equivariance - Robuta Search

https://openreview.net/forum?id=UcrVnXBdZI On the effectiveness of Rotation-Equivariance in U-Net: A Benchmark for Image Segmentation |... Numerous studies have recently focused on incorporating different variations of equivariance in Convolutional Neural Networks (CNNs). In particular,... https://arxiv.org/abs/2111.10042 [2111.10042] Functional equivariance and conservation laws in numerical integration Abstract page for arXiv paper 2111.10042: Functional equivariance and conservation laws in numerical integration conservation laws 2111 10042 functional equivariance https://openreview.net/forum?id=yLpuruMZHE Understanding the Role of Equivariance in Self-supervised Learning | OpenReview Contrastive learning has been a leading paradigm for self-supervised learning, but it is widely observed that it comes at the price of sacrificing useful... self supervised learning the role understanding equivariance openreview https://slides.com/mariogeiger/why-equivariance-is-so-popular-in-life-and-material-science Why equivariance is so popular in Life and Material Science? A presentation created with Slides. in life equivariance popular material science https://openreview.net/forum?id=wpzRkAW2Sy Group Equivariance Meets Mechanistic Interpretability: Equivariant Sparse Autoencoders | OpenReview Sparse autoencoders (SAEs) have proven useful in disentangling the opaque activations of neural networks, primarily large language models, into sets of... mechanistic interpretability group equivariance meets equivariant https://arxiv.org/abs/2502.05169 [2502.05169] Flopping for FLOPs: Leveraging equivariance for computational efficiency Abstract page for arXiv paper 2502.05169: Flopping for FLOPs: Leveraging equivariance for computational efficiency 2502 05169 flopping flops leveraging https://openreview.net/forum?id=WajJf47TUi Graph Neural PDE Solvers with Conservation and Similarity-Equivariance | OpenReview Utilizing machine learning to address partial differential equations (PDEs) presents significant challenges due to the diversity of spatial domains and their... graph neural pde solvers conservation https://arxiv.org/abs/1312.5910v2 [1312.5910v2] Operads with general groups of equivariance, and some 2-categorical aspects of... Abstract page for arXiv paper 1312.5910v2: Operads with general groups of equivariance, and some 2-categorical aspects of operads in Cat https://arxiv.org/abs/2112.12493 [2112.12493] Equivariance and generalization in neural networks Abstract page for arXiv paper 2112.12493: Equivariance and generalization in neural networks 2112 12493 equivariance generalization neural https://openreview.net/forum?id=z5bJ44Brc4 Drawback of Enforcing Equivariance and its Compensation via the Lens of Expressive Power |... Equivariant neural networks encode the intrinsic symmetry of data as an inductive bias, which has achieved impressive performance in wide domains. However, the... https://openreview.net/forum?id=Foq9bVEnih Using and Abusing Equivariance | OpenReview In this paper we show how Group Equivariant Convolutional Neural Networks use subsampling to learn to break equivariance to their symmetries. We focus on 2D... using equivariance openreview https://openreview.net/forum?id=cftKAMCl2h Evaluating Machine Learning Models with NERO: Non-Equivariance Revealed on Orbits | OpenReview Traditional scalar-based error metrics, while quick for assessing machine learning (ML) model performance, often fail to expose weaknesses or offer fair... machine learning models https://openreview.net/forum?id=iIWeyfGTof&referrer=%5Bthe%20profile%20of%20Johann%20Brehmer%5D(%2Fprofile%3Fid%3D~Johann_Brehmer1) Does equivariance matter at scale? | OpenReview Given large data sets and sufficient compute, is it beneficial to design neural architectures for the structure and symmetries of each problem? Or is it more... at scale equivariance matter openreview https://openreview.net/forum?id=NJENsJ37sQ Empowering Networks With Scale and Rotation Equivariance Using A Similarity Convolution | OpenReview The translational equivariant nature of Convolutional Neural Networks (CNNs) is a reason for its great success in computer vision. However, networks do not... with scale https://arxiv.org/abs/2601.13913 [2601.13913] On the Role of Rotation Equivariance in Monocular 3D Human Pose Estimation Abstract page for arXiv paper 2601.13913: On the Role of Rotation Equivariance in Monocular 3D Human Pose Estimation https://deepai.org/publication/self-supervised-wide-baseline-visual-servoing-via-3d-equivariance Self-supervised Wide Baseline Visual Servoing via 3D Equivariance | DeepAI Sep 12, 2022 - 09/12/22 - One of the challenging input settings for visual servoing is when the initial and goal camera views are far apart. Such settings a... self supervised visual servoing wide baseline via https://openreview.net/forum?id=YtQCoUtWQ9 Incorporating Arbitrary Matrix Group Equivariance into KANs | OpenReview Kolmogorov-Arnold Networks (KANs) have seen great success in scientific domains thanks to spline activation functions, becoming an alternative to Multi-Layer... matrix group incorporating arbitrary equivariance kans https://openreview.net/forum?id=a6rCdfABJXg Equivariance-aware Architectural Optimization of Neural Networks | OpenReview Towards architectural optimization over subgroups of equivariant neural networks, we present two mechanisms for approximate equivariance over subgroups and two... neural networks equivariance aware architectural optimization https://openreview.net/forum?id=2FMJtNDLeE A General Theory of Correct, Incorrect, and Extrinsic Equivariance | OpenReview Although equivariant machine learning has proven effective at many tasks, success depends heavily on the assumption that the ground truth function is symmetric... general theory correct extrinsic equivariance openreview