Aggregation methods have emerged as a powerful and flexible framework in statistical learning, providing unified solutions across diverse problems such as regression, classification, and density estimation. In the context of generalized linear models (GLMs), where responses follow exponential family distributions, aggregation offers an attractive alternative to classical parametric modeling. This paper investigates the problem of sparse aggregation in GLMs, aiming to approximate the true parameter vector by a sparse linear combination of predictors. We prove that an exponential weighted aggregation scheme yields a sharp oracle inequality for the Kullback-Leibler risk with leading constant equal to one, while also attaining the minimax-optimal rate of aggregation. These results are further enhanced by establishing high-probability bounds on the excess risk.

Given the demand for responsible and trustworthy AI for education, this study evaluates symbolic, sub-symbolic, and neural-symbolic AI (NSAI) in terms of generalizability and interpretability. Our extensive experiments on balanced and imbalanced self-regulated learning datasets of Estonian primary school students predicting 7th-grade mathematics national test performance showed that symbolic and sub-symbolic methods performed well on balanced data but struggled to identify low performers in imbalanced datasets. Interestingly, symbolic and sub-symbolic methods emphasized different factors in their decision-making: symbolic approaches primarily relied on cognitive and motivational factors, while sub-symbolic methods focused more on cognitive aspects, learnt knowledge, and the demographic variable of gender -- yet both largely overlooked metacognitive factors. The NSAI method, on the other hand, showed advantages by: (i) being more generalizable across both classes -- even in imbalanced datasets -- as its symbolic knowledge component compensated for the underrepresented class; and (ii) relying on a more integrated set of factors in its decision-making, including motivation, (meta)cognition, and learnt knowledge, thus offering a comprehensive and theoretically grounded interpretability framework. These contrasting findings highlight the need for a holistic comparison of AI methods before drawing conclusions based solely on predictive performance. They also underscore the potential of hybrid, human-centred NSAI methods to address the limitations of other AI families and move us closer to responsible AI for education. Specifically, by enabling stakeholders to contribute to AI design, NSAI aligns learned patterns with theoretical constructs, incorporates factors like motivation and metacognition, and strengthens the trustworthiness and responsibility of educational data mining.

This paper addresses the problem of sparse phase retrieval, a fundamental inverse problem in applied mathematics, physics, and engineering, where a signal need to be reconstructed using only the magnitude of its transformation while phase information remains inaccessible. Leveraging the inherent sparsity of many real-world signals, we introduce a novel sparse quasi-Bayesian approach and provide the first theoretical guarantees for such an approach. Specifically, we employ a scaled Student distribution as a continuous shrinkage prior to enforce sparsity and analyze the method using the PAC-Bayesian inequality framework. Our results establish that the proposed Bayesian estimator achieves minimax-optimal convergence rates under sub-exponential noise, matching those of state-of-the-art frequentist methods. To ensure computational feasibility, we develop an efficient Langevin Monte Carlo sampling algorithm. Through numerical experiments, we demonstrate that our method performs comparably to existing frequentist techniques, highlighting its potential as a principled alternative for sparse phase retrieval in noisy settings.

Exponential random graph models (ERGMs) are flexible probabilistic frameworks to model statistical networks through a variety of network summary statistics. Conventional Bayesian estimation for ERGMs involves iteratively exchanging with an auxiliary variable due to the intractability of ERGMs, however, this approach lacks scalability to large-scale implementations. Neural posterior estimation (NPE) is a recent advancement in simulation-based inference, using a neural network based density estimator to infer the posterior for models with doubly intractable likelihoods for which simulations can be generated. While NPE has been successfully adopted in various fields such as cosmology, little research has investigated its use for ERGMs. Performing NPE on ERGM not only provides a differing angle of resolving estimation for the intractable ERGM likelihoods but also allows more efficient and scalable inference using the amortisation properties of NPE, and therefore, we investigate how NPE can be effectively implemented in ERGMs. In this study, we present the first systematic implementation of NPE for ERGMs, rigorously evaluating potential biases, interpreting the biases magnitudes, and comparing NPE fittings against conventional Bayesian ERGM fittings. More importantly, our work highlights ERGM-specific areas that may impose particular challenges for the adoption of NPE.

Deep learning has emerged as a transformative technology in agricultural science, particularly for the identification of plant diseases. This approach leverages advanced algorithms, primarily Convolutional Neural Networks (CNNs), to analyze images of plants and accurately diagnose diseases that threaten crop health and yield (Mohanty et al., 2016; Guo et al., 2020; Saleem et al., 2020; Ahmed & Y adav, 2023; Jung et al., 2023; Shoaib et al., 2023; Pacal et al., 2024). Plant diseases pose a significant threat to global food security, leading to substantial yield losses and economic impacts on agriculture. T raditional methods of disease identification often rely on visual assessments by trained professionals, which can be time-consuming, subjective, and prone to errors (Jafar et al., 2024). As a result, there is a pressing need for automated systems that can provide rapid and accurate disease detection to support farmers and agricultural experts in managing crop health effectively . Deep learning models, especially CNNs, have been shown to outperform traditional methods in terms of accuracy and efficiency . These models can learn hierarchical representations from raw image data, enabling them to identify complex patterns associated with various plant diseases. Recent studies have demonstrated that CNNs can achieve accuracy rates as high as 99.35% when classifying images of diseased and healthy plants. The architecture of CNNs typically includes layers for feature extraction and classification, allowing them to process visual information effectively .

