Zobrazeno 1 - 10
of 13
pro vyhledávání: '"Elgabli, A. (Anis)"'
Publikováno v:
2022 IEEE Wireless Communications and Networking Conference (WCNC).
In this paper, we propose a communication-efficient alternating direction method of multipliers (ADMM)-based algorithm for solving a distributed learning problem in the stochastic non-convex setting. Our approach runs a few stochastic gradient descen
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::afcded56c374a70cf980f67fdad652b0
https://doi.org/10.1109/wcnc51071.2022.9771559
https://doi.org/10.1109/wcnc51071.2022.9771559
In this paper, we propose to solve a regularized distributionally robust learning problem in the decentralized setting, taking into account the data distribution shift. By adding a Kullback-Liebler regularization function to the robust min-max optimi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f0e58bbe9a841c29585787b44645e557
Autor:
Elgabli, A. (Anis), Ben Issaid, C. (Chaouki), Bedi, A. S. (Amrit S.), Bennis, M. (Mehdi), Aggarwal, V. (Vaneet)
In this paper, we propose an energy-efficient federated meta-learning framework. The objective is to enable learning a meta-model that can be fine-tuned to a new task with a few number of samples in a distributed setting and at low computation and co
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od______2423::cacfcb73c2df2b482ed451b22326dd98
http://urn.fi/urn:nbn:fi-fe2023032733313
http://urn.fi/urn:nbn:fi-fe2023032733313
Autor:
Park, J. (Jihong), Samarakoon, S. (Sumudu), Elgabli, A. (Anis), Kim, J. (Joongheon), Bennis, M. (Mehdi), Kim, S.-L. (Seong-Lyun), Debbah, M. (Mérouane)
Machine learning (ML) is a promising enabler for the fifth-generation (5G) communication systems and beyond. By imbuing intelligence into the network edge, edge nodes can proactively carry out decision-making and, thereby, react to local environmenta
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od______2423::0e72fde1464ae5ee004ce136c986298c
http://urn.fi/urn:nbn:fi-fe2021082343805
http://urn.fi/urn:nbn:fi-fe2021082343805
This article deals with the problem of distributed machine learning, in which agents update their models based on their local datasets, and aggregate the updated models collaboratively and in a fully decentralized manner. In this paper, we tackle the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od______2423::75c4f469c4100f3634762cab9aaa042b
http://urn.fi/urn:nbn:fi-fe2021102151850
http://urn.fi/urn:nbn:fi-fe2021102151850
Autor:
Elgabli, A. (Anis), Park, J. (Jihong), Bedi, A. S. (Amrit S.), Issaid, C. B. (Chaouki Ben), Bennis, M. (Mehdi), Aggarwal, V. (Vaneet)
In this article, we propose a communication-efficient decentralized machine learning (ML) algorithm, coined quantized group ADMM (Q-GADMM). To reduce the number of communication links, every worker in Q-GADMM communicates only with two neighbors, whi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od______2423::2a06c9a783f6dee8622815d08a26c5bc
http://urn.fi/urn:nbn:fi-fe202103096830
http://urn.fi/urn:nbn:fi-fe202103096830
This article proposes a communication-efficient decentralized deep learning algorithm, coined layer-wise federated group ADMM (L-FGADMM). To minimize an empirical risk, every worker in L-FGADMM periodically communicates with two neighbors, in which t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od______2423::695d91b0acb1048d619a235f1cbad463
http://urn.fi/urn:nbn:fi-fe2020102787858
http://urn.fi/urn:nbn:fi-fe2020102787858
This paper proposes and evaluates a novel algorithm for streaming video over HTTP. The problem is formulated as a non-convex optimization problem which is constrained by the predicted available bandwidth, chunk deadlines, available video rates, and b
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od______2423::152e80b364495c3dd43d4181ca47f112
http://urn.fi/urn:nbn:fi-fe2020102787863
http://urn.fi/urn:nbn:fi-fe2020102787863
Autor:
Elgabli, A. (Anis), Park, J. (Jihong), Bedi, A. S. (Amrit S.), Bennis, M. (Mehdi), Aggarwal, V. (Vaneet)
When the data is distributed across multiple servers, lowering the communication cost between the servers (or workers) while solving the distributed learning problem is an important problem and is the focus of this paper. In particular, we propose a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od______2423::05c4775689bf81e39d68b163e05c6de3
http://urn.fi/urn:nbn:fi-fe2020050825688
http://urn.fi/urn:nbn:fi-fe2020050825688
Simultaneous access to multiple interfaces (e.g., WiFi and cellular networks) can significantly improve the users’ quality of experience (QoE) in video streaming. However, some interfaces could be more expensive to use and less energy efficient. Th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od______2423::0041634108ac6cf5935b8e120b7a42aa
http://urn.fi/urn:nbn:fi-fe2020111390309
http://urn.fi/urn:nbn:fi-fe2020111390309