arXiv:2501.19237v2 Announce Type: replace-cross Abstract: Ensuring reliable data collection in large-scale particle physics experiments demands Data Quality Monitoring (DQM) procedures to detect possible detector malfunctions and preserve data integrity. Traditionally, this resource-intensive task has been handled by human shifters who…
arXiv:2509.14585v1 Announce Type: new Abstract: This paper introduces a structured and interpretable online policy-iteration framework for reinforcement learning (RL), built around the novel class of sparse Gaussian mixture model Q-functions (S-GMM-QFs). Extending earlier work that trained GMM-QFs offline, the proposed…
arXiv:2507.06344v2 Announce Type: replace-cross Abstract: Variational Quantum Algorithms (VQAs) are promising candidates for near-term quantum computing, yet they face scalability challenges due to barren plateaus, where gradients vanish exponentially in the system size. Recent conjectures suggest that avoiding barren plateaus…
arXiv:2509.14600v1 Announce Type: new Abstract: Molecular dynamics (MD) simulations provide atomistic insight into biomolecular systems but are often limited by high computational costs required to access long timescales. Coarse-grained machine learning models offer a promising avenue for accelerating sampling, yet…
arXiv:2509.14384v1 Announce Type: new Abstract: In this paper, we investigate the efficiency of Deep Neural Networks (DNNs) to approximate the solution of a nonlocal conservation law derived from the identical-oscillator Kuramoto model, focusing on the evaluation of an architectural choice…
arXiv:2509.14603v1 Announce Type: new Abstract: Split Federated Learning (SFL) has emerged as an efficient alternative to traditional Federated Learning (FL) by reducing client-side computation through model partitioning. However, exchanging of intermediate activations and model updates introduces significant privacy risks, especially…
arXiv:2509.15001v1 Announce Type: cross Abstract: Child-centered long-form recordings are essential for studying early language development, but existing speech models trained on clean adult data perform poorly due to acoustic and linguistic differences. We introduce BabyHuBERT, the first self-supervised speech representation…
arXiv:2509.14617v1 Announce Type: new Abstract: Energy-efficient medical data classification is essential for modern disease screening, particularly in home and field healthcare where embedded devices are prevalent. While deep learning models achieve state-of-the-art accuracy, their substantial energy consumption and reliance on…
arXiv:2509.15141v1 Announce Type: cross Abstract: Empirical Risk Minimization (ERM) is a foundational framework for supervised learning but primarily optimizes average-case performance, often neglecting fairness and robustness considerations. Tilted Empirical Risk Minimization (TERM) extends ERM by introducing an exponential tilt hyperparameter…
arXiv:2509.14633v1 Announce Type: new Abstract: As privacy and security take center stage in AI, machine unlearning, the ability to erase specific knowledge from models, has garnered increasing attention. However, existing methods overly prioritize efficiency and aggressive forgetting, which introduces notable…
