activity
20182023
most citedCharacterizing possible failure modes in physics-informed neural networks

118 citations · 440 across the 31 of their papers we have counts for

collaborators
Showing 2022Show all

11 papers · 1 filter

cs.LG2022★ 3 cited

Gated Recurrent Neural Networks with Weighted Time-Delay Feedback

N. Benjamin Erichson, Soon Hoe Lim, Michael W. Mahoney

In this paper, we present a novel approach to modeling long-term dependencies in sequential data by introducing a gated recurrent unit (GRU) with a weighted time-delay feedback mec…

stat.ML2022★ 1 cited

Monotonicity and Double Descent in Uncertainty Estimation with Gaussian Processes

Liam Hodgkinson, Chris van der Heide, Fred Roosta +1

Despite their importance for assessing reliability of predictions, uncertainty quantification (UQ) measures for machine learning models have only recently begun to be rigorously ch…

cs.LG2022★ 7 cited

Gradient Gating for Deep Multi-Rate Learning on Graphs

T. Konstantin Rusch, Benjamin P. Chamberlain, Michael W. Mahoney +2

We present Gradient Gating (G), a novel framework for improving the performance of Graph Neural Networks (GNNs). Our framework is based on gating the output of GNN layers with…

cs.LG2022★ 3 cited

Adaptive Self-supervision Algorithms for Physics-informed Neural Networks

Shashank Subramanian, Robert M. Kirby, Michael W. Mahoney +1

Physics-informed neural networks (PINNs) incorporate physical knowledge from the problem domain as a soft constraint on the loss function, but recent work has shown that this can l…

cs.LG2022★ 6 cited

Learning differentiable solvers for systems with hard constraints

Geoffrey Négiar, Michael W. Mahoney, Aditi S. Krishnapriyan

We introduce a practical method to enforce partial differential equation (PDE) constraints for functions defined by neural networks (NNs), with a high degree of accuracy and up to…

cs.CR2022★ 33 cited

Neurotoxin: Durable Backdoors in Federated Learning

Zhengming Zhang, Ashwinee Panda, Linyue Song +5

Due to their decentralized nature, federated learning (FL) systems have an inherent vulnerability during their training to adversarial backdoor attacks. In this type of attack, the…