中文
相关论文

相关论文: The information bottleneck method

200 篇论文

Discovering relevant, but possibly hidden, variables is a key step in constructing useful and predictive theories about the natural world. This brief note explains the connections between three approaches to this problem: the recently…

适应与自组织系统 · 物理学 2022-02-17 Cosma Rohilla Shalizi , James P. Crutchfield

Information bottleneck (IB) is a method for extracting information from one random variable $X$ that is relevant for predicting another random variable $Y$. To do so, IB identifies an intermediate "bottleneck" variable $T$ that has low…

机器学习 · 统计学 2022-11-22 Artemy Kolchinsky , Brendan D. Tracey , Steven Van Kuyk

The information bottleneck (IB) method is a technique for extracting information that is relevant for predicting the target random variable from the source random variable, which is typically implemented by optimizing the IB Lagrangian that…

机器学习 · 计算机科学 2020-12-23 Ziqi Pan , Li Niu , Jianfu Zhang , Liqing Zhang

Numerous deep learning algorithms have been inspired by and understood via the notion of information bottleneck, where unnecessary information is (often implicitly) minimized while task-relevant information is maximized. However, a rigorous…

机器学习 · 计算机科学 2023-05-31 Kenji Kawaguchi , Zhun Deng , Xu Ji , Jiaoyang Huang

Inference capabilities of machine learning (ML) systems skyrocketed in recent years, now playing a pivotal role in various aspect of society. The goal in statistical learning is to use data to obtain simple algorithms for predicting a…

机器学习 · 计算机科学 2020-05-04 Ziv Goldfeld , Yury Polyanskiy

The information bottleneck (IB) method seeks a compressed representation of data that preserves information relevant to a target variable for prediction while discarding irrelevant information from the original data. In its classical…

信息论 · 计算机科学 2026-02-23 Akira Kamatsuka , Takahiro Yoshida

In this work, we generalize the information bottleneck (IB) approach to the multi-view learning context. The exponentially growing complexity of the optimal representation motivates the development of two novel formulations with more…

信息论 · 计算机科学 2022-09-20 Teng-Hui Huang , Aly El Gamal , Hesham El Gamal

We study a distributed learning problem in which Alice sends a compressed distillation of a set of training data to Bob, who uses the distilled version to best solve an associated learning problem. We formalize this as a rate-distortion…

信息论 · 计算机科学 2018-10-30 Parinaz Farajiparvar , Ahmad Beirami , Matthew Nokleby

We formulate and analyze the compound information bottleneck programming. In this problem, a Markov chain $ \mathsf{X} \rightarrow \mathsf{Y} \rightarrow \mathsf{Z} $ is assumed with fixed marginal distributions $\mathsf{P}_{\mathsf{X}}$…

信息论 · 计算机科学 2022-05-11 Michael Dikshtein , Nir Weinberger , Shlomo Shamai

Interpretability is a pressing issue for machine learning. Common approaches to interpretable machine learning constrain interactions between features of the input, rendering the effects of those features on a model's output comprehensible…

机器学习 · 计算机科学 2023-05-11 Kieran A. Murphy , Dani S. Bassett

The presence of symmetries imposes a stringent set of constraints on a system. This constrained structure allows intelligent agents interacting with such a system to drastically improve the efficiency of learning and generalization, through…

信息论 · 计算机科学 2024-10-03 Hippolyte Charvin , Nicola Catenacci Volpi , Daniel Polani

The muti-layer information bottleneck (IB) problem, where information is propagated (or successively refined) from layer to layer, is considered. Based on information forwarded by the preceding layer, each stage of the network is required…

机器学习 · 统计学 2017-11-15 Qianqian Yang , Pablo Piantanida , Deniz Gündüz

Encoding only the task-related information from the raw data, \ie, disentangled representation learning, can greatly contribute to the robustness and generalizability of models. Although significant advances have been made by regularizing…

计算机视觉与模式识别 · 计算机科学 2024-08-15 Zhuohang Dang , Minnan Luo , Chengyou Jia , Guang Dai , Jihong Wang , Xiaojun Chang , Jingdong Wang

In this paper, we propose a unified information theoretic framework for learning-motivated methods aimed at odometry estimation, a crucial component of many robotics and vision tasks such as navigation and virtual reality where relative…

计算机视觉与模式识别 · 计算机科学 2022-08-16 Sen Zhang , Jing Zhang , Dacheng Tao

The Information Bottleneck (IB) is a method of lossy compression of relevant information. Its rate-distortion (RD) curve describes the fundamental tradeoff between input compression and the preservation of relevant information embedded in…

信息论 · 计算机科学 2023-07-27 Shlomi Agmon

The existence of external (``side'') semantic knowledge has been shown to result in more expressive computational event models. To enable the use of side information that may be noisy or missing, we propose a semi-supervised information…

机器学习 · 计算机科学 2023-02-15 Mehdi Rezaee , Francis Ferraro

Information bottleneck is an information-theoretic principle of representation learning that aims to learn a maximally compressed representation that preserves as much information about labels as possible. Under this principle, two…

信息论 · 计算机科学 2023-11-08 Yuyan Ni , Yanyan Lan , Ao Liu , Zhiming Ma

This work develops problem statements related to encoders and autoencoders with the goal of elucidating variational formulations and establishing clear connections to information-theoretic concepts. Specifically, four problems with varying…

信息论 · 计算机科学 2021-07-15 Karthik Duraisamy

The Information Bottleneck (IB) method is an information theoretical framework to design a parsimonious and tunable feature-extraction mechanism, such that the extracted features are maximally relevant to a specific learning or inference…

信号处理 · 电气工程与系统科学 2024-04-17 Francesco Binucci , Paolo Banelli , Paolo Di Lorenzo , Sergio Barbarossa

Deterministic chaos permits a precise notion of a "perfect measurement" as one that, when obtained repeatedly, captures all of the information created by the system's evolution with minimal redundancy. Finding an optimal measurement is…

机器学习 · 计算机科学 2024-03-21 Kieran A. Murphy , Dani S. Bassett