English
Related papers

Related papers: Anomalies in Neural Network Field Theory

200 papers

The Wess-Zumino consistency condition allows more exotic forms of anomalies than those we usually encounter. For example in two-dimensional conformal field theories in the curved background with space-time dependent coupling constant…

High Energy Physics - Theory · Physics 2018-10-10 Yu Nakayama

Obtaining system parameters and reconstructing the full flow state from limited velocity observations using conventional fluid dynamics solvers can be prohibitively expensive. Here we employ machine learning algorithms to overcome the…

Fluid Dynamics · Physics 2024-10-17 Vladimir Parfenyev , Mark Blumenau , Ilia Nikitin

In this thesis, we report on results in non-anticommutative field theory and twistor string theory, trying to be self-contained. We first review the construction of non-anticommutative N=4 super Yang-Mills theory and discuss a…

High Energy Physics - Theory · Physics 2007-05-23 Christian Saemann

Mean field theory has been successfully used to analyze deep neural networks (DNN) in the infinite size limit. Given the finite size of realistic DNN, we utilize the large deviation theory and path integral analysis to study the deviation…

Disordered Systems and Neural Networks · Physics 2020-02-21 Bo Li , David Saad

Symmetries (transformations by group actions) are present in many datasets, and leveraging them holds considerable promise for improving predictions in machine learning. In this work, we aim to understand when and how deep networks -- with…

Machine Learning · Computer Science 2025-06-27 Andrea Perin , Stephane Deny

Deep neural networks generalize well despite being heavily overparameterized, in apparent contradiction with classical learning theory based on uniform convergence over fixed hypothesis spaces. Uniform bounds over the entire parameter space…

Machine Learning · Statistics 2026-05-15 Hubert Leroux , Jean Marcus , Julien Roger

We propose that simple neural networks (NNs) trained on crossing symmetry can reconstruct conformal correlators restricted to a line to remarkable accuracy. The input is minimal: an external scaling dimension, a spectral gap, and the value…

High Energy Physics - Theory · Physics 2026-04-22 Kausik Ghosh , Sidhaarth Kumar , Vasilis Niarchos , Andreas Stergiou

Neural networks (NNs) are inherently multidimensional classifiers that learn complex, non-linear relationships among input observables. While their flexibility enables unprecedented performance in high-energy physics (HEP) analyses, it also…

The loop structure of two point Green's functions is investigated in the Wess-Zumino model in the formalism where the auxiliary fields are integrated out. In the usual frame of perturbation theory the deviation from the non-renormalization…

High Energy Physics - Theory · Physics 2007-05-23 V. Sauli

We derive maps relating currents and their divergences in non-abelian U(N) noncommutative gauge theory with the corresponding expressions in the ordinary (commutative) description. For the U(1) theory, in the slowly-varying-field…

High Energy Physics - Theory · Physics 2007-05-23 Rabin Banerjee , Kuldeep Kumar

Large-scale computations of fission properties are an important ingredient for nuclear reaction network calculations simulating rapid neutron-capture process (the r process) nucleosynthesis. Due to the large number of fissioning nuclei…

Nuclear Theory · Physics 2024-04-04 Daniel Lay , Eric Flynn , Samuel A. Giuliani , Witold Nazarewicz , Leó Neufcourt

Deep Neural Networks (DNNs) can be represented as graphs whose links and vertices iteratively process data and solve tasks sub-optimally. Complex Network Theory (CNT), merging statistical physics with graph theory, provides a method for…

Machine Learning · Computer Science 2024-04-19 Emanuele La Malfa , Gabriele La Malfa , Giuseppe Nicosia , Vito Latora

A detailed analysis of anomalous U(1)'s and their effective couplings is performed both in field theory and string theory. It is motivated by the possible relevance of such couplings in particle physics, as well as a potential signal…

High Energy Physics - Theory · Physics 2009-11-11 P. Anastasopoulos , M. Bianchi , E. Dudas , E. Kiritsis

We investigate critical $N$-component scalar field theories and the spontaneous breaking of scale invariance in three dimensions using functional renormalisation. Global and local renormalisation group flows are solved analytically in the…

High Energy Physics - Theory · Physics 2017-07-05 Edouard Marchais , Peter Mati , Daniel F Litim

We study one-dimensional disordered systems with average non-invertible symmetries, where quenched disorder may locally break part of the symmetry while preserving it upon disorder averaging. A canonical example is the random…

Disordered Systems and Neural Networks · Physics 2026-02-11 Yabo Li , Meng Cheng , Ruochen Ma

We derive a dual theory of the four-dimensional anomalous U(1) gauge theory with a Wess--Zumino (WZ) term and with a St\"uckelberg type mass term by means of a duality transformation at each of the classical and quantum levels. It is shown…

High Energy Physics - Theory · Physics 2009-10-31 Shinichi Deguchi , Tomoaki Mukai , Tadahito Nakajima

Deep Neural Networks (DNNs) are powerful algorithms that have been proven capable of extracting non-Gaussian information from weak lensing (WL) data sets. Understanding which features in the data determine the output of these nested,…

Cosmology and Nongalactic Astrophysics · Physics 2021-04-14 José Manuel Zorrilla Matilla , Manasi Sharma , Daniel Hsu , Zoltán Haiman

Deep neural networks (DNNs) achieve remarkable performance on a wide range of tasks, yet their mathematical analysis remains fragmented: stability and generalization are typically studied in disparate frameworks and on a case-by-case basis.…

Machine Learning · Statistics 2026-01-29 Jonathan Vacher

In N=1 supersymmetric U(N) gauge theory with adjoint matter $\Phi$ and polynomial tree-level superpotential $W(\Phi)$, the massless fluctuations about each quantum vacuum are generically described by $U(1)^n$ gauge theory for some n.…

High Energy Physics - Theory · Physics 2009-11-10 David Shih

Artificial Neural Networks (ANNs) have been successfully used in various nuclear engineering applications, such as predicting reactor physics parameters within reasonable time and with a high level of accuracy. Despite this success, they…

Machine Learning · Statistics 2023-03-24 Lesego E. Moloko , Pavel M. Bokov , Xu Wu , Kostadin N. Ivanov
‹ Prev 1 8 9 10 Next ›