English
Related papers

Related papers: Invariant Information Bottleneck for Domain Genera…

200 papers

The Information Bottleneck (IB) principle offers an information-theoretic framework for analyzing the training process of deep neural networks (DNNs). Its essence lies in tracking the dynamics of two mutual information (MI) values: between…

Machine Learning · Computer Science 2024-05-10 Ivan Butakov , Alexander Tolmachev , Sofia Malanchuk , Anna Neopryatnaya , Alexey Frolov , Kirill Andreev

In this theory paper, we investigate training deep neural networks (DNNs) for classification via minimizing the information bottleneck (IB) functional. We show that the resulting optimization problem suffers from two severe issues: First,…

Machine Learning · Computer Science 2020-08-10 Rana Ali Amjad , Bernhard C. Geiger

Despite widespread adoption, multimodal large language models (MLLMs) suffer performance degradation when encountering unfamiliar queries under distribution shifts. Existing methods to improve MLLM generalization typically require either…

Artificial Intelligence · Computer Science 2025-10-21 Changdae Oh , Jiatong Li , Shawn Im , Sharon Li

In the context of statistical learning, the Information Bottleneck method seeks a right balance between accuracy and generalization capability through a suitable tradeoff between compression complexity, measured by minimum description…

Information Theory · Computer Science 2021-02-16 Mohammad Mahdi Mahvari , Mari Kobayashi , Abdellatif Zaidi

Multimodal recommender systems (MRS) improve recommendation performance by integrating complementary semantic information from multiple modalities. However, the assumption of complete multimodality rarely holds in practice due to missing…

Information Retrieval · Computer Science 2025-10-16 Huilin Chen , Miaomiao Cai , Fan Liu , Zhiyong Cheng , Richang Hong , Meng Wang

The Information bottleneck (IB) method enables optimizing over the trade-off between compression of data and prediction accuracy of learned representations, and has successfully and robustly been applied to both supervised and unsupervised…

Information Theory · Computer Science 2021-05-25 Teng-Hui Huang , Aly El Gamal

Understanding the source of the superior generalization ability of NNs remains one of the most important problems in ML research. There have been a series of theoretical works trying to derive non-vacuous bounds for NNs. Recently, the…

Machine Learning · Computer Science 2022-03-07 Zifeng Wang , Shao-Lun Huang , Ercan E. Kuruoglu , Jimeng Sun , Xi Chen , Yefeng Zheng

The Symmetric Information Bottleneck (SIB), an extension of the more familiar Information Bottleneck, is a dimensionality reduction technique that simultaneously compresses two random variables to preserve information between their…

Information Theory · Computer Science 2024-02-06 K. Michael Martini , Ilya Nemenman

The Information bottleneck method is an unsupervised non-parametric data organization technique. Given a joint distribution P(A,B), this method constructs a new variable T that extracts partitions, or clusters, over the values of A that are…

Machine Learning · Computer Science 2013-01-14 Nir Friedman , Ori Mosenzon , Noam Slonim , Naftali Tishby

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 learning…

Machine Learning · Computer Science 2026-01-30 Antonio Almudévar , José Miguel Hernández-Lobato , Alfonso Ortega

Achieving health equity in Artificial Intelligence (AI) requires diagnostic models that maintain reliability across diverse populations. However, breast cancer screening systems frequently suffer from domain overfitting, degrading…

Computer Vision and Pattern Recognition · Computer Science 2026-01-27 Hung Q. Vo , Samira Zare , Son T. Ly , Lin Wang , Chika F. Ezeana , Xiaohui Yu , Kelvin K. Wong , Stephen T. C. Wong , Hien V. Nguyen

Learning with hidden variables is a central challenge in probabilistic graphical models that has important implications for many real-life problems. The classical approach is using the Expectation Maximization (EM) algorithm. This…

Machine Learning · Computer Science 2012-12-12 Gal Elidan , Nir Friedman

Information geometry describes a framework where probability densities can be viewed as differential geometry structures. This approach has shown that the geometry in the space of probability distributions that are parameterized by their…

Information Theory · Computer Science 2018-01-16 M. Ashok Kumar , Kumar Vijay Mishra

We show that the Invariant Risk Minimization (IRM) formulation of Arjovsky et al. (2019) can fail to capture "natural" invariances, at least when used in its practical "linear" form, and even on very simple problems which directly follow…

Machine Learning · Statistics 2021-03-02 Pritish Kamath , Akilesh Tangella , Danica J. Sutherland , Nathan Srebro

In the past decade, deep neural networks have seen unparalleled improvements that continue to impact every aspect of today's society. With the development of high performance GPUs and the availability of vast amounts of data, learning…

Machine Learning · Computer Science 2021-05-12 Mohammad Ali Alomrani

This paper offers a new perspective to ease the challenge of domain generalization, which involves maintaining robust results even in unseen environments. Our design focuses on the decision-making process in the final classifier layer.…

Computer Vision and Pattern Recognition · Computer Science 2023-08-23 Liang Chen , Yong Zhang , Yibing Song , Anton van den Hengel , Lingqiao Liu

Domain adaptation aims to leverage the supervision signal of source domain to obtain an accurate model for target domain, where the labels are not available. To leverage and adapt the label information from source domain, most existing…

Machine Learning · Computer Science 2019-11-22 Yuxuan Song , Lantao Yu , Zhangjie Cao , Zhiming Zhou , Jian Shen , Shuo Shao , Weinan Zhang , Yong Yu

Symmetry transformations induce invariances which are frequently described with deep latent variable models. In many complex domains, such as the chemical space, invariances can be observed, yet the corresponding symmetry transformation…

Machine Learning · Computer Science 2020-10-23 Mario Wieser , Sonali Parbhoo , Aleksander Wieczorek , Volker Roth

We tackle a common domain adaptation setting in causal systems. In this setting, the target variable is observed in the source domain but is entirely missing in the target domain. We aim to impute the target variable in the target domain…

Machine Learning · Computer Science 2026-01-09 Mohammad Ali Javidian

The performance of machine learning models can be impacted by changes in data over time. A promising approach to address this challenge is invariant learning, with a particular focus on a method known as invariant risk minimization (IRM).…

Machine Learning · Computer Science 2024-04-09 Wenlu Tang , Zicheng Liu
‹ Prev 1 3 4 5 6 7 10 Next ›