User profiling, the practice of collecting user information for personalized recommendations, has become widespread, driving progress in technology. However, this growth poses a threat to user privacy, as devices often collect sensitive data without their owners' awareness. This article aims to consolidate knowledge on user profiling, exploring various approaches and associated challenges. Through the lens of two companies sharing user data and an analysis of 18 popular Android applications in India across various categories, including $\textit{Social, Education, Entertainment, Travel, Shopping and Others}$, the article unveils privacy vulnerabilities. Further, the article propose an enhanced machine learning framework, employing decision trees and neural networks, that improves state-of-the-art classifiers in detecting personal information exposure. Leveraging the XAI (explainable artificial intelligence) algorithm LIME (Local Interpretable Model-agnostic Explanations), it enhances interpretability, crucial for reliably identifying sensitive data. Results demonstrate a noteworthy performance boost, achieving a $75.01\%$ accuracy with a reduced training time of $3.62$ seconds for neural networks. Concluding, the paper suggests research directions to strengthen digital security measures.

Based on existing ideas in the field of imprecise probabilities, we present a new approach for assessing the reliability of the individual predictions of a generative probabilistic classifier. We call this approach robustness quantification, compare it to uncertainty quantification, and demonstrate that it continues to work well even for classifiers that are learned from small training sets that are sampled from a shifted distribution.

Diffusion models have emerged as powerful generative tools with applications in computer vision and scientific machine learning (SciML), where they have been used to solve large-scale probabilistic inverse problems. Traditionally, these models have been derived using principles of variational inference, denoising, statistical signal processing, and stochastic differential equations. In contrast to the conventional presentation, in this study we derive diffusion models using ideas from linear partial differential equations and demonstrate that this approach has several benefits that include a constructive derivation of the forward and reverse processes, a unified derivation of multiple formulations and sampling strategies, and the discovery of a new class of models. We also apply the conditional version of these models to solving canonical conditional density estimation problems and challenging inverse problems. These problems help establish benchmarks for systematically quantifying the performance of different formulations and sampling strategies in this study, and for future studies. Finally, we identify and implement a mechanism through which a single diffusion model can be applied to measurements obtained from multiple measurement operators. Taken together, the contents of this manuscript provide a new understanding and several new directions in the application of diffusion models to solving physics-based inverse problems.

--Performance gap across classes remains a persistent challenge in machine learning, often attributed to variations in class hardness. One way to quantify class hardness is through sample complexity - the minimum number of samples required to effectively learn a given class. Sample complexity theory suggests that class hardness is driven by differences in the amount of data required for generalization. That is, harder classes need substantially more samples to achieve generalization. Therefore, hardness-based resampling is a promising approach to mitigate these performance disparities. While resampling has been studied extensively in data-imbalanced settings, its impact on balanced datasets remains unexplored. This raises the fundamental question whether resampling is effective because it addresses data imbalance or hardness imbalance. We begin addressing this question by introducing class imbalance into balanced datasets and evaluate its effect on performance disparities. We oversample hard classes and undersample easy classes to bring hard classes closer to their sample complexity requirements while maintaining a constant dataset size for fairness. We estimate class-level hardness using the Area Under the Margin (AUM) hardness estimator and leverage it to compute resampling ratios. Using these ratios, we perform hardness-based resampling on the well-known CIF AR-10 and CIF AR-100 datasets. Contrary to theoretical expectations, our results show that hardness-based resampling does not meaningfully affect class-wise performance disparities. T o explain this discrepancy, we conduct detailed analyses to identify key challenges unique to hardness-based imbalance, distinguishing it from traditional data-based imbalance. Our insights help explain why theoretical sample complexity expectations fail to translate into practical performance gains and we provide guidelines for future research. CCESS to large datasets has fueled recent machine learning breakthroughs [1], yet data efficiency remains a critical challenge [2]. Addressing this challenge requires a deep understanding of instance, class, and dataset level hardness. Empirical works reveal large performance gaps across classes [3]-[5] and clear distinctions between easy (e.g. ImageNet) [6], [7] as shown in see Figure 1. Pawel Pukowski is with the University of Sheffield. V enet Osmani is with the Digital Environment Research Institute, Queen Mary University of London. This work has been submitted to the IEEE for possible publication. Figure 1: Training an ensemble of ten ResNet18 networks on CIFAR-10 (left) and CIFAR-100 (right) reveals large recall gaps across classes, despite the balanced nature of these datasets. Paired with significantly larger recall gaps across classes for CIFAR-100 than CIFAR-10, this shows class-and dataset-level hardness discrepancies, which we call hardness-based imbalance.

Cancer remains a leading global health challenge and a major cause of mortality. This study leverages machine learning (ML) to predict the survivability of cancer patients with metastatic patterns using the comprehensive MSK-MET dataset, which includes genomic and clinical data from 25,775 patients across 27 cancer types. We evaluated five ML models-XGBoost, Naïve Bayes, Decision Tree, Logistic Regression, and Random Fores using hyperparameter tuning and grid search. XGBoost emerged as the best performer with an area under the curve (AUC) of 0.82. To enhance model interpretability, SHapley Additive exPlanations (SHAP) were applied, revealing key predictors such as metastatic site count, tumor mutation burden, fraction of genome altered, and organ-specific metastases. Further survival analysis using Kaplan-Meier curves, Cox Proportional Hazards models, and XGBoost Survival Analysis identified significant predictors of patient outcomes, offering actionable insights for clinicians. These findings could aid in personalized prognosis and treatment planning, ultimately improving patient care.