Fundamental connections between utility theories of wealth and information theory

• URL: http://arxiv.org/abs/2306.07975v1
• Date: Mon, 22 May 2023 09:46:08 GMT
• Title: Fundamental connections between utility theories of wealth and information theory
• Authors: Andres F. Ducuara, Paul Skrzypczyk
• Abstract summary: We establish fundamental connections between utility theories of wealth from the economic sciences and information-theoretic quantities. We introduce new conditional R'enyi divergences, and explore some of their properties.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: We establish fundamental connections between utility theories of wealth from the economic sciences and information-theoretic quantities. In particular, we introduce operational tasks based on betting where both gambler and bookmaker have access to side information, or betting tasks with double side information for short. In order to characterise these operational tasks we introduce new conditional R\'enyi divergences, and explore some of their properties. Furthermore, we introduce an utility theory of wealth ratios, and operationally interpret there the two-parameter $(q,r)$ generalised mutual information measure recently introduced by V. M. Ili\'c and I. V. Djordjevi\'c; it quantifies the advantage provided by side information in betting tasks for utility theories of wealth ratios. Moreover, we show that the Ili\'c-Djordjevi\'c conditional entropy satisfies a type of generalised chain rule, which generalises that of Arimoto-R\'enyi. Finally, we address the implications of these results on the quantum resource theories of informative measurements and non-constant channels. Altogether, these results further help strengthening the bridge between the theory of expected utility from the economic sciences and Shannon's theory of information.

Related papers

• A resource theory of gambling [0.509780930114934]
  We recast the Kelly criterion for betting as a resource theory of adversarial information.<n>We compute the optimal strategy which maximises the probability of successfully reaching the target.<n>We generalize this framework to a distributed side-information game.
  arXiv  Detail & Related papers  (2025-10-09T16:37:27Z)
• Relative Quantum Resource Theory and Operational Applications in Subchannel Discrimination [5.5637520917012315]
  A central problem in quantum resource theory is to give operational meaning to quantum resources that can provide clear advantages in certain physical tasks. We propose to extend this basic principle by defining the relative superiority of resources over a specific convex set of resource states. We also offer a new framework for defining the deficiency of a given state in physical tasks compared to the set of maximum resource states.
  arXiv  Detail & Related papers  (2024-12-26T01:21:41Z)
• Mutual Information Multinomial Estimation [53.58005108981247]
  Estimating mutual information (MI) is a fundamental yet challenging task in data science and machine learning. Our main discovery is that a preliminary estimate of the data distribution can dramatically help estimate. Experiments on diverse tasks including non-Gaussian synthetic problems with known ground-truth and real-world applications demonstrate the advantages of our method.
  arXiv  Detail & Related papers  (2024-08-18T06:27:30Z)
• Disentangled Representation Learning with Transmitted Information Bottleneck [57.22757813140418]
  We present textbfDisTIB (textbfTransmitted textbfInformation textbfBottleneck for textbfDisd representation learning), a novel objective that navigates the balance between information compression and preservation.
  arXiv  Detail & Related papers  (2023-11-03T03:18:40Z)
• On the Joint Interaction of Models, Data, and Features [82.60073661644435]
  We introduce a new tool, the interaction tensor, for empirically analyzing the interaction between data and model through features. Based on these observations, we propose a conceptual framework for feature learning. Under this framework, the expected accuracy for a single hypothesis and agreement for a pair of hypotheses can both be derived in closed-form.
  arXiv  Detail & Related papers  (2023-06-07T21:35:26Z)
• Resource theory of dephasing estimation in multiqubit systems [0.0]
  We present a resource theory to investigate the power of a multqubit system as a probe in the task of dephasing estimation. Our results provide new insights into quantum parameter estimation by the resource-theoretic approach.
  arXiv  Detail & Related papers  (2023-04-28T03:44:16Z)
• Investigating the Global Properties of a Resource Theory of Contextuality [0.0]
  We will investigate some properties of a resource theory for quantum contextuality. This characteristic ensures the impossibility of interpreting the results of quantum measurements as revealing properties that are independent of the set of measurements being made. We will use the so called cost and yield monotones, extending the results of reference Quantum 4, 280 ( 2020) to general contextuality scenarios.
  arXiv  Detail & Related papers  (2022-10-07T00:33:49Z)
• Variational Distillation for Multi-View Learning [104.17551354374821]
  We design several variational information bottlenecks to exploit two key characteristics for multi-view representation learning. Under rigorously theoretical guarantee, our approach enables IB to grasp the intrinsic correlation between observations and semantic labels.
  arXiv  Detail & Related papers  (2022-06-20T03:09:46Z)
• Knowledge is reward: Learning optimal exploration by predictive reward cashing [5.279475826661643]
  We exploit the inherent mathematical structure of Bayes-adaptive problems in order to dramatically simplify the problem. The key to this simplification comes from the novel concept of cross-value. This results in a new denser reward structure that "cashes in" all future rewards that can be predicted from the current information state.
  arXiv  Detail & Related papers  (2021-09-17T12:52:24Z)
• What Data Augmentation Do We Need for Deep-Learning-Based Finance? [2.470815298095903]
  We focus on developing a theoretical framework for understanding the use of data augmentation for deep-learning-based approaches to quantitative finance. The proposed theory clarifies the role and necessity of data augmentation for finance; moreover, our theory motivates a simple algorithm of injecting a random noise of strength. This algorithm is shown to work well in practice.
  arXiv  Detail & Related papers  (2021-06-08T05:26:58Z)
• RelWalk A Latent Variable Model Approach to Knowledge Graph Embedding [50.010601631982425]
  This paper extends the random walk model (Arora et al., 2016a) of word embeddings to Knowledge Graph Embeddings (KGEs) We derive a scoring function that evaluates the strength of a relation R between two entities h (head) and t (tail) We propose a learning objective motivated by the theoretical analysis to learn KGEs from a given knowledge graph.
  arXiv  Detail & Related papers  (2021-01-25T13:31:29Z)
• Fundamental Limits and Tradeoffs in Invariant Representation Learning [99.2368462915979]
  Many machine learning applications involve learning representations that achieve two competing goals. Minimax game-theoretic formulation represents a fundamental tradeoff between accuracy and invariance. We provide an information-theoretic analysis of this general and important problem under both classification and regression settings.
  arXiv  Detail & Related papers  (2020-12-19T15:24:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.