4 papers
Computer-aided analyses of stochastic first-order methods, via interpolation conditions for stochastic optimization
Anne Rubbens, Sébastien Colla, Julien M. Hendrickx
This work proposes a framework, embedded within the Performance Estimation framework (PEP), for obtaining worst-case performance guarantees on stochastic first-order methods. Given…
Analysis of Value Iteration Through Absolute Probability Sequences
Arsenii Mustafin, Sebastien Colla, Alex Olshevsky +1
Value Iteration is a widely used algorithm for solving Markov Decision Processes (MDPs). While previous studies have extensively analyzed its convergence properties, they primarily…
Exploiting Agent Symmetries for Performance Analysis of Distributed Optimization Methods
Sebastien Colla, Julien M. Hendrickx
We show that, in many settings, the worst-case performance of a distributed optimization algorithm is independent of the number of agents in the system, and can thus be computed in…
On the Optimal Communication Weights in Distributed Optimization Algorithms
Sebastien Colla, Julien M. Hendrickx
We establish that in distributed optimization, the prevalent strategy of minimizing the second-largest eigenvalue modulus (SLEM) of the averaging matrix for selecting communication…