English
Related papers

Related papers: Strong Converses Are Just Edge Removal Properties

200 papers

Deep neural networks are representation learning techniques. During training, a deep net is capable of generating a descriptive language of unprecedented size and detail in machine learning. Extracting the descriptive language coded within…

Neural and Evolutionary Computing · Computer Science 2018-01-30 Dario Garcia-Gasulla , Ferran Parés , Armand Vilalta , Jonatan Moreno , Eduard Ayguadé , Jesús Labarta , Ulises Cortés , Toyotaro Suzumura

Predictive coding (PC) is an energy-based learning algorithm that performs iterative inference over network activities before updating weights. Recent work suggests that PC can converge in fewer learning steps than backpropagation thanks to…

Machine Learning · Computer Science 2024-11-12 Francesco Innocenti , El Mehdi Achour , Ryan Singh , Christopher L. Buckley

In many cases of attacks or failures, memory effects play a significant role. Therefore, we present a model that not only considers the dependencies between nodes but also incorporates the memory effects of attacks. Our research…

Physics and Society · Physics 2023-06-21 Yanpeng Zhu , Lei Chen , Fanyuan Meng , Chun-Xiao Jia , Run-Ran Liu

Important insights towards the explainability of neural networks reside in the characteristics of their decision boundaries. In this work, we borrow tools from the field of adversarial robustness, and propose a new perspective that relates…

Machine Learning · Computer Science 2020-10-16 Guillermo Ortiz-Jimenez , Apostolos Modas , Seyed-Mohsen Moosavi-Dezfooli , Pascal Frossard

Nodal superconductors without inversion symmetry exhibit nontrivial topological properties, manifested by topologically protected flat-band edge states. Here we study the effects of breaking translational symmetry, crucial to the definition…

Superconductivity · Physics 2014-02-07 Raquel Queiroz , Andreas P. Schnyder

Better understanding our ability to control an interconnected system of entities has been one of the central challenges in network science. The theories of node and edge controllability have been the main methodologies suggested to find the…

Systems and Control · Electrical Eng. & Systems 2021-05-11 Milan van den Heuvel , Jannes Nys

We consider the problem of covert communication with random slot selection over binary-input Discrete Memoryless Channels and Additive White Gaussian Noise channels, in which a transmitter attempts to reliably communicate with a legitimate…

Information Theory · Computer Science 2025-07-21 Shi-Yuan Wang , Keerthi S. K. Arumugam , Matthieu R. Bloch

We investigate the robustness of random networks reinforced by adding hidden edges against targeted attacks. This study focuses on two types of reinforcement: uniform reinforcement, where edges are randomly added to all nodes, and selective…

Physics and Society · Physics 2024-07-30 Tomoyo Kawasumi , Takehisa Hasegawa

In this paper, we study the crucial elements of complex networks, namely nodes, and edges and their properties such as their community structure, which play an important role in dictating the robustness of the network towards structural…

Social and Information Networks · Computer Science 2021-02-04 V. Parimi , A. Pal , S. Ruj , P. Kumaraguru , T. Chakraborty

In many real, directed networks, the strongly connected component of nodes which are mutually reachable is very small. This does not fit with current theory, based on random graphs, according to which strong connectivity depends on mean…

Disordered Systems and Neural Networks · Physics 2023-04-12 Niall Rodgers , Peter Tino , Samuel Johnson

Social networks transmitting covert or sensitive information cannot use all ties for this purpose. Rather, they can only use a subset of ties that are strong enough to be ``trusted''. In this paper we consider transitivity as evidence of…

Statistical Mechanics · Physics 2015-06-25 Xiaolin Shi , Lada A. Adamic , Martin J. Strauss

Edge expansion is a parameter indicating how well-connected a graph is. It is useful for designing robust networks, analysing random walks or information flow through a network and is an important notion in theoretical computer science.…

Probability · Mathematics 2026-01-12 Colin McDiarmid , Katarzyna Rybarczyk , Fiona Skerman , Małgorzata Sulkowska

Along with the rapid development of deep learning in practice, the theoretical explanations for its success become urgent. Generalization and expressivity are two widely used measurements to quantify theoretical behaviors of deep learning.…

Machine Learning · Computer Science 2018-03-26 Shao-Bo Lin

Previous studies on the invulnerability of scale-free networks under edge attacks supported the conclusion that scale-free networks would be fragile under selective attacks. However, these studies are based on qualitative methods with…

Social and Information Networks · Computer Science 2012-11-15 Bojin Zheng , Hongrun Wu , Wenhua Du , Wanneng Shu , Jun Qin

Quantum privacy amplification is a central task in quantum cryptography. Given shared randomness, which is initially correlated with a quantum system held by an eavesdropper, the goal is to extract uniform randomness which is decoupled from…

Quantum Physics · Physics 2022-02-23 Robert Salzmann , Nilanjana Datta

This paper investigates the robustness of strong structural controllability for linear time-invariant and linear time-varying directed networks with respect to structural perturbations, including edge deletions and additions. In this…

Dynamical Systems · Mathematics 2020-05-26 Shima Sadat Mousavi , Mohammad Haeri , Mehran Mesbahi

Classical information theory typically assumes reliable receiver-side processing. We study remote inference when communication is noisy and the receiver itself is built from unreliable components under a finite redundancy budget. Under a…

Information Theory · Computer Science 2026-04-22 Zhenyu Liu , Yi Ma , Rahim Tafazolli

Edge machine learning can deliver low-latency and private artificial intelligent (AI) services for mobile devices by leveraging computation and storage resources at the network edge. This paper presents an energy-efficient edge processing…

Information Theory · Computer Science 2020-03-03 Kai Yang , Yuanming Shi , Wei Yu , Zhi Ding

We develop upper bounds on code size for an independent and identically distributed deletion and insertion channels for a given code length and target frame error probability. The bounds are obtained as a variation of a general converse…

Information Theory · Computer Science 2026-04-14 Ruslan Morozov , Tolga Mete Duman

Convex splitting is a powerful technique in quantum information theory used in proving the achievability of numerous information-processing protocols such as quantum state redistribution and quantum network channel coding. In this work, we…

Quantum Physics · Physics 2023-05-05 Hao-Chung Cheng , Li Gao