English
Related papers

Related papers: AI Uncertainty Based on Rademacher Complexity and …

200 papers

We present fundamental limits on the reliable classification of linear and affine subspaces from noisy, linear features. Drawing an analogy between discrimination among subspaces and communication over vector wireless channels, we propose…

Information Theory · Computer Science 2014-12-12 Matthew Nokleby , Miguel Rodrigues , Robert Calderbank

Accurate fading characterization and channel capacity determination are of paramount importance in both conventional and emerging communication systems. The present work addresses the nonlinearity of the propagation medium and its effects…

Information Theory · Computer Science 2016-12-30 Paschalis C. Sofotasios , Sami Muhaidat , Mikko Valkama , Mounir Ghogho , George K. Karagiannidis

Assembly Theory (AT) and its central measure, the assembly index (Ai), represent an invaluable opportunity to address some of the most persistent and widespread conflations and misconceptions about computability and complexity theory in…

The generalization of Shannon's theory to include messages with given autocorrelations is presented. The analytical calculation of the channel capacity is based on the transfer matrix method of the effective 1D Hamiltonian. This bridge…

Statistical Mechanics · Physics 2007-05-23 Ido Kanter , Hanan Rosemarin

Let $W$ be a binary-input memoryless symmetric (BMS) channel with Shannon capacity $I(W)$ and fix any $\alpha > 0$. We construct, for any sufficiently small $\delta > 0$, binary linear codes of block length $O(1/\delta^{2+\alpha})$ and rate…

Information Theory · Computer Science 2022-01-25 Venkatesan Guruswami , Andrii Riazanov , Min Ye

The asymptotic rates of information-theoretic protocols - including error exponents, compression rates, and channel capacities - are traditionally defined under the idealised assumption that the underlying resource (state or channel) is…

Quantum Physics · Physics 2026-05-19 Filippo Girardi , Nilanjana Datta , Giacomo De Palma , Ludovico Lami

Tremendous efforts have been put into evaluating the inclusivity and effectiveness of AI systems across cultures. However, the cultural capabilities considered in much of the literature remain vaguely defined, are referred to using…

Computation and Language · Computer Science 2026-05-18 Isar Nejadgholi , Masoud Kianpour , Krishnapriya Vishnubhotla , Maryam Molamohamadi

AI has been dealing with uncertainty to have highly accurate results. This becomes even worse with reasonably small data sets or a variation in the data sets. This has far-reaching effects on decision-making, forecasting and learning…

Artificial Intelligence · Computer Science 2024-08-05 Keivan Shariatmadar

Quantifying uncertainty in a model's predictions is important as it enables the safety of an AI system to be increased by acting on the model's output in an informed manner. This is crucial for applications where the cost of an error is…

Computer Vision and Pattern Recognition · Computer Science 2021-05-31 Aria Khoshsirat

This paper considers an information bottleneck problem with the objective of obtaining a most informative representation of a hidden feature subject to a R\'enyi entropy complexity constraint. The optimal bottleneck trade-off between…

Information Theory · Computer Science 2021-02-01 Jian-Jia Weng , Fady Alajaji , Tamás Linder

A group of transition probability functions form a Shannon's channel whereas a group of truth functions form a semantic channel. By the third kind of Bayes' theorem, we can directly convert a Shannon's channel into an optimized semantic…

Machine Learning · Computer Science 2018-03-28 Chenguang Lu

The ability to acknowledge the inevitable uncertainty in their knowledge and reasoning is a prerequisite for AI systems to be truly truthful and reliable. In this paper, we present a taxonomy of uncertainty specific to vision-language AI…

Artificial Intelligence · Computer Science 2024-07-03 Khyathi Raghavi Chandu , Linjie Li , Anas Awadalla , Ximing Lu , Jae Sung Park , Jack Hessel , Lijuan Wang , Yejin Choi

If a sender and a receiver lack precise knowledge about the communication line that connects them, designing a scheme to reliably transmit information becomes more challenging. This has been studied in classical and quantum information…

Quantum Physics · Physics 2024-08-27 Paula Belzig

Shannon's Capacity Theorem is the main concept behind the Theory of Communication. It says that if the amount of information contained in a signal is smaller than the channel capacity of a physical media of communication, it can be…

Chaotic Dynamics · Physics 2009-11-13 M. S. Baptista , J. Kurths

Most of statistics and AI draw insights through modelling discord or variance between sources of information (i.e., inter-source uncertainty). Increasingly, however, research is focusing upon uncertainty arising at the level of individual…

Machine Learning · Computer Science 2023-03-01 Shaily Kabir , Christian Wagner , Zack Ellerby

This paper studies the Shannon regime for the random displacement of stationary point processes. Let each point of some initial stationary point process in $\R^n$ give rise to one daughter point, the location of which is obtained by adding…

Information Theory · Computer Science 2015-03-17 Venkat Anantharam , Francois Baccelli

We study the excess capacity of deep networks in the context of supervised classification. That is, given a capacity measure of the underlying hypothesis class - in our case, empirical Rademacher complexity - to what extent can we (a…

Machine Learning · Computer Science 2023-01-20 Florian Graf , Sebastian Zeng , Bastian Rieck , Marc Niethammer , Roland Kwitt

We study the channel coding problem when errors and uncertainty occur in the encoding process. For simplicity we assume the channel between the encoder and the decoder is perfect. Focusing on linear block codes, we model the encoding…

Information Theory · Computer Science 2013-05-17 Jad Hachem , I-Hsiang Wang , Christina Fragouli , Suhas Diggavi

Explainable AI (XAI) aims to provide interpretations for predictions made by learning machines, such as deep neural networks, in order to make the machines more transparent for the user and furthermore trustworthy also for applications in…

Machine Learning · Computer Science 2020-06-17 Kirill Bykov , Marina M. -C. Höhne , Klaus-Robert Müller , Shinichi Nakajima , Marius Kloft

Researchers in explainable artificial intelligence have developed numerous methods for helping users understand the predictions of complex supervised learning models. By contrast, explaining the $\textit{uncertainty}$ of model outputs has…

Machine Learning · Statistics 2023-11-01 David S. Watson , Joshua O'Hara , Niek Tax , Richard Mudd , Ido Guy