English
Related papers

Related papers: Incremental Generation is Necessary and Sufficient…

200 papers

Quantum ergodicity asserts that almost all infinite sequences of eigenstates of a quantized ergodic system are equidistributed in the phase space. On the other hand, there are might exist exceptional sequences which converge to different…

Mathematical Physics · Physics 2015-05-13 Boris Gutkin

Many practical problems need the output of a machine learning model to satisfy a set of constraints, $K$. Nevertheless, there is no known guarantee that classical neural network architectures can exactly encode constraints while…

Machine Learning · Computer Science 2022-02-10 Anastasis Kratsios , Behnoosh Zamanlooy , Tianlin Liu , Ivan Dokmanić

Modern generative modelling systems are increasingly improved by expanding model capacity, training data, and computational resources. While empirical studies have documented such scaling behaviour across architectures including generative…

Logic in Computer Science · Computer Science 2026-03-23 Angshul Majumdar

We construct the general first-order hydrodynamic theory invariant under time translations, the Euclidean group of spatial transformations and preserving particle number, that is with symmetry group $\mathbb{R}_t\times$ISO$(d)\times$U$(1)$.…

High Energy Physics - Theory · Physics 2020-08-26 Igor Novak , Julian Sonner , Benjamin Withers

A normalizing flow models a complex probability density as an invertible transformation of a simple base density. Flows based on either coupling or autoregressive transforms both offer exact density evaluation and sampling, but rely on the…

Machine Learning · Statistics 2019-12-03 Conor Durkan , Artur Bekasov , Iain Murray , George Papamakarios

We present a novel theoretical framework for understanding the expressive power of normalizing flows. Despite their prevalence in scientific applications, a comprehensive understanding of flows remains elusive due to their restricted…

Machine Learning · Computer Science 2025-01-30 Felix Draxler , Stefan Wahl , Christoph Schnörr , Ullrich Köthe

A topological group $G$ is topologically normally generated if there exists $g \in G$ such that the normal closure of $g$ is dense in $G$. Let $S$ be a tame, infinite type surface whose mapping class group $\mathrm{Map}(S)$ is generated by…

Group Theory · Mathematics 2026-02-04 Juhun Baik

The geometric approach to optimal transport and information theory has triggered the interpretation of probability densities as an infinite-dimensional Riemannian manifold. The most studied Riemannian structures are Otto's metric, yielding…

Analysis of PDEs · Mathematics 2018-07-20 Martin Bauer , Sarang Joshi , Klas Modin

Probabilistic graphical models are powerful tools which allow us to formalise our knowledge about the world and reason about its inherent uncertainty. There exist a considerable number of methods for performing inference in probabilistic…

Artificial Intelligence · Computer Science 2018-11-13 Robert Walecki , Albert Buchard , Kostis Gourgoulias , Chris Hart , Maria Lomeli , A. K. W. Navarro , Max Zwiessele , Yura Perov , Saurabh Johri

Controlled generation with pre-trained Diffusion and Flow Matching models has vast applications. One strategy for guiding ODE-based generative models is through optimizing a target loss $R(x_1)$ while staying close to the prior…

Machine Learning · Computer Science 2025-03-11 Luran Wang , Chaoran Cheng , Yizhen Liao , Yanru Qu , Ge Liu

Learning-based models for fluid dynamics often operate in unconstrained function spaces, leading to physically inadmissible, unstable simulations. While penalty-based methods offer soft regularization, they provide no structural guarantees,…

Machine Learning · Computer Science 2026-03-26 Xigui Li , Hongwei Zhang , Ruoxi Jiang , Deshu Chen , Chensen Lin , Limei Han , Yuan Qi , Xin Guo , Yuan Cheng

For a unimodular random graph $(G,\rho)$, we consider deformations of its intrinsic path metric by a (random) weighting of its vertices. This leads to the notion of the conformal growth exponent of $(G,\rho)$, which is the best asymptotic…

Probability · Mathematics 2020-06-02 James R. Lee

Autoregressive generative PDE solvers can be accurate one step ahead yet drift over long rollouts, especially in coarse-to-fine regimes where each step must regenerate unresolved fine scales. This is the regime of diffusion and…

Machine Learning · Computer Science 2026-02-09 Victor Armegioiu

We prove almost sure convergence of the maximum degree in an evolving graph model combining a growing number of local choices with sublinear preferential attachment. At each step in the growth of the graph, a new vertex is introduced. Then…

Probability · Mathematics 2019-11-19 Yury Malyshkin

We present a proof of the almost sure existence, uniqueness and coalescence of directed semi-infinite geodesics in planar growth models that is based on properties of an increment-stationary version of the growth process. The argument is…

Probability · Mathematics 2019-07-16 Timo Seppäläinen

In this paper, we extend the concept of generalized entropy to uniform spaces, allowing computations beyond metrizable settings. We apply this to parabolic dynamics - systems with a unique fixed point uniformly attracting all compact…

Dynamical Systems · Mathematics 2025-07-02 Frederico A. C. L. Marinho , Hellen de Paula , Lucas H. R. de Souza

Stochastic interface dynamics serve as mathematical models for diverse time-dependent physical phenomena: the evolution of boundaries between thermodynamic phases, crystal growth, random deposition... Interesting limits arise at large…

Probability · Mathematics 2019-03-22 F. L. Toninelli

We develop a geometric convergence theory for neural-network optimization within the minimizing movement scheme (MMS) framework. Reformulating each neural MMS step as a minimization over the set of increments in a Hilbert space, we show…

Optimization and Control · Mathematics 2026-05-28 Shixin Zheng , Yiwei Wang , Haizhao Yang

Likelihood-based deep generative models have been widely investigated for Image Anomaly Detection (IAD), particularly Normalizing Flows, yet their strict architectural invertibility needs often constrain scalability, particularly in…

Computer Vision and Pattern Recognition · Computer Science 2026-04-15 Liangwei Li , Lin Liu , Hanzhe Liang , Juanxiu Liu , Jing Zhang , Ruqian Hao , Xiaohui Du , Yong Liu , Pan Li

In the quest to build generative surrogate models as computationally efficient alternatives to rule-based simulations, the quality of the generated samples remains a crucial frontier. So far, normalizing flows have been among the models…

Instrumentation and Detectors · Physics 2024-09-05 Thorsten Buss , Frank Gaede , Gregor Kasieczka , Claudius Krause , David Shih