paper-with-me

Papers

Data Augmentation vs. Equivariant Networks: A Theory of Generalization on Dynamics Forecasting

2022-06-19 · Rui Wang, Robin Walters, Rose Yu

Exploiting symmetry in dynamical systems is a powerful way to improve the generalization of deep learning. The model learns to be invariant to transformation and hence is more robust to distribution shift. Data augmentation and equivariant networks are two major approaches to injecting symmetry into learning. However, their exact role in improving generalization is not well understood. In this work, we derive the generalization bounds for data augmentation and equivariant networks, characterizing their effect on learning in a unified framework. Unlike most prior theories for the i.i.d. setting, we focus on non-stationary dynamics forecasting with complex temporal dependencies.

📄 PDF Abstract BibTeX arXiv:2206.09450

Code (0)

등록된 구현이 없습니다.

Tasks

Data AugmentationGeneralization Bounds

Similar Papers 제목 키워드 기반

Equivariant score-based generative models provably learn distributions with symmetries efficiently

2024-10-02 · Ziyu Chen, Markos A. Katsoulakis, Benjamin J. Zhang

Symmetry is ubiquitous in many real-world phenomena and tasks, such as physics, images, and molecular simulations. Empirical studies have demonstrated that incorporating symmetries into generative models can provide bett…

Data AugmentationGeneralization BoundsInductive Bias

Equivariant Data Augmentation for Generalization in Offline Reinforcement Learning

2023-09-14 · Cristina Pinneri, Sarah Bechtle, Markus Wulfmeier, Arunkumar Byravan 외

We present a novel approach to address the challenge of generalization in offline reinforcement learning (RL), where the agent learns from a fixed dataset without any additional interaction with the environment. Specific…

Data AugmentationOffline RLreinforcement-learningReinforcement Learning+1

Understanding the Role of Equivariance in Self-supervised Learning

2024-11-10 · Yifei Wang, Kaiwen Hu, Sharut Gupta, Ziyu Ye 외

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 features (\eg colors) by being invariant to data augmentations. Gi…

Contrastive LearningSelf-Supervised Learning

Equivariant Neural Tangent Kernels

2024-06-10 · Philipp Misof, Pan Kessel, Jan E. Gerken

Little is known about the training dynamics of equivariant neural networks, in particular how it compares to data augmented training of their non-equivariant counterparts. Recently, neural tangent kernels (NTKs) have eme…

Data Augmentationimage-classificationImage ClassificationMedical Image Analysis+1

SE(3)-Equivariant Robot Learning and Control: A Tutorial Survey

2025-03-12 · Joohwan Seo, Soochul Yoo, Junwoo Chang, Hyunseok An 외

Recent advances in deep learning and Transformers have driven major breakthroughs in robotics by employing techniques such as imitation learning, reinforcement learning, and LLM-based multimodal perception and decision-m…

Data AugmentationDeep LearningImitation Learning