6 papers
The Geometry of Randomized Smoothing on Feasible Sets
Syed Izhan Khilji, Alireza Furutanpey, Schahram Dustdar
Randomized smoothing certifies the probability of a fixed output event as the center of Gaussian noise moves. Feasibility or confidence filtering reports label probabilities only a…
On Task Scope and Information Retention in Source Coding
Alireza Furutanpey, Kerstin Bunte
We argue that dividing codec design into Coding for Machines (CfM) and Coding for Humans (CfH) is a misleading distinction for deciding what information a codec may discard. Receiv…
FANS: Federated Adaptive Network Search Learning for Heterogeneous Devices
Jiaxin Zhang, Xingwei Wang, Bo Yi +6
Heterogeneous Federated Learning (HFL) aims to train models across devices with diverse resource budgets while preserving data privacy. Existing HFL methods typically bind training…
LYRA: Label-Free Structural Synchronization and Resource Allocation for UAV Edge Networks
Feng He, Alireza Furutanpey, Paolo Bellavista +4
While deploying hierarchical vision models to process mission-critical tasks, UAV edge systems must adaptively update the models to sustain inference reliability under low-level en…
Principled Direction-Free Intrinsic Motivation through Model-Free Epistemic Free-Energy Estimators
Alireza Furutanpey, Schahram Dustdar
Across environments with mixed sources of uncertainty, unsupervised reinforcement learning requires intrinsic motivation that does not precommit to a particular direction of surpri…
Incentives and Evidence in Learned Service Orchestration
Syed Izhan Khilji, Alireza Furutanpey, Schahram Dustdar
Reinforcement learning for service orchestration has been the subject of sustained research for over a decade, yet it is not used in production at scale. The usual explanation is t…