34 citations · 210 across the 68 of their papers we have counts for
13 papers · 1 filter
R2DN: Scalable Parameterization of Contracting and Lipschitz Recurrent Deep Networks
Nicholas H. Barbara, Ruigang Wang, Ian R. Manchester
This paper presents the Robust Recurrent Deep Network (R2DN), a scalable parameterization of stable and robust recurrent neural networks for machine learning and data-driven contro…
Norm-Bounded Low-Rank Adaptation
Ruigang Wang, Krishnamurthy Dvijotham, Ian R. Manchester
In this work, we propose norm-bounded low-rank adaptation (NB-LoRA) for parameter-efficient fine tuning. NB-LoRA is a novel parameterization of low-rank weight adaptations that adm…
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…
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…
RobustNeuralNetworks.jl: a Package for Machine Learning and Data-Driven Control with Certified Robustness
Nicholas H. Barbara, Max Revay, Ruigang Wang +2
Neural networks are typically sensitive to small input perturbations, leading to unexpected or brittle behaviour. We present RobustNeuralNetworks.jl: a Julia package for neural net…
Lipschitz-bounded 1D convolutional neural networks using the Cayley transform and the controllability Gramian
Patricia Pauli, Ruigang Wang, Ian R. Manchester +1
We establish a layer-wise parameterization for 1D convolutional neural networks (CNNs) with built-in end-to-end robustness guarantees. In doing so, we use the Lipschitz constant of…
Direct Parameterization of Lipschitz-Bounded Deep Networks
Ruigang Wang, Ian R. Manchester
This paper introduces a new parameterization of deep neural networks (both fully-connected and convolutional) with guaranteed Lipschitz bounds, i.e. limited sensitivity to…
Learning Stable Koopman Embeddings
Fletcher Fan, Bowen Yi, David Rye +2
In this paper, we present a new data-driven method for learning stable models of nonlinear systems. Our model lifts the original state space to a higher-dimensional linear manifold…
Recurrent Equilibrium Networks: Flexible Dynamic Models with Guaranteed Stability and Robustness
Max Revay, Ruigang Wang, Ian R. Manchester
This paper introduces recurrent equilibrium networks (RENs), a new class of nonlinear dynamical models} for applications in machine learning, system identification and control. The…
Lipschitz Bounded Equilibrium Networks
Max Revay, Ruigang Wang, Ian R. Manchester
This paper introduces new parameterizations of equilibrium neural networks, i.e. networks defined by implicit equations. This model class includes standard multilayer and residual…
A Convex Parameterization of Robust Recurrent Neural Networks
Max Revay, Ruigang Wang, Ian R. Manchester
Recurrent neural networks (RNNs) are a class of nonlinear dynamical systems often used to model sequence-to-sequence maps. RNNs have excellent expressive power but lack the stabili…
Contracting Implicit Recurrent Neural Networks: Stable Models with Improved Trainability
Max Revay, Ian R. Manchester
Stability of recurrent models is closely linked with trainability, generalizability and in some applications, safety. Methods that train stable recurrent neural networks, however,…