Search for dissertations about: "Communication efficient learning"

Showing result 1 - 5 of 63 swedish dissertations containing the words Communication efficient learning.

  1. 1. Machine Learning for Wireless Link Adaptation : Supervised and Reinforcement Learning Theory and Algorithms

    Author : Vidit Saxena; Joakim Jaldén; Mats Bengtsson; Hugo Tullberg; Jakob Hoydis; KTH; []
    Keywords : ENGINEERING AND TECHNOLOGY; TEKNIK OCH TEKNOLOGIER; TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Wireless Communications; Reinforcement Learning; Multi-Armed Bandits; Thompson Sampling; Convex Optimization; Deep Learning; Electrical Engineering; Elektro- och systemteknik;

    Abstract : Wireless data communication is a complex phenomenon. Wireless links encounter random, time-varying, channel effects that are challenging to predict and compensate. Hence, to optimally utilize the channel, wireless links adapt the data transmission parameters in real time. READ MORE

  2. 2. Efficient Communication via Reinforcement Learning

    Author : Emil Carlsson; Chalmers University of Technology; []
    Keywords : NATURVETENSKAP; NATURAL SCIENCES;

    Abstract : Why do languages partition mental concepts into words the way the do? Recent works have taken a information-theoretic view on human language and suggested that it is shaped by the need for efficient communication. This means that human language is shaped by a simultaneous pressure for being informative, while also being simple in order to minimize the cognitive load. READ MORE

  3. 3. Reliable and Efficient Distributed Machine Learning

    Author : Hao Chen; Ming Xiao; Mikael Skoglund; Yan Zhang; KTH; []
    Keywords : ENGINEERING AND TECHNOLOGY; TEKNIK OCH TEKNOLOGIER; Distributed machine learning; federated learning; communication efficiency; decentralized optimization; Electrical Engineering; Elektro- och systemteknik;

    Abstract : With the ever-increasing penetration and proliferation of various smart Internet of Things (IoT) applications, machine learning (ML) is envisioned to be a key technique for big-data-driven modelling and analysis. Since massive data generated from these IoT devices are commonly collected and stored in a distributed manner, ML at the networks, e.g. READ MORE

  4. 4. First-Order Algorithms for Communication Efficient Distributed Learning

    Author : Sarit Khirirat; Mikael Johansson; Tong Zhang; KTH; []
    Keywords : ENGINEERING AND TECHNOLOGY; TEKNIK OCH TEKNOLOGIER; TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Communication efficient learning; Optimization algorithms; Quantization; Error compensation; First-order algorithms; Stochastic gradient descent; Electrical Engineering; Elektro- och systemteknik;

    Abstract : Innovations in numerical optimization, statistics and high performance computing have enabled tremendous advances in machine learning algorithms, fuelling applications from natural language processing to autonomous driving.To deal with increasing data volumes, and to keep the training times of increasingly complex machine learning models reasonable, modern optimization algorithms distribute both data and computations over a large number of machines. READ MORE

  5. 5. First-Order Algorithms for Communication Efficient Distributed Learning

    Author : Sarit Khirirat; Mikael Johansson; Martin Jaggi; KTH; []
    Keywords : ENGINEERING AND TECHNOLOGY; TEKNIK OCH TEKNOLOGIER; TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Communication efficient learning; Optimization algorithms; Quantization; Error compensation; First-order algorithms; Stochastic gradient descent; Tillämpad matematik och beräkningsmatematik; Applied and Computational Mathematics; Optimeringslära och systemteori; Optimization and Systems Theory; Electrical Engineering; Elektro- och systemteknik;

    Abstract : Technological developments in devices and storages have made large volumes of data collections more accessible than ever. This transformation leads to optimization problems with massive data in both volume and dimension. READ MORE