2 papers
math.OC2026
Operator Calculus for Population-Based Optimization: Modular Convergence and Finite-Population Guarantees
Pekka Malo, Lauri Viitasaari, Patrik Nummi +3
Population-based optimizers combine update rules such as mutation, selection, and recombination. When one rule changes, it is often unclear which convergence guarantees survive or…
cs.LG2024
Convex Regularization and Convergence of Policy Gradient Flows under Safety Constraints
Pekka Malo, Lauri Viitasaari, Antti Suominen +2
This paper examines reinforcement learning (RL) in infinite-horizon decision processes with almost-sure safety constraints, crucial for applications like autonomous systems, financ…