paper-with-me

Papers

On the Implicit Bias of Linear Equivariant Steerable Networks

2023-03-07 · NeurIPS 2023 11

We study the implicit bias of gradient flow on linear equivariant steerable networks in group-invariant binary classification. Our findings reveal that the parameterized predictor converges in direction to the unique group-invariant classifier with a maximum margin defined by the input group action. Under a unitary assumption on the input representation, we establish the equivalence between steerable networks and data augmentation. Furthermore, we demonstrate the improved margin and generalization bound of steerable networks over their non-invariant counterparts.

📄 PDF Abstract BibTeX arXiv:2303.04198

Code (0)

등록된 구현이 없습니다.

Tasks

Binary ClassificationData Augmentation

Similar Papers 제목 키워드 기반

Implicit Convolutional Kernels for Steerable CNNs

2022-12-12 · NeurIPS 2023 11 · Maksim Zhdanov, Nico Hoffmann, Gabriele Cesa

Steerable convolutional neural networks (CNNs) provide a general framework for building neural networks equivariant to translations and transformations of an origin-preserving group $G$, such as reflections and rotations…

Molecular Property PredictionPoint Cloud ClassificationProperty Prediction

Geometric and Physical Quantities Improve E(3) Equivariant Message Passing

2021-10-06 · ICLR 2022 4 · Johannes Brandstetter, Rob Hesselink, Elise van der Pol, Erik J Bekkers 외

Including covariant information, such as position, force, velocity or spin is important in many tasks in computational physics and chemistry. We introduce Steerable E(3) Equivariant Graph Neural Networks (SEGNNs) that ge…

Graph Property Prediction

3D Steerable CNNs: Learning Rotationally Equivariant Features in Volumetric Data

2018-07-06 · NeurIPS 2018 12 · Maurice Weiler, Mario Geiger, Max Welling, Wouter Boomsma 외

We present a convolutional network that is equivariant to rigid body motions. The model uses scalar-, vector-, and tensor fields over 3D Euclidean space to represent data, and equivariant convolutions to map between such…

General Classification

Steerable Equivariant Representation Learning

2023-02-22 · Sangnie Bhardwaj, Willie McClinton, Tongzhou Wang, Guillaume Lajoie 외

Pre-trained deep image representations are useful for post-training tasks such as classification through transfer learning, image retrieval, and object detection. Data augmentations are a crucial aspect of pre-training r…

Image Retrievalobject-detectionObject DetectionOut-of-Distribution Detection+3

Clifford-Steerable Convolutional Neural Networks

2024-02-22 · Maksim Zhdanov, David Ruhe, Maurice Weiler, Ana Lucic 외

We present Clifford-Steerable Convolutional Neural Networks (CS-CNNs), a novel class of $\mathrm{E}(p, q)$-equivariant CNNs. CS-CNNs process multivector fields on pseudo-Euclidean spaces $\mathbb{R}^{p,q}$. They cover, f…