English
Related papers

Related papers: Conditional Mutual Information Constrained Deep Le…

200 papers

The Maximum Mutual Information (MMI) criterion is different from the Least Error Rate (LER) criterion. It can reduce failing to report small probability events. This paper introduces the Channels Matching (CM) algorithm for the MMI…

Machine Learning · Computer Science 2019-01-30 Chenguang Lu

It is believed that in knowledge distillation (KD), the role of the teacher is to provide an estimate for the unknown Bayes conditional probability distribution (BCPD) to be used in the student training process. Conventionally, this…

Machine Learning · Computer Science 2024-03-11 Linfeng Ye , Shayan Mohajer Hamidi , Renhao Tan , En-Hui Yang

Deep neural network (DNN) models have demonstrated impressive performance in various domains, yet their application in cognitive neuroscience is limited due to their lack of interpretability. In this study we employ two structurally…

Signal Processing · Electrical Eng. & Systems 2024-09-04 Murat Kucukosmanoglu , Javier O. Garcia , Justin Brooks , Kanika Bansal

Several recent works in communication systems have proposed to leverage the power of neural networks in the design of encoders and decoders. In this approach, these blocks can be tailored to maximize the transmission rate based on…

Information Theory · Computer Science 2020-07-15 Sina Molavipour , Germán Bassi , Mikael Skoglund

Online Class-Incremental continual Learning (OCIL) addresses the challenge of continuously learning from a single-channel data stream, adapting to new tasks while mitigating catastrophic forgetting. Recently, Mutual Information (MI)-based…

Machine Learning · Computer Science 2024-07-29 Huan Zhang , Fan Lyu , Shenghua Fan , Yujin Zheng , Dingwen Wang

Deep neural networks (DNNs) often suffer from "catastrophic forgetting" during incremental learning (IL) --- an abrupt degradation of performance on the original set of classes when the training objective is adapted to a newly added set of…

Computer Vision and Pattern Recognition · Computer Science 2020-01-17 Junting Zhang , Jie Zhang , Shalini Ghosh , Dawei Li , Serafettin Tasci , Larry Heck , Heming Zhang , C. -C. Jay Kuo

Entropy and mutual information in neural networks provide rich information on the learning process, but they have proven difficult to compute reliably in high dimensions. Indeed, in noisy and high-dimensional data, traditional estimates in…

Computer Vision and Pattern Recognition · Computer Science 2023-12-11 Danqi Liao , Chen Liu , Benjamin W. Christensen , Alexander Tong , Guillaume Huguet , Guy Wolf , Maximilian Nickel , Ian Adelstein , Smita Krishnaswamy

Deep neural networks (DNNs) are found to be vulnerable to adversarial noise. They are typically misled by adversarial samples to make wrong predictions. To alleviate this negative effect, in this paper, we investigate the dependence between…

Machine Learning · Computer Science 2022-07-26 Dawei Zhou , Nannan Wang , Xinbo Gao , Bo Han , Xiaoyu Wang , Yibing Zhan , Tongliang Liu

Recent work has established that the conditional mutual information (CMI) framework of Steinke and Zakynthinou (2020) is expressive enough to capture generalization guarantees in terms of algorithmic stability, VC dimension, and related…

Machine Learning · Computer Science 2023-03-28 Fredrik Hellström , Giuseppe Durisi

Estimating conditional mutual information (CMI) is an essential yet challenging step in many machine learning and data mining tasks. Estimating CMI from data that contains both discrete and continuous variables, or even discrete-continuous…

Information Theory · Computer Science 2021-01-14 Alexander Marx , Lincen Yang , Matthijs van Leeuwen

The emerging neural topic models make topic modeling more easily adaptable and extendable in unsupervised text mining. However, the existing neural topic models is difficult to retain representative information of the documents within the…

Computation and Language · Computer Science 2022-03-15 Kang Xu , Xiaoqiu Lu , Yuan-fang Li , Tongtong Wu , Guilin Qi , Ning Ye , Dong Wang , Zheng Zhou

Recent contrastive representation learning methods rely on estimating mutual information (MI) between multiple views of an underlying context. E.g., we can derive multiple views of a given image by applying data augmentation, or we can…

Machine Learning · Computer Science 2021-06-28 Alessandro Sordoni , Nouha Dziri , Hannes Schulz , Geoff Gordon , Phil Bachman , Remi Tachet

Continual Learning (CL) aims to enable Deep Neural Networks (DNNs) to learn new data without forgetting previously learned knowledge. The key to achieving this goal is to avoid confusion at the feature level, i.e., avoiding confusion within…

Machine Learning · Computer Science 2024-08-07 Shaoxu Cheng , Kanglei Geng , Chiyuan He , Zihuan Qiu , Linfeng Xu , Heqian Qiu , Lanxiao Wang , Qingbo Wu , Fanman Meng , Hongliang Li

Estimating mutual information between continuous random variables is often intractable and extremely challenging for high-dimensional data. Recent progress has leveraged neural networks to optimize variational lower bounds on mutual…

Machine Learning · Computer Science 2020-12-01 Ruizhi Liao , Daniel Moyer , Polina Golland , William M. Wells

We derive information theoretic generalization bounds for supervised learning algorithms based on a new measure of leave-one-out conditional mutual information (loo-CMI). Contrary to other CMI bounds, which are black-box bounds that do not…

Machine Learning · Computer Science 2022-07-04 Mohamad Rida Rammal , Alessandro Achille , Aditya Golatkar , Suhas Diggavi , Stefano Soatto

Knowledge-based AI typically depends on a knowledge engineer to construct a formal model of domain knowledge -- but what if domain experts could do this themselves? This paper describes an extension to the Decision Model and Notation (DMN)…

Artificial Intelligence · Computer Science 2021-10-07 Simon Vandevelde , Bram Aerts , Joost Vennekens

Leveraging the diversity and quantity of data provided by various graph-structured data augmentations while preserving intrinsic semantic information is challenging. Additionally, successive layers in graph neural network (GNN) tend to…

Machine Learning · Computer Science 2026-03-19 Jie Chen , Hua Mao , Chuanbin Liu , Zhu Wang , Xi Peng

We study the mutual information between (certain summaries of) the output of a learning algorithm and its $n$ training data, conditional on a supersample of $n+1$ i.i.d. data from which the training data is chosen at random without…

Machine Learning · Computer Science 2022-06-30 Mahdi Haghifam , Shay Moran , Daniel M. Roy , Gintare Karolina Dziugaite

Token-level adaptive training approaches can alleviate the token imbalance problem and thus improve neural machine translation, through re-weighting the losses of different target tokens based on specific statistical metrics (e.g., token…

Computation and Language · Computer Science 2022-03-08 Songming Zhang , Yijin Liu , Fandong Meng , Yufeng Chen , Jinan Xu , Jian Liu , Jie Zhou

In recent years, several unsupervised, "contrastive" learning algorithms in vision have been shown to learn representations that perform remarkably well on transfer tasks. We show that this family of algorithms maximizes a lower bound on…

Machine Learning · Computer Science 2020-06-08 Mike Wu , Chengxu Zhuang , Milan Mosse , Daniel Yamins , Noah Goodman