English
Related papers

Related papers: Deformed Statistics Formulation of the Information…

200 papers

Normalization is fundamental to deep learning, but existing approaches such as BatchNorm, LayerNorm, and RMSNorm are variance-centric by enforcing zero mean and unit variance, stabilizing training without controlling how representations…

Machine Learning · Computer Science 2026-01-30 Xiandong Zou , Jia Li , Xiaotong Yuan , Pan Zhou

The equipartition theorem states that inverse temperature equals the log-derivative of the density of states. This relation can be generalized by introducing a proportionality factor involving an increasing positive function phi(x). It is…

Statistical Mechanics · Physics 2009-11-10 Jan Naudts

Deep learning has become the most powerful machine learning tool in the last decade. However, how to efficiently train deep neural networks remains to be thoroughly solved. The widely used minibatch stochastic gradient descent (SGD) still…

Machine Learning · Computer Science 2021-05-18 Xinyu Peng , Jiawei Zhang , Fei-Yue Wang , Li Li

Tsallis' non-extensive entropy is extended to incorporate the dependence on affinities between the microstates of a system. At the core of our construction of the extended entropy ($\mathcal{H}$) is the concept of the effective number of…

Quantitative Methods · Quantitative Biology 2022-02-08 Keisuke Okamura

An unified thermodynamical framework based in the use of a generalized Massieu-Planck thermodynamic potential is proposed and a new formulation of Boltzmann-Gibbs Statistical Mechanics is established. Under this philosophy a generalization…

Mathematical Physics · Physics 2007-05-23 V. Garcia-Morales , J. Pellicer

Graph data, essential in fields like knowledge representation and social networks, often involves large networks with many nodes and edges. Transmitting these graphs can be highly inefficient due to their size and redundancy for specific…

Machine Learning · Computer Science 2024-09-05 Shujing Li , Yanhu Wang , Shuaishuai Guo , Chenyuan Feng

Tsallis and R\'{e}nyi entropies, which are monotone transformations of each other, are deformations of the celebrated Shannon entropy. Maximization of these deformed entropies, under suitable constraints, leads to the $q$-exponential family…

Probability · Mathematics 2022-01-14 Ting-Kam Leonard Wong , Jun Zhang

We derive a novel version of information-disturbance theorems for mutually unbiased observables. We show that the information gain by Eve inevitably makes the outcomes by Bob in the conjugate basis not only erroneous but random.

Quantum Physics · Physics 2007-05-23 Takayuki Miyadera , Hideki Imai

Selecting an optimal subset of features or instances under an information theoretic criterion has become an effective preprocessing strategy for reducing data complexity while preserving essential information. This study investigates two…

Optimization and Control · Mathematics 2025-08-25 Taotao He , Jun Luo , Junkai Zhao

We study the informational underpinnings of thermodynamics and statistical mechanics, using an abstract framework, general probabilistic theories, capable of describing arbitrary physical theories. This allows one to abstract the…

Quantum Physics · Physics 2019-01-25 Carlo Maria Scandolo

Statistical inference is considered for variables of interest, called primary variables, when auxiliary variables are observed along with the primary variables. We consider the setting of incomplete data analysis, where some primary…

Methodology · Statistics 2019-03-27 Shinpei Imori , Hidetoshi Shimodaira

We review with a tutorial scope the information theory foundations of quantum statistical physics. Only a small proportion of the variables that characterize a system at the microscopic scale can be controlled, for both practical and…

Statistical Mechanics · Physics 2007-05-23 R. Balian

Contrastive learning is effective for aligning paired views or modalities, but alignment beyond two modalities remains non-trivial and comparatively underexplored. Pairwise CLIP-style losses decompose multi-modal alignment into independent…

Machine Learning · Computer Science 2026-05-29 Tianchao Li , Shujian Yu , Xinrui Zu , Zhaolong Wei , Jeremy Gummeson , Jack C. P. Cheng , Robert Jenssen

This study comes as a timely response to mounting criticism of the information bottleneck (IB) theory, injecting fresh perspectives to rectify misconceptions and reaffirm its validity. Firstly, we introduce an auxiliary function to…

Machine Learning · Computer Science 2023-05-22 Faxian Cao , Yongqiang Cheng , Adil Mehmood Khan , Zhijing Yang

We discuss the generalized von Neumann (Tsallis) entropy and the generalized Fisher information (GFI) in nonextensive quantum systems, by using the interpolation approximation (IA) which has been shown to yield good results for the quantal…

Statistical Mechanics · Physics 2009-09-22 Hideo Hasegawa

In order to improve the teaching of the course of statistical physics in universities, in this article we introduce nonextensive statistics, a new statistical theory about complex systems. We study the two modification coefficients a and b…

General Physics · Physics 2018-09-12 Lining Zheng , Jiulin Du

Based on the form invariance of the structures given by Khinchin's axiomatic foundations of information theory and the pseudoadditivity of the Tsallis entropy indexed by q, the concept of conditional entropy is generalized to the case of…

Quantum Physics · Physics 2009-11-06 Sumiyoshi Abe , A. K. Rajagopal

Learned representations at the level of characters, sub-words, words and sentences, have each contributed to advances in understanding different NLP tasks and linguistic phenomena. However, learning textual embeddings is costly as they are…

Computation and Language · Computer Science 2023-10-27 Melika Behjati , Fabio Fehr , James Henderson

By extracting task-relevant information while maximally compressing the input, the information bottleneck (IB) principle has provided a guideline for learning effective and robust representations of the target inference. However, extending…

Information Theory · Computer Science 2025-01-22 Yuhan Wang , Youlong Wu , Shuai Ma , Ying-Jun Angela Zhang

Based on the notion of information bottleneck (IB), we formulate a quantization problem called "IB quantization". We show that IB quantization is equivalent to learning based on the IB principle. Under this equivalence, the standard neural…

Machine Learning · Computer Science 2019-02-13 Hongyu Guo , Yongyi Mao , Ali Al-Bashabsheh , Richong Zhang