Summary and Contributions: The paper deals with coresets (data summary obtained by subsampling and approximating the objective function for all queries) for least squares regression on panel data. In the usual "cross-sectional" setting the data consists of N individuals with d features each. Panel data extends this by introducing a time-series for each individual, consisting of the d features measured at T time steps. Moreover a correlation structure is introduced between the time steps to model dependencies over the time axes. The objective is to minimize the sum over all individuals of the least squares regressions subject to correlations between the time steps. The variables are thus the regression parameters as well as the defining parameters of the covariance structure.

In this paper, we evaluate the performance of four randomized optimization algorithms: Randomized Hill Climbing (RHC), Simulated Annealing (SA), Genetic Algorithms (GA), and MIMIC (Mutual Information Maximizing Input Clustering), across three distinct types of problems: binary, permutation, and combinatorial. We systematically compare these algorithms using a set of benchmark fitness functions that highlight the specific challenges and requirements of each problem category. Our study analyzes each algorithm's effectiveness based on key performance metrics, including solution quality, convergence speed, computational cost, and robustness. Results show that while MIMIC and GA excel in producing high-quality solutions for binary and combinatorial problems, their computational demands vary significantly. RHC and SA, while computationally less expensive, demonstrate limited performance in complex problem landscapes. The findings offer valuable insights into the trade-offs between different optimization strategies and provide practical guidance for selecting the appropriate algorithm based on the type of problems, accuracy requirements, and computational constraints.

The study of learning causal structure with latent variables has advanced the understanding of the world by uncovering causal relationships and latent factors, e.g., Causal Representation Learning (CRL). However, in real-world scenarios, such as those in climate systems, causal relationships are often nonparametric, dynamic, and exist among both observed variables and latent variables. These challenges motivate us to consider a general setting in which causal relations are nonparametric and unrestricted in their occurrence, which is unconventional to current methods. To solve this problem, with the aid of 3-measurement in temporal structure, we theoretically show that both latent variables and processes can be identified up to minor indeterminacy under mild assumptions. Moreover, we tackle the general nonlinear Causal Discovery (CD) from observations, e.g., temperature, as a specific task of learning independent representation, through the principle of functional equivalence. Based on these insights, we develop an estimation approach simultaneously recovering both the observed causal structure and latent causal process in a nontrivial manner. Simulation studies validate the theoretical foundations and demonstrate the effectiveness of the proposed methodology. In the experiments involving climate data, this approach offers a powerful and in-depth understanding of the climate system.

Foundation models have made rapid advances in many domains including Earth observation, where Geospatial Foundation Models (GFMs) can help address global challenges such as climate change, agriculture, and disaster response. Previous work on GFMs focused on tailoring model architecture and pre-text tasks, and did not investigate the impact of pre-training data selection on model performance. However, recent works from other domains show that the pre-training data distribution is an important factor influencing the performance of the foundation models. With this motivation, our research explores how the geographic distribution of pre-training data affects the performance of GFMs. We evaluated several pre-training data distributions by sampling different compositions from a global data pool. Our experiments with two GFMs on downstream tasks indicate that balanced and globally representative data compositions often outperform region-specific sampling, highlighting the importance of diversity and global coverage in pre-training data. Our results suggest that the most appropriate data sampling technique may depend on the specific GFM architecture. These findings will support the development of robust GFMs by incorporating quality pre-training data distributions, ultimately improving machine learning solutions for Earth observation.

The attribution of the author of an art piece is typically a laborious manual process, usually relying on subjective evaluations of expert figures. However, there are some situations in which quantitative features of the artwork can support these evaluations. The extraction of these features can sometimes be automated, for instance, with the use of Machine Learning (ML) techniques. An example of these features is represented by repeated, mechanically impressed patterns, called punches, present chiefly in 13th and 14th-century panel paintings from Tuscany. Previous research in art history showcased a strong connection between the shapes of punches and specific artists or workshops, suggesting the possibility of using these quantitative cues to support the attribution. In the present work, we first collect a dataset of large-scale images of these panel paintings. Then, using YOLOv10, a recent and popular object detection model, we train a ML pipeline to perform object detection on the punches contained in the images. Due to the large size of the images, the detection procedure is split across multiple frames by adopting a sliding-window approach with overlaps, after which the predictions are combined for the whole image using a custom non-maximal suppression routine. Our results indicate how art historians working in the field can reliably use our method for the identification and extraction of punches.

