technocracy

Active learning for photonic crystals explores the integration of analytic approximate Bayesian last layer neural networks (LL-BNNs) with uncertainty-driven sample selection to accelerate photonic band gap prediction. We employ an analytic LL-BNN formulation, corresponding to the infinite Monte Carlo sample limit, to obtain uncertainty estimates that are strongly correlated with the true predictive error on unlabeled candidate structures. These uncertainty scores drive an active learning strategy that prioritizes the most informative simulations during training. Applied to the task […]

Ver mais

We introduce a principled learning to optimize (L2O) framework for solving fixed-point problems involving general nonexpansive mappings. Our idea is to deliberately inject summable perturbations into a standard Krasnosel’skii-Mann iteration to improve its average-case performance over a specific distribution of problems while retaining its convergence guarantees. Under a metric sub-regularity assumption, we prove that the proposed parametrization includes only iterations that locally achieve linear convergence-up to a vanishing bias term-and that it encompasses all iterations that do so […]

Ver mais

Membership inference attacks (MIAs) pose a serious threat to the privacy of machine learning models by allowing adversaries to determine whether a specific data sample was included in the training set. Although federated learning (FL) is widely regarded as a privacy-aware training paradigm due to its decentralized nature, recent evidence shows that the final global model can still leak sensitive membership information through black-box access. In this paper, we introduce Res-MIA, a novel training-free and black-box membership inference […]

Ver mais

Artificial intelligence now outperforms humans in several scientific and engineering tasks, yet its internal representations often remain opaque. In this Perspective, we argue that explainable artificial intelligence (XAI), combined with causal reasoning, enables {it learning from the learners}. Focusing on discovery, optimization and certification, we show how the combination of foundation models and explainability methods allows the extraction of causal mechanisms, guides robust design and control, and supports trust and accountability in high-stakes applications. We discuss challenges in […]

Ver mais

arXiv:2601.02374v1 Announce Type: new Abstract: Large Language Models (LLM) have experienced strong development in recent years, with varied applications. This paper uses LLMs to develop a post-hoc process that provides more elaborated explanations of the results of food recommendation systems. By combining LLM with a hybrid extraction of key variables using SHAP, we obtain dynamic, convincing and more comprehensive explanations to lay user, compared to those in the literature. This approach enhances user trust and transparency by making […]

Ver mais

arXiv:2602.19790v1 Announce Type: cross Abstract: Concept drift — the change of the distribution over time — poses significant challenges for learning systems and is of central interest for monitoring. Understanding drift is thus paramount, and drift localization — determining which samples are affected by the drift — is essential. While several approaches exist, most rely on local testing schemes, which tend to fail in high-dimensional, low-signal settings. In this work, we consider a fundamentally different approach based on […]

Ver mais

arXiv:2601.08991v1 Announce Type: new Abstract: The ubiquity of machine learning (ML) and the demand for ever-larger models bring an increase in energy consumption and environmental impact. However, little is known about the energy scaling laws in ML, and existing research focuses on training cost — ignoring the larger cost of inference. Furthermore, tools for measuring the energy consumption of ML do not provide actionable feedback. To address these gaps, we developed Energy Consumption Optimiser (ECOpt): a hyperparameter tuner […]

Ver mais

arXiv:2312.16819v4 Announce Type: replace-cross Abstract: We consider the optimization problem associated with training two-layer ReLU networks with (d) inputs under the squared loss, where the labels are generated by a target network. Recent work has identified two distinct classes of infinite families of minima: one whose training loss vanishes in the high-dimensional limit, and another whose loss remains bounded away from zero. The latter family is empirically avoided by stochastic gradient descent, hence emph{hidden}, motivating the search for […]

Ver mais

In hierarchical multi-label classification, a persistent challenge is enabling model predictions to reach deeper levels of the hierarchy for more detailed or fine-grained classifications. This difficulty partly arises from the natural rarity of certain classes (or hierarchical nodes) and the hierarchical constraint that ensures child nodes are almost always less frequent than their parents. To address this, we propose a weighted loss objective for neural networks that combines node-wise imbalance weighting with focal weighting components, the latter leveraging […]

Ver mais