low cost and fast approach based on computer vision and machine learning to determine whether cutting tools used in edge profile milling processes are serviceable or disposable based on their wear level. We created a new dataset of 254 images of edge profile cutting heads which is, to the best of our knowledge, the first publicly available dataset with enough quality for this purpose. All the inserts were segmented and their cutting edges were cropped, obtaining 577 images of cutting edges: 301 functional and 276 disposable. The proposed method is based on (1) dividing the cutting edge image in different regions, called Wear Patches (WP), (2) characterising each one as worn or serviceable using texture descriptors based on different variants of Local Binary Patterns (LBP) and (3) determine, based on the state of these WP, if the cutting edge (and, therefore, the tool) is serviceable or disposable. We proposed and assessed five different patch division configurations. The individual WP were classified by a Support Vector Machine (SVM) with an intersection kernel. The best patch division configuration and texture descriptor for the WP achieves an accuracy of 90.26% in the detection of the disposable cutting edges. These results show a very promising opportunity for automatic wear monitoring in edge profile milling processes.

Privacy, scalability, and reliability are significant challenges in unmanned aerial vehicle (UAV) networks as distributed systems, especially when employing machine learning (ML) technologies with substantial data exchange. Recently, the application of federated learning (FL) to UAV networks has improved collaboration, privacy, resilience, and adaptability, making it a promising framework for UAV applications. However, implementing FL for UAV networks introduces drawbacks such as communication overhead, synchronization issues, scalability limitations, and resource constraints. To address these challenges, this paper presents the Blockchain-enabled Clustered and Scalable Federated Learning (BCS-FL) framework for UAV networks. This improves the decentralization, coordination, scalability, and efficiency of FL in large-scale UAV networks. The framework partitions UAV networks into separate clusters, coordinated by cluster head UAVs (CHs), to establish a connected graph. Clustering enables efficient coordination of updates to the ML model. Additionally, hybrid inter-cluster and intra-cluster model aggregation schemes generate the global model after each training round, improving collaboration and knowledge sharing among clusters. The numerical findings illustrate the achievement of convergence while also emphasizing the trade-offs between the effectiveness of training and communication efficiency.

Resonances in open quantum systems depending on at least two controllable parameters can show the phenomenon of exceptional points (EPs), where not only the eigenvalues but also the eigenvectors of two or more resonances coalesce. Their exact localization in the parameter space is challenging, in particular in systems, where the computation of the quantum spectra and resonances is numerically very expensive. We introduce an efficient machine learning algorithm to find exceptional points based on Gaussian process regression (GPR). The GPR-model is trained with an initial set of eigenvalue pairs belonging to an EP and used for a first estimation of the EP position via a numerically cheap root search. The estimate is then improved iteratively by adding selected exact eigenvalue pairs as training points to the GPR-model. The GPR-based method is developed and tested on a simple low-dimensional matrix model and then applied to a challenging real physical system, viz., the localization of EPs in the resonance spectra of excitons in cuprous oxide in external electric and magnetic fields. The precise computation of EPs, by taking into account the complete valence band structure and central-cell corrections of the crystal, can be the basis for the experimental observation of EPs in this system.

Masked Autoencoder (MAE) is a prevailing self-supervised learning method that achieves promising results in model pre-training. However, when the various downstream tasks have data distributions different from the pre-training data, the semantically irrelevant pre-training information might result in negative transfer, impeding MAE's scalability. To address this issue, we propose a novel MAEbased pre-training paradigm, Mixture of Cluster-conditional Experts (MoCE), which can be trained once but provides customized pre-training models for diverse downstream tasks. Thus, each downstream task can be allocated to its customized model pretrained with data most similar to the downstream data. Experiments on a collection of 11 downstream tasks show that MoCE outperforms the vanilla MAE by 2.45% on average. Self-supervised learning (SSL), which learns effective transferable representations without human annotations, has become a prevailing model pre-training paradigm (He et al., 2020; Chen et al., 2021a; Bao et al., 2022). Currently, the most prevalent SSL method is the Masked Autoencoder (MAE) (He et al., 2022), which constructs supervision signals from raw image data by masking random input patches and then reconstructing the missing pixels. This simple strategy has proved efficient in the training of large-scale models. For example, ViT (Dosovitskiy et al., 2021) shows impressive performance on popular benchmarks such as the ImageNet However, does MAE really scale well for various downstream tasks (Deng et al., 2009; Lin et al., 2014; Zhou et al., 2019; Han et al., 2021; Li et al., 2022a)? Preliminary studies (in Section 3.1) show that the MAE indeed suffers from negative transfer (Liu et al., 2022) when transferring to downstream tasks with very different semantics. Figure 1(a) shows that on 9 of 11 downstream tasks, an MAE pre-trained on the full ImageNet data is outperformed by the one that is pre-trained on only the semantically relevant data subsets.

The over-parameterized pre-trained models pose a great challenge to fine-tuning with limited computation resources. An intuitive solution is to prune the less informative samples from the fine-tuning dataset. A series of training-based scoring functions are proposed to quantify the informativeness of the data subset but the pruning cost becomes non-negligible due to the heavy parameter updating. For efficient pruning, it is viable to adapt the similarity scoring function of geometric-based methods from training-based to training-free. However, we empirically show that such adaption distorts the original pruning and results in inferior performance on the downstream tasks. In this paper, we propose to treat the learning complexity (LC) as the scoring function for classification and regression tasks. Specifically, the learning complexity is defined as the average predicted confidence of subnets with different capacities, which encapsulates data processing within a converged model. Then we preserve the diverse and easy samples for fine-tuning. Extensive experiments with vision datasets demonstrate the effectiveness and efficiency of the proposed scoring function for classification tasks. For the instruction fine-tuning of large language models, our method achieves state-of-the-art performance with stable convergence, outperforming the full training with only 10\% of the instruction dataset.

With the wide deployment of multimodal learning systems (MMLS) in real-world scenarios, safety concerns have become increasingly prominent. The absence of systematic research into their safety is a significant barrier to progress in this field. To bridge the gap, we present the first taxonomy for MMLS safety, identifying four essential pillars of these concerns. Leveraging this taxonomy, we conduct in-depth reviews for each pillar, highlighting key limitations based on the current state of development. Finally, we pinpoint unique challenges in MMLS safety and provide potential directions for future research.

Neurosymbolic AI combines the interpretability, parsimony, and explicit reasoning of classical symbolic approaches with the statistical learning of data-driven neural approaches. Models and policies that are simultaneously differentiable and interpretable may be key enablers of this marriage. This paper demonstrates three pathways to implementing such models and policies in a real-world reinforcement learning setting. Specifically, we study a broad class of neural networks that build interpretable semantics directly into their architecture. We reveal and highlight both the potential and the essential difficulties of combining logic, simulation, and learning. One lesson is that learning benefits from continuity and differentiability, but classical logic is discrete and non-differentiable. The relaxation to real-valued, differentiable representations presents a trade-off; the more learnable, the less interpretable. Another lesson is that using logic in the context of a numerical simulation involves a non-trivial mapping from raw (e.g., real-valued time series) simulation data to logical predicates. Some open questions this note exposes include: What are the limits of rule-based controllers, and how learnable are they? Do the differentiable interpretable approaches discussed here scale to large, complex, uncertain systems? Can we truly achieve interpretability? We highlight these and other themes across the three approaches.