34 citations · 210 across the 68 of their papers we have counts for
6 papers · 1 filter
LipKernel: Lipschitz-Bounded Convolutional Neural Networks via Dissipative Layers
Patricia Pauli, Ruigang Wang, Ian Manchester +1
We propose a novel layer-wise parameterization for convolutional neural networks (CNNs) that includes built-in robustness guarantees by enforcing a prescribed Lipschitz bound. Each…
On Robust Reinforcement Learning with Lipschitz-Bounded Policy Networks
Nicholas H. Barbara, Ruigang Wang, Ian R. Manchester
This paper presents a study of robust policy networks in deep reinforcement learning. We investigate the benefits of policy parameterizations that naturally satisfy constraints on…
Learning Stable and Passive Neural Differential Equations
Jing Cheng, Ruigang Wang, Ian R. Manchester
In this paper, we introduce a novel class of neural differential equation, which are intrinsically Lyapunov stable, exponentially stable or passive. We take a recently proposed Pol…
Control contraction metrics on Lie groups
Dongjun Wu, Bowen Yi, Ian R. Manchester
In this paper, we extend the control contraction metrics (CCM) approach, which was originally proposed for the universal tracking control of nonlinear systems, to those that evolve…
Monotone, Bi-Lipschitz, and Polyak-Lojasiewicz Networks
Ruigang Wang, Krishnamurthy Dvijotham, Ian R. Manchester
This paper presents a new bi-Lipschitz invertible neural network, the BiLipNet, which has the ability to smoothly control both its Lipschitzness (output sensitivity to input pertur…
Learning Stable Koopman Embeddings for Identification and Control
Fletcher Fan, Bowen Yi, David Rye +2
This paper introduces new model parameterizations for learning discrete-time dynamical systems from data via the Koopman operator and studies their properties. Whereas most existin…