Rethinking lipschitz neural networks and certified robustness: A boolean function perspective

B Zhang, D Jiang, D He… - Advances in neural …, 2022 - proceedings.neurips.cc
Designing neural networks with bounded Lipschitz constant is a promising way to obtain
certifiably robust classifiers against adversarial examples. However, the relevant progress …

fkan: Fractional kolmogorov-arnold networks with trainable jacobi basis functions

AA Aghaei - Neurocomputing, 2025 - Elsevier
Recent advancements in neural network design have given rise to the development of
Kolmogorov-Arnold Networks (KANs), which enhance interpretability and precision of these …

[PDF][PDF] A neural-network-based convex regularizer for image reconstruction

A Goujon, S Neumayer, P Bohra… - arxiv preprint arxiv …, 2022 - researchgate.net
The emergence of deep-learning-based methods for solving inverse problems has enabled
a significant increase in reconstruction quality. Unfortunately, these new methods often lack …

Provably convergent plug-and-play quasi-Newton methods

HY Tan, S Mukherjee, J Tang, CB Schönlieb - SIAM Journal on Imaging …, 2024 - SIAM
Plug-and-Play (PnP) methods are a class of efficient iterative methods that aim to combine
data fidelity terms and deep denoisers using classical optimization algorithms, such as ISTA …

Compact: Approximating complex activation functions for secure computation

M Islam, SS Arora, R Chatterjee, P Rindal… - arxiv preprint arxiv …, 2023 - arxiv.org
Secure multi-party computation (MPC) techniques can be used to provide data privacy when
users query deep neural network (DNN) models hosted on a public cloud. State-of-the-art …