From the 1 of 4 linked papers with an AI index.
4 papers
Learning a Decentralized Medium Access Control Protocol for Shared Message Transmission
Lorenzo Mario Amorosa, Zhan Gao, Roberto Verdone +2
The paper proposes a decentralized learning framework that lets IoT nodes coordinate transmission of shared messages without inter-node communication, using deterministic strategie…
On the Generalization Error of Differentially Private Algorithms via Typicality
Yanxiao Liu, Chun Hei Michael Shiu, Lele Wang +1
We study the generalization error of stochastic learning algorithms from an information-theoretic perspective, with a particular emphasis on deriving sharper bounds for differentia…
Training with Fewer Bits: Unlocking Edge LLMs Training with Stochastic Rounding
Taowen Liu, Marta Andronic, Deniz Gündüz +1
LLM training is resource-intensive. Quantized training improves computational and memory efficiency but introduces quantization noise, which can hinder convergence and degrade mode…
Token-Domain Multiple Access: Exploiting Semantic Orthogonality for Collision Mitigation
Li Qiao, Mahdi Boloursaz Mashhadi, Zhen Gao +1
Token communications is an emerging generative semantic communication concept that reduces transmission rates by using context and transformer-based token processing, with tokens s…