This paper discusses an approach to inertial parameter estimation for the case of cargo carrying spacecraft that is based on causal learning, i.e. learning from the responses of the spacecraft, under actuation. Different spacecraft configurations (inertial parameter sets) are simulated under different actuation profiles, in order to produce an optimised time-series clustering classifier that can be used to distinguish between them. The actuation is comprised of finite sequences of constant inputs that are applied in order, based on typical actuators available. By learning from the system's responses across multiple input sequences, and then applying measures of time-series similarity and F1-score, an optimal actuation sequence can be chosen either for one specific system configuration or for the overall set of possible configurations. This allows for both estimation of the inertial parameter set without any prior knowledge of state, as well as validation of transitions between different configurations after a deployment event. The optimisation of the actuation sequence is handled by a reinforcement learning model that uses the proximal policy optimisation (PPO) algorithm, by repeatedly trying different sequences and evaluating the impact on classifier performance according to a multi-objective metric.

We present ENTIRE, a novel approach for volume rendering time prediction. Time-dependent volume data from simulations or experiments typically comprise complex deforming structures across hundreds or thousands of time steps, which in addition to the camera configuration has a significant impact on rendering performance. We first extract a feature vector from a volume that captures its structure that is relevant for rendering time performance. Then we combine this feature vector with further relevant parameters (e.g. camera setup), and with this perform the final prediction. Our experiments conducted on various datasets demonstrate that our model is capable of efficiently achieving high prediction accuracy with fast response rates. We showcase ENTIRE's capability of enabling dynamic parameter adaptation for stable frame rates and load balancing in two case studies.

With the advent of the COVID-19 pandemic, ultrasound imaging has emerged as a promising technique for COVID-19 detection, due to its non-invasive nature, affordability, and portability. In response, researchers have focused on developing AI-based scoring systems to provide real-time diagnostic support. However, the limited size and lack of proper annotation in publicly available ultrasound datasets pose significant challenges for training a robust AI model. This paper proposes MeDiVLAD, a novel pipeline to address the above issue for multi-level lung-ultrasound (LUS) severity scoring. In particular, we leverage self-knowledge distillation to pretrain a vision transformer (ViT) without label and aggregate frame-level features via dual-level VLAD aggregation. We show that with minimal finetuning, MeDiVLAD outperforms conventional fully-supervised methods in both frame- and video-level scoring, while offering classification reasoning with exceptional quality. This superior performance enables key applications such as the automatic identification of critical lung pathology areas and provides a robust solution for broader medical video classification tasks.

Self-supervised learning holds the promise to learn good representations from real-world continuous uncurated data streams. However, most existing works in visual self-supervised learning focus on static images or artificial data streams. Towards exploring a more realistic learning substrate, we investigate streaming self-supervised learning from long-form real-world egocentric video streams. Inspired by the event segmentation mechanism in human perception and memory, we propose "Memory Storyboard" that groups recent past frames into temporal segments for more effective summarization of the past visual streams for memory replay. To accommodate efficient temporal segmentation, we propose a two-tier memory hierarchy: the recent past is stored in a short-term memory, and the storyboard temporal segments are then transferred to a long-term memory. Experiments on real-world egocentric video datasets including SAYCam and KrishnaCam show that contrastive learning objectives on top of storyboard frames result in semantically meaningful representations which outperform those produced by state-of-the-art unsupervised continual learning methods.

Collaborative learning (CL) enables multiple participants to jointly train machine learning (ML) models on decentralized data sources without raw data sharing. While the primary goal of CL is to maximize the expected accuracy gain for each participant, it is also important to ensure that the gains are fairly distributed. Specifically, no client should be negatively impacted by the collaboration, and the individual gains must ideally be commensurate with the contributions. Most existing CL algorithms require central coordination and focus on the gain maximization objective while ignoring collaborative fairness. In this work, we first show that the existing measure of collaborative fairness based on the correlation between accuracy values without and with collaboration has drawbacks because it does not account for negative collaboration gain. We argue that maximizing mean collaboration gain (MCG) while simultaneously minimizing the collaboration gain spread (CGS) is a fairer alternative. Next, we propose the CYCle protocol that enables individual participants in a private decentralized learning (PDL) framework to achieve this objective through a novel reputation scoring method based on gradient alignment between the local cross-entropy and distillation losses. Experiments on the CIFAR-10, CIFAR-100, and Fed-ISIC2019 datasets empirically demonstrate the effectiveness of the CYCle protocol to ensure positive and fair collaboration gain for all participants, even in cases where the data distributions of participants are highly skewed. For the simple mean estimation problem with two participants, we also theoretically show that CYCle performs better than standard FedAvg, especially when there is large statistical heterogeneity.