Cover Image

To Augment or Not to Augment? Diagnosing Distributional Symmetry Breaking

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lawrence, Hannah, Hofgard, Elyssa, Portilheiro, Vasco, Chen, Yuxuan, Smidt, Tess, Walters, Robin
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Discovering Symmetry Breaking in Physical Systems with Relaxed Group Convolution
by: Wang, Rui, et al.
Published: (2023)

Relaxed Equivariant Graph Neural Networks
by: Hofgard, Elyssa, et al.
Published: (2024)

Implicit Augmentation from Distributional Symmetry in Turbulence Super-Resolution
by: Balla, Julia, et al.
Published: (2025)

Improving Equivariant Networks with Probabilistic Symmetry Breaking
by: Lawrence, Hannah, et al.
Published: (2025)

Equivariant Symmetry Breaking Sets
by: Xie, YuQing, et al.
Published: (2024)

A Tale of Two Symmetries: Exploring the Loss Landscape of Equivariant Models
by: Xie, YuQing, et al.
Published: (2025)

Symphony: Symmetry-Equivariant Point-Centered Spherical Harmonics for 3D Molecule Generation
by: Daigavane, Ameya, et al.
Published: (2023)

Symmetry-Breaking Augmentations for Ad Hoc Teamwork
by: Hammond, Ravi, et al.
Published: (2024)

Training a Foundation Model for Materials on a Budget
by: Koker, Teddy, et al.
Published: (2025)

Any-Subgroup Equivariant Networks via Symmetry Breaking
by: Goel, Abhinav, et al.
Published: (2026)

A Cosmic-Scale Benchmark for Symmetry-Preserving Data Processing
by: Balla, Julia, et al.
Published: (2024)

Symmetry in Neural Network Parameter Spaces
by: Zhao, Bo, et al.
Published: (2025)

Latent Space Symmetry Discovery
by: Yang, Jianke, et al.
Published: (2023)

Understanding Mode Connectivity via Parameter Space Symmetry
by: Zhao, Bo, et al.
Published: (2025)

Symmetry-Informed Governing Equation Discovery
by: Yang, Jianke, et al.
Published: (2024)

LieAugmenter: Equivariant Learning by Discovering Symmetries with Learnable Augmentations
by: Santos-Escriche, Eduardo, et al.
Published: (2025)

The Price of Freedom: Exploring Expressivity and Runtime Tradeoffs in Equivariant Tensor Products
by: Xie, YuQing, et al.
Published: (2025)

Asymptotically Fast Clebsch-Gordan Tensor Products with Vector Spherical Harmonics
by: Xie, YuQing, et al.
Published: (2026)

Improving Convergence and Generalization Using Parameter Symmetries
by: Zhao, Bo, et al.
Published: (2023)

PFT: Phonon Fine-tuning for Machine Learned Interatomic Potentials
by: Koker, Teddy, et al.
Published: (2026)

EquiformerV2: Improved Equivariant Transformer for Scaling to Higher-Degree Representations
by: Liao, Yi-Lun, et al.
Published: (2023)

AtlasD: Automatic Local Symmetry Discovery
by: Bhat, Manu, et al.
Published: (2025)

Turbulence teaches equivariance to neural networks
by: McConkey, Ryley, et al.
Published: (2026)

Generalizing Denoising to Non-Equilibrium Structures Improves Equivariant Force Fields
by: Liao, Yi-Lun, et al.
Published: (2024)

Discovering Symbolic Differential Equations with Symmetry Invariants
by: Yang, Jianke, et al.
Published: (2025)

Accelerating Protein Molecular Dynamics Simulation with DeepJump
by: Costa, Allan dos Santos, et al.
Published: (2025)

The Empirical Impact of Neural Parameter Symmetries, or Lack Thereof
by: Lim, Derek, et al.
Published: (2024)

Convergence Guarantees for Neural Network-Based Hamilton-Jacobi Reachability
by: Hofgard, William
Published: (2024)

Sensor-Specific Transformer (PatchTST) Ensembles with Test-Matched Augmentation
by: Chandankar, Pavankumar, et al.
Published: (2025)

RePCS: Diagnosing Data Memorization in LLM-Powered Retrieval-Augmented Generation
by: Anh, Le Vu, et al.
Published: (2025)

Symmetry-Guided Memory Augmentation for Efficient Locomotion Learning
by: Bao, Kaixi, et al.
Published: (2025)

Attention-stacked Generative Adversarial Network (AS-GAN)-empowered Sensor Data Augmentation for Online Monitoring of Manufacturing System
by: Li, Yuxuan, et al.
Published: (2023)

Breaking Symmetry Bottlenecks in GNN Readouts
by: Talhi, Mouad, et al.
Published: (2026)

Symmetry Breaking and Equivariant Neural Networks
by: Kaba, Sékou-Oumar, et al.
Published: (2023)

Breaking the Benchmark: Revealing LLM Bias via Minimal Contextual Augmentation
by: Miandoab, Kaveh Eskandari, et al.
Published: (2025)

Synthetic Data Generation for Augmenting Small Samples
by: Liu, Dan, et al.
Published: (2025)

Matching the Optimal Denoiser in Point Cloud Diffusion with (Improved) Rotational Alignment
by: Daigavane, Ameya, et al.
Published: (2025)

Symmetry-Breaking Descent for Invariant Cost Functionals
by: Osipov, Mikhail
Published: (2025)

AimTS: Augmented Series and Image Contrastive Learning for Time Series Classification
by: Chen, Yuxuan, et al.
Published: (2025)

Stochastic Monkeys at Play: Random Augmentations Cheaply Break LLM Safety Alignment
by: Vega, Jason, et al.
Published: (2024)