English
Related papers

Related papers: AdS/CFT as a deep Boltzmann machine

200 papers

We give an interpretation of holography in the form of the AdS/CFT correspondence in terms of homotopy algebras. A field theory such as a bulk gravity theory can be viewed as a homotopy Lie or $L_{\infty}$ algebra. We extend this dictionary…

High Energy Physics - Theory · Physics 2023-09-08 Christoph Chiaffrino , Talha Ersoy , Olaf Hohm

We present a layered Boltzmann machine (BM) that can better exploit the advantages of a distributed representation. It is widely believed that deep BMs (DBMs) have far greater representational power than its shallow counterpart, restricted…

Neural and Evolutionary Computing · Computer Science 2015-06-23 Taichi Kiwaki

We discuss dilatonic gravity (bulk theory) from the point of view of (generalized) AdS/CFT correspondence. Self-consistent dilatonic background is considered. It may be understood as two boundaries space where AdS boundary appears as…

High Energy Physics - Theory · Physics 2009-09-17 Shin'ichi Nojiri , Sergei D. Odintsov

Restricted Boltzmann machines (RBMs) and their extensions, called 'deep-belief networks', are powerful neural networks that have found applications in the fields of machine learning and artificial intelligence. The standard way to training…

Machine Learning · Computer Science 2018-10-25 Haik Manukian , Fabio L. Traversa , Massimiliano Di Ventra

We propose a new approach for using the AdS/CFT correspondence to study quantum black hole physics. The black holes on a brane in an AdS$_{D+1}$ braneworld that solve the classical bulk equations are interpreted as duals of {\it…

High Energy Physics - Theory · Physics 2010-04-06 Roberto Emparan , Alessandro Fabbri , Nemanja Kaloper

It is a long-standing conjecture that any CFT with a large central charge and a large gap $\Delta_{\text{gap}}$ in the spectrum of higher-spin single-trace operators must be dual to a local effective field theory in AdS. We prove a sharp…

High Energy Physics - Theory · Physics 2021-12-08 Simon Caron-Huot , Dalimil Mazac , Leonardo Rastelli , David Simmons-Duffin

The restricted Boltzmann machine (RBM) is one of the fundamental building blocks of deep learning. RBM finds wide applications in dimensional reduction, feature extraction, and recommender systems via modeling the probability distributions…

Strongly Correlated Electrons · Physics 2018-02-07 Jing Chen , Song Cheng , Haidong Xie , Lei Wang , Tao Xiang

The AdS/CFT correspondence stipulates a duality between conformal field theories and certain theories of quantum gravity in one higher spatial dimension. However, probing this conjecture on contemporary classical or quantum computers is…

Quantum Physics · Physics 2024-01-25 Rahul Sahay , Mikhail D. Lukin , Jordan Cotler

Four-dimensional cosmological models are studied on a boundary of a five-dimensional Anti-de Sitter (AdS_5) black hole with AdS Reissner-Nordstrom and scalar charged Reissner- Nordstrom black hole solutions, where we call the former a…

General Relativity and Quantum Cosmology · Physics 2021-11-17 Sunly Khimphun , Bum-Hoon Lee , Gansukh Tumurtushaa

In this work we expand on the holographic description of CFTs on de Sitter (dS) and anti-de Sitter (AdS) spacetimes and examine how violations of the unitarity bound in the boundary theory are recovered in the bulk physics. To this end we…

High Energy Physics - Theory · Physics 2012-03-21 Tomas Andrade , Christoph F. Uhlemann

We consider the AdS_2/CFT_1 holographic correspondence near the horizon of big four-dimensional black holes preserving four supersymmetries in toroidally compactified Type-II string theory. The boundary partition function of CFT_1 is given…

High Energy Physics - Theory · Physics 2013-02-20 Atish Dabholkar , Joao Gomes , Sameer Murthy

Deep learning methods relying on multi-layered networks have been actively studied in a wide range of fields in recent years, and deep Boltzmann machines(DBMs) is one of them. In this study, a model of DBMs with some properites of weight…

Disordered Systems and Neural Networks · Physics 2022-10-06 Yuma Ichikawa , Koji Hukushima

In this paper, we study a new class of AdS/BCFT setups, where the world-volumes of end-of-the-world branes (EOW branes) are given by flat spaces, to explore flat space holography from an AdS bulk. We show that they provide gravity duals of…

High Energy Physics - Theory · Physics 2025-09-23 Peng-Xiang Hao , Naoki Ogawa , Tadashi Takayanagi , Takahiro Waki

The 5d dilatonic gravity action with surface counterterms, motivated by the AdS/CFT correspondence and with contributions of brane quantum CFTs is considered with an AdS-like bulk. The role of quantum brane CFT consists in inducing…

General Relativity and Quantum Cosmology · Physics 2007-05-23 K. E. Osetrin

In AdS/CFT, the entanglement wedge EW$(B)$ is the portion of the bulk geometry that can be reconstructed from a boundary region $B$; in other words, EW$(B)$ is the hologram of $B$. We extend this notion to arbitrary spacetimes. Given any…

High Energy Physics - Theory · Physics 2023-09-07 Raphael Bousso , Geoff Penington

In the AdS/CFT correspondence, the causal structure of the bulk AdS spacetime is tied to entanglement in the dual CFT. This relationship is captured by the connected wedge theorem, which states that a bulk scattering process implies the…

High Energy Physics - Theory · Physics 2025-07-22 Jacqueline Caminiti , Batia Friedman-Shaw , Alex May , Robert C. Myers , Olga Papadoulaki

We study the dimensionality manifested in the AdS/CFT correspondence. We show that the dimensionality as expressed by the high temperature behavior of a system has a holographic nature also at the quantum level. The emergence of the AdS…

High Energy Physics - Theory · Physics 2008-11-26 J. L. F. Barbon , E. Rabinovici

The cosmological horizon has an associated entropy suggesting that it might encode a quantum mechanical system on its surface. This has motivated extending the principles of the anti-de Sitter (AdS) space/ conformal field theory (CFT)…

High Energy Physics - Theory · Physics 2024-07-22 S. E. Aguilar-Gutierrez

Estimation of Distribution Algorithms (EDAs) require flexible probability models that can be efficiently learned and sampled. Deep Boltzmann Machines (DBMs) are generative neural networks with these desired properties. We integrate a DBM…

Neural and Evolutionary Computing · Computer Science 2016-08-09 Malte Probst , Franz Rothlauf

Restricted Boltzmann Machines (RBMs) and models derived from them have been successfully used as basic building blocks in deep artificial neural networks for automatic features extraction, unsupervised weights initialization, but also as…

Neural and Evolutionary Computing · Computer Science 2016-07-20 Decebal Constantin Mocanu , Elena Mocanu , Phuong H. Nguyen , Madeleine Gibescu , Antonio Liotta