8 papers
Privacy Preserving Gossip Learning
Erkan Bayram, Mohamed-Ali Belabbas, Tamer Başar
We propose a decentralized privacy-preserving learning algorithm in which each agent holds a single private sample and a shared model. Samples are learned sequentially, and each up…
Control Disturbance Rejection in Neural ODEs
Erkan Bayram, Mohamed-Ali Belabbas, Tamer Başar
In this paper, we propose an iterative training algorithm for Neural ODEs that provides models resilient to control (parameter) disturbances. The method builds on our earlier work…
Geometric Foundations of Tuning without Forgetting in Neural ODEs
Erkan Bayram, Mohamed-Ali Belabbas, Tamer Başar
In our earlier work, we introduced the principle of Tuning without Forgetting (TwF) for sequential training of neural ODEs, where training samples are added iteratively and paramet…
Constructing Stochastic Matrices for Weighted Averaging in Gossip Networks
Erkan Bayram, Mohamed-Ali Belabbas
The convergence of the gossip process has been extensively studied; however, algorithms that generate a set of stochastic matrices, the infinite product of which converges to a ran…
Age of Coded Updates In Gossip Networks Under Memory and Memoryless Schemes
Erkan Bayram, Melih Bastopcu, Mohamed-Ali Belabbas +1
We consider an information update system on a gossip network, where a source node encodes information into total keys such that any subset of at least keys can fully reco…
Control Theoretic Approach to Fine-Tuning and Transfer Learning
Erkan Bayram, Shenyu Liu, Mohamed-Ali Belabbas +1
Given a training set in the form of a paired , we say that the control system has learned the paired set via the control if the s…
Age of -out-of- Systems on a Gossip Network
Erkan Bayram, Melih Bastopcu, Mohamed-Ali Belabbas +1
We consider information update systems on a gossip network, which consists of a single source and receiver nodes. The source encrypts the information into distinct keys wit…
Vector-Valued Gossip over -Holonomic Networks
Erkan Bayram, Mohamed-Ali Belabbas, Tamer Başar
We study the weighted average consensus problem for a gossip network of agents with vector-valued states. For a given matrix-weighted graph, the gossip process is described by a se…