arXiv:2512.16607v2 Announce Type: replace Abstract: Sampling configurations in thermodynamic equilibrium is a long-standing challenge in statistical physics. Boltzmann generators address this problem by employing generative models…
arXiv:2607.21409v1 Announce Type: cross Abstract: A central challenge in quantum machine learning is understanding the scaling behavior of parameterized quantum circuits (PQCs). In particular, it remains…
arXiv:2510.24616v4 Announce Type: replace Abstract: For four decades statistical physics has been providing a framework to analyse neural networks. A long-standing question remained on its capacity…
arXiv:2607.21366v1 Announce Type: cross Abstract: Deep neural networks encode complex representations, but deconstructing this internal knowledge remains a challenge. Given the link between learning and compression,…
arXiv:2607.21098v1 Announce Type: cross Abstract: Temporal point processes (TPPs) provide a general and flexible framework for modeling sequences of events in continuous time. Neural networks have…
arXiv:2607.20818v1 Announce Type: cross Abstract: Many instances of sequential sampling, including audit and inspection scheduling, representative sampling, and treatment assignment, require selections to be distributed evenly…
arXiv:2508.11780v3 Announce Type: replace-cross Abstract: Recent developments in computer vision have made segmented images widely available across many domains, such as medicine, where segmented radiographs play…
arXiv:2607.20760v1 Announce Type: cross Abstract: The twoblock clustering tree (tbtree) is introduced as a highly interpretable regression tree for multivariate responses. Twoblock trees are deterministic decision…
arXiv:2607.21200v1 Announce Type: new Abstract: The modeling of hydrometeorological time series with limited observations is a key challenge in the monitoring of hydro-systems and water resources,…
arXiv:2607.20526v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed in settings where fluent but incorrect answers can be costly. In these settings, accuracy…
arXiv:2607.20578v1 Announce Type: cross Abstract: We study Gaussian-width complexity on statistical manifolds through a pair of functionals: the primal Fisher width $w_G(T) = w(G^{1/2}T)$, induced by…
arXiv:2607.20714v1 Announce Type: cross Abstract: Let $X(t)$, $tin K$, be a centred Gaussian process with continuous sample paths on a compact metric space $K$, and let…
arXiv:2607.20594v1 Announce Type: cross Abstract: When does a weight-tied looped transformer -- one block applied T times -- implement an actual algorithm? We answer with four…
arXiv:2501.18897v4 Announce Type: replace Abstract: Generative models have achieved remarkable success across a range of applications, yet their evaluation still lacks principled uncertainty quantification. In this…
arXiv:2605.25050v2 Announce Type: replace-cross Abstract: Integrating multimodal datasets in clinical oncology is frequently hindered by high dimensionality and blockwise missingness, where entire data sources are unavailable…
arXiv:2511.02258v3 Announce Type: replace Abstract: This paper studies the high-dimensional scaling limits of online stochastic gradient descent (SGD). Building on the work of Ben Arous, Gheissari,…
arXiv:2510.11147v2 Announce Type: replace Abstract: This paper introduces torchsom, an open-source Python library that provides a reference implementation of the Self-Organizing Map (SOM) in PyTorch. This…
arXiv:2601.15363v2 Announce Type: replace Abstract: Functional bilevel optimization (FBO) provides a powerful framework for hierarchical learning in function spaces, yet current methods are limited to static…
arXiv:2607.21220v1 Announce Type: new Abstract: Expensive simulation-driven design is widely used in engineering to identify requirement-satisfying designs with as few high-fidelity simulations as possible. Most existing…
arXiv:2607.20792v1 Announce Type: cross Abstract: Memoir combines per-sample fast memory, shared slow parameters, variable-depth latent recurrence, and a future-latent energy objective. We test its riskiest coupling:…
arXiv:2607.21005v1 Announce Type: cross Abstract: Most explanations of training instability focus on emph{learning-rate criticality}, typically characterized by the Edge of Stability, beyond which optimization becomes unstable.…
arXiv:2508.20458v2 Announce Type: replace Abstract: This article proposes the Ecological Cycle Optimizer (ECO), a novel metaheuristic algorithm inspired by energy flow and material cycling within ecosystems.…
arXiv:2512.19321v2 Announce Type: replace Abstract: Urban underground cable construction is essential for enhancing power grid reliability, yet the high construction costs demand systematic optimization. Constrained by…
arXiv:2601.21778v3 Announce Type: replace Abstract: Spiking Neural Networks (SNNs) can achieve competitive performance by converting already existing well-trained Artificial Neural Networks (ANNs), avoiding further costly training.…