works on

From the 1 of 7 linked papers with an AI index.

collaborators

7 papers

cs.DC2026

User-Assisted Collaborative Distributed Inference for Efficient QoS-Aware Autoscaling

Alfreds Lapkovskis, Ali Beikmohammadi, Sindri Magnússon +1

Growing demand for artificial intelligence (AI) inference services requires scalable infrastructure, yet centralized serving costs rise with demand. We propose a collaborative dist…

cs.DC2026

Trust-Aware Topology Learning for Dynamic Decentralized Federated Learning under Adversaries

Shubham Vaishnav, Murtaza Rangwala, Ali Beikmohammadi +3

In dynamic mobile decentralized federated learning (DFL), adversaries can poison both model updates and the topology information devices use to choose collaborators. We present DMT…

cs.LG2026

Reinforcement Learning in Switching Non-Stationary Markov Decision Processes: Algorithms and Convergence Analysis

Mohsen Amiri, Sindri Magnússon

The paper introduces a Switching Non-Stationary MDP framework where the environment alternates among a finite set of MDPs via a hidden Markov chain, and proves that standard TD lea…

cs.DC2026

Dynamic and Distributed Routing in IoT Networks based on Multi-Objective Q-Learning

Shubham Vaishnav, Praveen Kumar Donta, Sindri Magnússon

IoT networks often face conflicting routing goals such as maximizing packet delivery, minimizing delay, and conserving limited battery energy. These priorities can also change dyna…

cs.LG2025

Adaptive Budgeted Multi-Armed Bandits for IoT with Dynamic Resource Constraints

Shubham Vaishnav, Praveen Kumar Donta, Sindri Magnússon

Internet of Things (IoT) systems increasingly operate in environments where devices must respond in real time while managing fluctuating resource constraints, including energy and…

cs.LG2025

Collaborative Value Function Estimation Under Model Mismatch: A Federated Temporal Difference Analysis

Ali Beikmohammadi, Sarit Khirirat, Peter Richtárik +1

Federated reinforcement learning (FedRL) enables collaborative learning while preserving data privacy by preventing direct data exchange between agents. However, many existing FedR…