15 citations · 20 across the 6 of their papers we have counts for
5 papers · 1 filter
A Large Deviations Perspective on Policy Gradient Algorithms
Wouter Jongeneel, Daniel Kuhn, Mengmeng Li
Motivated by policy gradient methods in the context of reinforcement learning, we identify a large deviation rate function for the iterates generated by stochastic gradient descent…
On continuation and convex Lyapunov functions
Wouter Jongeneel, Roland Schwan
Suppose that the origin is globally asymptotically stable under a set of continuous vector fields on Euclidean space and suppose that all those vector fields come equipped with --…
Topological Linear System Identification via Moderate Deviations Theory
Wouter Jongeneel, Tobias Sutter, Daniel Kuhn
Two dynamical systems are topologically equivalent when their phase-portraits can be morphed into each other by a homeomorphic coordinate transformation on the state space. The ind…
Small errors in random zeroth-order optimization are imaginary
Wouter Jongeneel, Man-Chung Yue, Daniel Kuhn
Most zeroth-order optimization algorithms mimic a first-order algorithm but replace the gradient of the objective function with some gradient estimator that can be computed from a…
Efficient Learning of a Linear Dynamical System with Stability Guarantees
Wouter Jongeneel, Tobias Sutter, Daniel Kuhn
We propose a principled method for projecting an arbitrary square matrix to the non-convex set of asymptotically stable matrices. Leveraging ideas from large deviations theory, we…