English
Related papers

Related papers: How the Optimizer Shapes Learned Solutions in Equi…

200 papers

Neural networks are trained by choosing an architecture and training the parameters. The choice of architecture is often by trial and error or with Neural Architecture Search (NAS) methods. While NAS provides some automation, it often…

Machine Learning · Computer Science 2024-10-14 Zitong Huang , Mansooreh Montazerin , Ajitesh Srivastava

(Non-)robustness of neural networks to small, adversarial pixel-wise perturbations, and as more recently shown, to even random spatial transformations (e.g., translations, rotations) entreats both theoretical and empirical understanding.…

Machine Learning · Computer Science 2021-11-11 Sandesh Kamath , Amit Deshpande , K V Subrahmanyam , Vineeth N Balasubramanian

Most current deep learning models equivariant to $O(n)$ or $SO(n)$ either consider mostly scalar information such as distances and angles or have a very high computational complexity. In this work, we test a few novel message passing graph…

Machine Learning · Computer Science 2024-07-11 Cong Liu , David Ruhe , Patrick Forré

In recent years, deep learning techniques have shown great success in various tasks related to inverse problems, where a target quantity of interest can only be observed through indirect measurements by a forward operator. Common approaches…

Numerical Analysis · Mathematics 2024-03-18 Matthias Beckmann , Nick Heilenkötter

Existing Neural Architecture Search (NAS) methods either encode neural architectures using discrete encodings that do not scale well, or adopt supervised learning-based methods to jointly learn architecture representations and optimize…

Computer Vision and Pattern Recognition · Computer Science 2020-10-27 Shen Yan , Yu Zheng , Wei Ao , Xiao Zeng , Mi Zhang

We construct and evaluate group-equivariant neural networks for the prediction of the two-dimensional $Q$-tensor order parameter of nematic liquid crystals from synthetically generated microscopic textures. Seven architectures, equivariant…

Soft Condensed Matter · Physics 2026-05-28 Julia Navarro , Mark Wilkinson

Equivariant networks have been adopted in many 3-D learning areas. Here we identify a fundamental limitation of these networks: their ambiguity to symmetries. Equivariant networks cannot complete symmetry-dependent tasks like segmenting a…

Computer Vision and Pattern Recognition · Computer Science 2022-11-01 Sidhika Balachandar , Adrien Poulenard , Congyue Deng , Leonidas Guibas

A novel comparison is presented of the effect of optimiser choice on the accuracy of physics-informed neural networks (PINNs). To give insight into why some optimisers are better, a new approach is proposed that tracks the training…

Machine Learning · Computer Science 2023-03-28 Nayara Fonseca , Veronica Guidetti , Will Trojak

We address the problem of determining correspondences between two images in agreement with a geometric model such as an affine or thin-plate spline transformation, and estimating its parameters. The contributions of this work are…

Computer Vision and Pattern Recognition · Computer Science 2017-04-17 Ignacio Rocco , Relja Arandjelović , Josef Sivic

Capsule networks are constrained by the parameter-expensive nature of their layers, and the general lack of provable equivariance guarantees. We present a variation of capsule networks that aims to remedy this. We identify that learning all…

Machine Learning · Computer Science 2019-09-27 Sairaam Venkatraman , S. Balasubramanian , R. Raghunatha Sarma

Equivariant models leverage prior knowledge on symmetries to improve predictive performance, but misspecified architectural constraints can harm it instead. While work has explored learning or relaxing constraints, selecting among…

Machine Learning · Computer Science 2025-07-16 Putri A. van der Linden , Alexander Timans , Dharmesh Tailor , Erik J. Bekkers

We present a genetic algorithm framework for automatically discovering deep learning optimization algorithms. Our approach encodes optimizers as genomes that specify combinations of primitive update terms (gradient, momentum, RMS…

Neural and Evolutionary Computing · Computer Science 2025-12-16 Mitchell Marfinetz

Muon, a recently proposed optimizer that leverages the inherent matrix structure of neural network parameters, has demonstrated strong empirical performance, indicating its potential as a successor to standard optimizers such as AdamW. This…

Machine Learning · Computer Science 2025-11-24 Naoki Sato , Hiroki Naganuma , Hideaki Iiduka

This paper introduces the Neural Differential Manifold (NDM), a novel neural network architecture that explicitly incorporates geometric structure into its fundamental design. Departing from conventional Euclidean parameter spaces, the NDM…

Machine Learning · Computer Science 2025-10-30 Di Zhang

While both shape and texture are fundamental to visual recognition, research on deep neural networks (DNNs) has predominantly focused on the latter, leaving their geometric understanding poorly probed. Here, we show: first, that optimized…

Computer Vision and Pattern Recognition · Computer Science 2025-11-10 Jian Wang , Yixing Yong , Haixia Bi , Lijun He , Fan Li

Soft, porous mechanical metamaterials exhibit pattern transformations that may have important applications in soft robotics, sound reduction and biomedicine. To design these innovative materials, it is important to be able to simulate them…

Soft Condensed Matter · Physics 2025-03-14 Fleur Hendriks , Vlado Menkovski , Martin Doškář , Marc G. D. Geers , Ondřej Rokoš

Equivariant networks are specifically designed to ensure consistent behavior with respect to a set of input transformations, leading to higher sample efficiency and more accurate and robust predictions. However, redesigning each component…

Machine Learning · Computer Science 2023-10-31 Arnab Kumar Mondal , Siba Smarak Panigrahi , Sékou-Oumar Kaba , Sai Rajeswar , Siamak Ravanbakhsh

Equivariant neural networks (ENNs) are graph neural networks embedded in $\mathbb{R}^3$ and are well suited for predicting molecular properties. The ENN library e3nn has customizable convolutions, which can be designed to depend only on…

Machine Learning · Computer Science 2020-11-25 Benjamin Kurt Miller , Mario Geiger , Tess E. Smidt , Frank Noé

Deep neural networks lack straightforward ways to incorporate domain knowledge and are notoriously considered black boxes. Prior works attempted to inject domain knowledge into architectures implicitly through data augmentation. Building on…

Machine Learning · Computer Science 2022-11-18 Emmanouil Theodosis , Demba Ba

Optimizing and certifying the positivity of polynomials are fundamental primitives across mathematics and engineering applications, from dynamical systems to operations research. However, solving these problems in practice requires large…

Machine Learning · Computer Science 2023-12-05 Hannah Lawrence , Mitchell Tong Harris
‹ Prev 1 8 9 10 Next ›