From the 1 of 10 linked papers with an AI index.
10 papers
Distributed Optimization with Streaming Data: A Temporal Weighting Perspective
Muhammad Faraz Ul Abrar, Nicolò Michelusi, Erik G. Larsson
Optimization theory is a widely used tool for intelligent decision-making. While classical optimization deals with fixed, time-invariant objective functions, many modern applicatio…
Decentralized Gradient Descent: Bottleneck Regimes and Budget Complexity
Nicolò Michelusi
The paper analyzes how much communication and computation are needed for decentralized gradient descent to reach a given accuracy, identifying different bottleneck regimes and prov…
Decentralized Time-Varying Optimization for Streaming Data via Temporal Weighting
Muhammad Faraz Ul Abrar, Nicolò Michelusi, Erik G. Larsson
Classical optimization theory largely focuses on fixed objective functions, whereas many modern learning systems operate in dynamic environments where data arrive sequentially and…
Biased Federated Learning under Wireless Heterogeneity
Muhammad Faraz Ul Abrar, Nicolò Michelusi
Federated learning (FL) has emerged as a promising framework for distributed learning, enabling collaborative model training without sharing private data. Existing wireless FL work…
Non-Convex Over-the-Air Heterogeneous Federated Learning: A Bias-Variance Trade-off
Muhammad Faraz Ul Abrar, Nicolò Michelusi
Over-the-air (OTA) federated learning (FL) has been well recognized as a scalable paradigm that exploits the waveform superposition of the wireless multiple-access channel to aggre…
Interference-Robust Non-Coherent Over-the-Air Computation for Decentralized Optimization
Nicolò Michelusi
Non-coherent over-the-air (NCOTA) computation enables low-latency and bandwidth-efficient decentralized optimization by exploiting the average energy superposition property of wire…