Recent research has made some progress towards deep learning theory from the perspective of infinite-width NN.

Classical methods, such as weighted cross-entropy, fail when training deep nets to the terminal phase of training (TPT), that is training beyond zero training error.

Graph Neural Networks (GNNs) are a powerful solution in many settings where the data is naturally graph-structured; they enable us to learn not only from individual features of objects, but also from the connections between them [15, 20]. They make the graph topology a key part of the learning process, enabling more accurate results in a range of scenarios [19, 21]. However, graph learning is computationally expensive, and training GNNs is usually much slower than training for state of the art methods on tabular data [11, 5]. In this paper, we aim to achieve graph learning with simpler, more efficient methods for tabular data, after enriching graph nodes with information about the graph topology. Our stepping stone is the Weisfeiler-Leman algorithm (WL), a well-known technique for approximating graph isomorphism [18]. In addition to its many applications in graph theory and other areas of computer science, WL has been very influential in graph learning. It has been used in graph kernels, enabling algorithms such as support vector machines to operate directly on graphs [16, 11]. Crucially, it has been used to characterize the expressive power of several types of GNNs [8, 20, 1], suggesting WL as a suitable tool to distill the topological information that GNNs can learn from.

Cloud detection is essential for atmospheric retrievals, climate studies, and weather forecasting. We analyze infrared radiances from the Infrared Atmospheric Sounding Interferometer (IASI) onboard Meteorological Operational (MetOp) satellites to classify scenes as clear or cloudy. We apply the Support Vector Machine (SVM) approach, based on kernel methods for non-separable data. In this study, the method is implemented for Cloud Identification (CISVM) to classify the test set using radiances or brightness temperatures, with dimensionality reduction through Principal Component Analysis (PCA) and cloud-sensitive channel selection to focus on the most informative features. Our best configuration achieves 88.30 percent agreement with reference labels and shows strong consistency with cloud masks from the Moderate Resolution Imaging Spectroradiometer (MODIS), with the largest discrepancies in polar regions due to sensor differences. These results demonstrate that CISVM is a robust, flexible, and efficient method for automated cloud classification from infrared radiances, suitable for operational retrievals and future missions such as Far infrared Outgoing Radiation Understanding and Monitoring (FORUM), the ninth European Space Agency Earth Explorer Mission.

Low-mass stars and brown dwarfs -- spectral types (SpTs) M0 and later -- play a significant role in studying stellar and substellar processes and demographics, reaching down to planetary-mass objects. Currently, the classification of these sources remains heavily reliant on visual inspection of spectral features, equivalent width measurements, or narrow-/wide-band spectral indices. Recent advances in machine learning (ML) methods offer automated approaches for spectral typing, which are becoming increasingly important as large spectroscopic surveys such as Gaia, SDSS, and SPHEREx generate datasets containing millions of spectra. We investigate the application of ML in spectral type classification on low-resolution (R $\sim$ 120) near-infrared spectra of M0--T9 dwarfs obtained with the SpeX instrument on the NASA Infrared Telescope Facility. We specifically aim to classify the gravity- and metallicity-dependent subclasses for late-type dwarfs. We used binned fluxes as input features and compared the efficacy of spectral type estimators built using Random Forest (RF), Support Vector Machine (SVM), and K-Nearest Neighbor (KNN) models. We tested the influence of different normalizations and analyzed the relative importance of different spectral regions for surface gravity and metallicity subclass classification. Our best-performing model (using KNN) classifies 95.5 $\pm$ 0.6% of sources to within $\pm$1 SpT, and assigns surface gravity and metallicity subclasses with 89.5 $\pm$ 0.9% accuracy. We test the dependence of signal-to-noise ratio on classification accuracy and find sources with SNR $\gtrsim$ 60 have $\gtrsim$ 95% accuracy. We also find that zy-band plays the most prominent role in the RF model, with FeH and TiO having the highest feature importance.

This paper presents the "Non-native Children's Automatic Speech Assessment" (NOCASA) - a data competition part of the IEEE MLSP 2025 conference. NOCASA challenges participants to develop new systems that can assess single-word pronunciations of young second language (L2) learners as part of a gamified pronunciation training app. To achieve this, several issues must be addressed, most notably the limited nature of available training data and the highly unbalanced distribution among the pronunciation level categories. To expedite the development, we provide a pseudo-anonymized training data (TeflonNorL2), containing 10,334 recordings from 44 speakers attempting to pronounce 205 distinct Norwegian words, human-rated on a 1 to 5 scale (number of stars that should be given in the game). In addition to the data, two already trained systems are released as official baselines: an SVM classifier trained on the ComParE_16 acoustic feature set and a multi-task wav2vec 2.0 model. The latter achieves the best performance on the challenge test set, with an unweighted average recall (UAR) of 36.37%.

Partial Optimal Transport (POT) has recently emerged as a central tool in various Machine Learning (ML) applications. It lifts the stringent assumption of the conventional Optimal Transport (OT) that input measures are of equal masses, which is often not guaranteed in real-world datasets, and thus offers greater flexibility by permitting transport between unbalanced input measures. Nevertheless, existing major solvers for POT commonly rely on entropic regularization for acceleration and thus return dense transport plans, hindering the adoption of POT in various applications that favor sparsity. In this paper, as an alternative approach to the entropic POT formulation in the literature, we propose a novel formulation of POT with quadratic regularization, hence termed quadratic regularized POT (QPOT), which induces sparsity to the transport plan and consequently facilitates the adoption of POT in many applications with sparsity requirements. Extensive experiments on synthetic and CIFAR-10 datasets, as well as real-world applications such as color transfer and domain adaptations, consistently demonstrate the improved sparsity and favorable performance of our proposed QPOT formulation.

--Personalised music-based interventions offer a powerful means of supporting motor rehabilitation by dynamically tailoring auditory stimuli to provide external timekeeping cues, modulate affective states, and stabilise gait patterns. Gener-alisable Brain-Computer Interfaces (BCIs) thus hold promise for adapting these interventions across individuals. However, inter-subject variability in EEG signals, further compounded by movement-induced artefacts and motor planning differences, hinders the generalisability of BCIs and results in lengthy calibration processes. We propose Individual T angent Space Alignment (ITSA), a novel pre-alignment strategy incorporating subject-specific recentering, distribution matching, and supervised rotational alignment to enhance cross-subject generalisation. Using leave-one-subject-out cross-validation, 'ITSA' demonstrates significant performance improvements across subjects and conditions. The parallel fusion approach shows the greatest enhancement over its sequential counterpart, with robust performance maintained across varying data conditions and electrode configurations. The code will be made publicly available at the time of publication. Brain-computer interfaces (BCI) are effective tools for motor rehabilitation and understanding musical stimulus effects on motor function [1]-[4]. In stroke rehabilitation, BCIs decode the user's intention from brain electrical activity to provide sensorimotor feedback and enable control of external devices or motor functions [5], [6]. The use of these BCI strategies for motor rehabilitation has been grouped into either assistive or rehabilitative. The former focuses on bypassing the damaged neuronal pathways to provide alternative control of the external devices, whereas the latter aims to exploit neuro-plasticity by promoting the recovery of damaged pathways and therefore restoring impaired motor functions [5]. Electroen-cephalography signals are often used for the input of BCIs as they provide portable, non-invasive, low-cost solutions and have high temporal resolution [7].