3 papers
math.OC2026
A New Duality-Free Framework for Convex Optimisation with Superlinear Convergence and Effective Warm-Starting
Michael Cummins, Eric Kerrigan
Modern second order solvers for convex optimisation, such as interior point methods, rely on primal dual information and are difficult to warm start, limiting their applicability i…
math.OC2024
DeePC-Hunt: Data-enabled Predictive Control Hyperparameter Tuning via Differentiable Optimization
Michael Cummins, Alberto Padoan, Keith Moffat +2
This paper introduces Data-enabled Predictive Control Hyperparameter Tuning via Differentiable Optimization (DeePC-Hunt), a backpropagation-based method for automatic hyperparamete…
cs.LG2024
Controlling Participation in Federated Learning with Feedback
Michael Cummins, Guner Dilsad Er, Michael Muehlebach
We address the problem of client participation in federated learning, where traditional methods typically rely on a random selection of a small subset of clients for each training…