paper-with-me

홈 › Papers

Relevant sparse codes with variational information bottleneck

2016-05-24 · NeurIPS 2016 12 · Matthew Chalk, Olivier Marre, Gasper Tkacik

In many applications, it is desirable to extract only the relevant aspects of data. A principled way to do this is the information bottleneck (IB) method, where one seeks a code that maximizes information about a 'relevance' variable, Y, while constraining the information encoded about the original data, X. Unfortunately however, the IB method is computationally demanding when data are high-dimensional and/or non-gaussian. Here we propose an approximate variational scheme for maximizing a lower bound on the IB objective, analogous to variational EM. Using this method, we derive an IB algorithm to recover features that are both relevant and sparse. Finally, we demonstrate how kernelized versions of the algorithm can be used to address a broad range of problems with non-linear relation between X and Y.

📄 PDF Abstract BibTeX arXiv:1605.07332

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

There Was Never a Bottleneck in Concept Bottleneck Models

2025-06-05 · Antonio Almudévar, José Miguel Hernández-Lobato, Alfonso Ortega

Deep learning representations are often difficult to interpret, which can hinder their deployment in sensitive applications. Concept Bottleneck Models (CBMs) have emerged as a promising approach to mitigate this issue by…

Drop-Bottleneck: Learning Discrete Compressed Representation for Noise-Robust Exploration

2021-03-23 · ICLR 2021 1 · Jaekyeom Kim, Minjung Kim, Dongyeon Woo, Gunhee Kim

We propose a novel information bottleneck (IB) method named Drop-Bottleneck, which discretely drops features that are irrelevant to the target variable. Drop-Bottleneck not only enjoys a simple and tractable compression …

Adversarial RobustnessDimensionality Reduction

Robust Information Bottleneck for Task-Oriented Communication with Digital Modulation

2022-09-21 · Songjie Xie, Shuai Ma, Ming Ding, Yuanming Shi 외

Task-oriented communications, mostly using learning-based joint source-channel coding (JSCC), aim to design a communication-efficient edge inference system by transmitting task-relevant information to the receiver. Howev…

Informativeness

Self-supervised Sequential Information Bottleneck for Robust Exploration in Deep Reinforcement Learning

2022-09-12 · Bang You, Jingming Xie, Youping Chen, Jan Peters 외

Effective exploration is critical for reinforcement learning agents in environments with sparse rewards or high-dimensional state-action spaces. Recent works based on state-visitation counts, curiosity and entropy-maximi…

Deep Reinforcement LearningEfficient Explorationreinforcement-learningReinforcement Learning (RL)+2

Flexible Variational Information Bottleneck: Achieving Diverse Compression with a Single Training

2024-02-02 · Sota Kudo, Naoaki Ono, Shigehiko Kanaya, Ming Huang

Information Bottleneck (IB) is a widely used framework that enables the extraction of information related to a target random variable from a source random variable. In the objective function, IB controls the trade-off be…

Data Compression