4 papers
When Graph Structure Provably Helps Classification: Non-Asymptotic Recovery Guarantees
Firooz Shahriari-Mehr, Javad Aliakbari, Alexandre Graell i Amat +1
The joint use of graph structure and node-specific information is central to transductive node classification, yet a fundamental theoretical question remains: when does graph struc…
Asynchronous Decentralized Optimization with Constraints: Achievable Speeds of Convergence for Directed Graphs
Firooz Shahriari-Mehr, Ashkan Panahi
We address a decentralized convex optimization problem, where every agent has its unique local objective function and constraint set. Agents compute at different speeds, and their…
Double Averaging and Gradient Projection: Convergence Guarantees for Decentralized Constrained Optimization
Firooz Shahriari-Mehr, Ashkan Panahi
We consider a generic decentralized constrained optimization problem over static, directed communication networks, where each agent has exclusive access to only one convex, differe…
Decentralized Constrained Optimization: Double Averaging and Gradient Projection
Firooz Shahriari-Mehr, David Bosch, Ashkan Panahi
In this paper, we consider the convex, finite-sum minimization problem with explicit convex constraints over strongly connected directed graphs. The constraint is an intersection o…