32 citations · 40 across the 11 of their papers we have counts for
19 papers
Fundamentals of Task-Agnostic Data Valuation
Mohammad Mohammadi Amiri, Frederic Berdoz, Ramesh Raskar
We study valuing the data of a data owner/seller for a data seeker/buyer. Data valuation is often carried out for a specific task assuming a particular utility metric, such as test…
Private independence testing across two parties
Praneeth Vepakomma, Mohammad Mohammadi Amiri, Clément L. Canonne +2
We introduce -test, a privacy-preserving algorithm for testing statistical independence between data distributed across multiple parties. Our algorithm relies on privately estim…
Communication-Efficient Federated Learning over MIMO Multiple Access Channels
Yo-Seb Jeon, Mohammad Mohammadi Amiri, Namyoon Lee
Communication efficiency is of importance for wireless federated learning systems. In this paper, we propose a communication-efficient strategy for federated learning over multiple…
Federated Learning with Downlink Device Selection
Mohammad Mohammadi Amiri, Sanjeev R. Kulkarni, H. Vincent Poor
We study federated edge learning, where a global model is trained collaboratively using privacy-sensitive data at the edge of a wireless network. A parameter server (PS) keeps trac…
Blind Federated Edge Learning
Mohammad Mohammadi Amiri, Tolga M. Duman, Deniz Gunduz +2
We study federated edge learning (FEEL), where wireless edge devices, each with its own dataset, learn a global model collaboratively with the help of a wireless access point actin…
Communicate to Learn at the Edge
Deniz Gunduz, David Burth Kurka, Mikolaj Jankowski +3
Bringing the success of modern machine learning (ML) techniques to mobile devices can enable many new services and businesses, but also poses significant technical and research cha…
Convergence of Federated Learning over a Noisy Downlink
Mohammad Mohammadi Amiri, Deniz Gunduz, Sanjeev R. Kulkarni +1
We study federated learning (FL), where power-limited wireless devices utilize their local datasets to collaboratively train a global model with the help of a remote parameter serv…
Federated Learning With Quantized Global Model Updates
Mohammad Mohammadi Amiri, Deniz Gunduz, Sanjeev R. Kulkarni +1
We study federated learning (FL), which enables mobile devices to utilize their local datasets to collaboratively train a global model with the help of a central server, while keep…
A Compressive Sensing Approach for Federated Learning over Massive MIMO Communication Systems
Yo-Seb Jeon, Mohammad Mohammadi Amiri, Jun Li +1
Federated learning is a privacy-preserving approach to train a global model at a central server by collaborating with wireless devices, each with its own local training data set. I…
Convergence of Update Aware Device Scheduling for Federated Learning at the Wireless Edge
Mohammad Mohammadi Amiri, Deniz Gunduz, Sanjeev R. Kulkarni +1
We study federated learning (FL) at the wireless edge, where power-limited devices with local datasets collaboratively train a joint model with the help of a remote parameter serve…
Multi-Antenna Coded Content Delivery with Caching: A Low-Complexity Solution
Junlin Zhao, Mohammad Mohammadi Amiri, Deniz Gündüz
We study downlink beamforming in a single-cell network with a multi-antenna base station serving cache-enabled users. Assuming a library of files with a common rate, we formulate t…
Collaborative Machine Learning at the Wireless Edge with Blind Transmitters
Mohammad Mohammadi Amiri, Tolga M. Duman, Deniz Gunduz
We study wireless collaborative machine learning (ML), where mobile edge devices, each with its own dataset, carry out distributed stochastic gradient descent (DSGD) over-the-air w…
Federated Learning over Wireless Fading Channels
Mohammad Mohammadi Amiri, Deniz Gunduz
We study federated machine learning at the wireless network edge, where limited power wireless devices, each with its own dataset, build a joint model with the help of a remote par…
A Low-Complexity Cache-Aided Multi-antenna Content Delivery Scheme
Junlin Zhao, Mohammad Mohammadi Amiri, Deniz Gündüz
We study downlink beamforming in a single-cell network with a multi-antenna base station (BS) serving cache-enabled users. For a given common rate of the files in the system, we fi…
On the Capacity Region of a Cache-Aided Gaussian Broadcast Channel with Multi-Layer Messages
Mohammad Mohammadi Amiri, Deniz Gunduz
A cache-aided -user Gaussian broadcast channel (BC) is studied. The transmitter has a library of files, from which each user requests one. The users are equipped with caches…
Caching and Coded Delivery over Gaussian Broadcast Channels for Energy Efficiency
Mohammad Mohammadi Amiri, Deniz Gunduz
A cache-aided -user Gaussian broadcast channel (BC) is considered. The transmitter has a library of equal-rate files, from which each user demands one. The impact of the equ…
Cache-Aided Content Delivery over Erasure Broadcast Channels
Mohammad Mohammadi Amiri, Deniz Gunduz
A cache-aided broadcast network is studied, in which a server delivers contents to a group of receivers over a packet erasure broadcast channel (BC). The receivers are divided into…
Decentralized Coded Caching with Distinct Cache Capacities
Mohammad Mohammadi Amiri, Qianqian Yang, Deniz Gündüz
Decentralized coded caching is studied for a content server with files, each of size bits, serving active users, each equipped with a cache of distinct capacity. It is…
Coded Caching for a Large Number Of Users
Mohammad Mohammadi Amiri, Qianqian Yang, Deniz Gunduz
Information theoretic analysis of a coded caching system is considered, in which a server with a database of N equal-size files, each F bits long, serves K users. Each user is assu…