We propose a thermodynamics-based learning strategy for non-equilibrium evolution
equations based on Onsager's variational principle, which allows us to write such PDEs in …

Anisotropy in the mechanical response of materials with microstructure is common and yet is
difficult to assess and model. To construct accurate response models given only stress …

Abstract Input-Convex Neural Networks (ICNNs) are networks that guarantee convexity in
their input-output map**. These networks have been successfully applied for energy …

We develop fast algorithms and robust software for convex optimization of two-layer neural
networks with ReLU activation functions. Our work leverages a convex re-formulation of the …

A simple approach to rectify unconstrained neural networks for hyperelastic constitutive
models is proposed with the aim of ensuring both mathematical well-posedness (in terms of …

In this paper, we analyze Difference of Convex Neural Networks in the context of one-
dimensional nonlinear regression. Specifically, we show the surprising ability of the …

We propose a non-stationary iterated network Tikhonov (iNETT) method for the solution of ill-
posed inverse problems. The iNETT employs deep neural networks to build a data-driven …

Real-world adversarial attacks on machine learning models often feature an asymmetric
structure wherein adversaries only attempt to induce false negatives (eg, classify a spam …

Two-party computation (2PC) is promising to enable privacy-preserving deep learning (DL).
However, the 2PC-based privacy-preserving DL implementation comes with high …

Mesh degeneration is a bottleneck for fluid–structure interaction (FSI) simulations and for
shape optimization via the method of map**s. In both cases, an appropriate mesh motion …