English
Related papers

Related papers: Distributed Information Bottleneck Method for Disc…

200 papers

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…

Computer Vision and Pattern Recognition · Computer Science 2024-08-15 Zhuohang Dang , Minnan Luo , Chengyou Jia , Guang Dai , Jihong Wang , Xiaojun Chang , Jingdong Wang

Two major challenges in distributed learning and estimation are 1) preserving the privacy of the local samples; and 2) communicating them efficiently to a central server, while achieving high accuracy for the end-to-end task. While there…

Machine Learning · Computer Science 2021-04-23 Wei-Ning Chen , Peter Kairouz , Ayfer Özgür

This work addresses private communication with distributed systems in mind. We consider how to best use secret key resources and communication to transmit signals across a system so that an eavesdropper is least capable to act on the…

Cryptography and Security · Computer Science 2015-03-19 Paul Cuff

This paper considers an information bottleneck problem with the objective of obtaining a most informative representation of a hidden feature subject to a R\'enyi entropy complexity constraint. The optimal bottleneck trade-off between…

Information Theory · Computer Science 2021-02-01 Jian-Jia Weng , Fady Alajaji , Tamás Linder

Information Bottleneck (IB) is a generalization of rate-distortion theory that naturally incorporates compression and relevance trade-offs for learning. Though the original IB has been extensively studied, there has not been much…

Machine Learning · Computer Science 2019-10-08 Thanh T. Nguyen , Jaesik Choi

In the worst-case distributed source coding (DSC) problem of [1], the smaller cardinality of the support-set describing the correlation in informant data, may neither imply that fewer informant bits are required nor that fewer informants…

Information Theory · Computer Science 2009-07-13 Samar Agnihotri , Rajesh Venkatachalapathy

Variational inequalities are an important tool, which includes minimization, saddles, games, fixed-point problems. Modern large-scale and computationally expensive practical applications make distributed methods for solving these problems…

Optimization and Control · Mathematics 2023-03-01 Aleksandr Beznosikov , Alexander Gasnikov

Bounded agents are limited by intrinsic constraints on their ability to process information that is available in their sensors and memory and choose actions and memory updates. In this dissertation, we model these constraints as…

Machine Learning · Computer Science 2017-03-31 Roy Fox

Lossy gradient compression, with either unbiased or biased compressors, has become a key tool to avoid the communication bottleneck in centrally coordinated distributed training of machine learning models. We analyze the performance of two…

Machine Learning · Computer Science 2020-12-23 Sebastian U. Stich

The goal of this thesis is to study the compression problems arising in distributed computing systematically. In the first part of the thesis, we study gradient compression for distributed first-order optimization. We begin by establishing…

Information Theory · Computer Science 2023-01-12 Prathamesh Mayekar

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…

Information Theory · Computer Science 2021-07-15 Karthik Duraisamy

The mutual information is a core statistical quantity that has applications in all areas of machine learning, whether this is in training of density models over multiple data modalities, in maximising the efficiency of noisy transmission…

Machine Learning · Statistics 2015-09-30 Shakir Mohamed , Danilo Jimenez Rezende

Whenever communication takes place to fulfil a goal, an effective way to encode the source data to be transmitted is to use an encoding rule that allows the receiver to meet the requirements of the goal. A formal way to identify the…

Signal Processing · Electrical Eng. & Systems 2022-11-24 Francesco Pezone , Sergio Barbarossa , Paolo Di Lorenzo

We consider the problem of in-network compressed sensing from distributed measurements. Every agent has a set of measurements of a signal $x$, and the objective is for the agents to recover $x$ from their collective measurements using only…

Information Theory · Computer Science 2015-06-17 Stacy Patterson , Yonina C. Eldar , Idit Keidar

In this paper, we present an information-theoretic method for clustering mixed-type data, that is, data consisting of both continuous and categorical variables. The proposed approach extends the Information Bottleneck principle to…

Methodology · Statistics 2026-02-02 Efthymios Costa , Ioanna Papatsouma , Angelos Markos

Decentralized optimization methods enable on-device training of machine learning models without a central coordinator. In many scenarios communication between devices is energy demanding and time consuming and forms the bottleneck of the…

Optimization and Control · Mathematics 2020-11-04 Dmitry Kovalev , Anastasia Koloskova , Martin Jaggi , Peter Richtarik , Sebastian U. Stich

This work considers a layered coding approach for efficient transmission of data over a wireless block fading channel without transmitter channel state information (CSI), which is connected to a limited capacity reliable link, known as the…

Information Theory · Computer Science 2020-05-01 Avi Steiner , Shlomo Shamai

The information bottleneck (IB) problem is a widely studied framework in machine learning for extracting compressed features that are informative for downstream tasks. However, current approaches to solving the IB problem rely on a…

Information Theory · Computer Science 2024-10-11 Amirmohammad Farzaneh , Osvaldo Simeone

The paper studies the distributed stochastic compositional optimization problems over networks, where all the agents' inner-level function is the sum of each agent's private expectation function. Focusing on the aggregative structure of the…

Optimization and Control · Mathematics 2022-11-10 Shengchao Zhao , Yongchao Liu

Variational inequalities in general and saddle point problems in particular are increasingly relevant in machine learning applications, including adversarial learning, GANs, transport and robust optimization. With increasing data and…

Machine Learning · Computer Science 2023-04-04 Aleksandr Beznosikov , Peter Richtárik , Michael Diskin , Max Ryabinin , Alexander Gasnikov