English
Related papers

Related papers: Relaxed Equivariance via Multitask Learning

200 papers

In robotic manipulation, acquiring samples is extremely expensive because it often requires interacting with the real world. Traditional image-level data augmentation has shown the potential to improve sample efficiency in various machine…

Robotics · Computer Science 2022-11-02 Mingxi Jia , Dian Wang , Guanang Su , David Klee , Xupeng Zhu , Robin Walters , Robert Platt

Numerical simulation is an essential tool in many areas of science and engineering, but its performance often limits application in practice or when used to explore large parameter spaces. On the other hand, surrogate deep learning models,…

Machine Learning · Computer Science 2022-05-18 Mario Lino , Stati Fotiadis , Anil A. Bharath , Chris Cantwell

Model agnostic meta-learning (MAML) is a popular state-of-the-art meta-learning algorithm that provides good weight initialization of a model given a variety of learning tasks. The model initialized by provided weight can be fine-tuned to…

Machine Learning · Computer Science 2021-06-11 Thanh Nguyen , Tung Luu , Trung Pham , Sanzhar Rakhimkul , Chang D. Yoo

Model-free reinforcement learning is a promising approach for autonomously solving challenging robotics control problems, but faces exploration difficulty without information of the robot's kinematics and dynamics morphology. The…

The requirement of generating predictions that exactly fulfill the fundamental symmetry of the corresponding physical quantities has profoundly shaped the development of machine-learning models for physical simulations. In many cases,…

Machine Learning · Computer Science 2026-03-27 Michelangelo Domina , Joseph William Abbott , Paolo Pegolo , Filippo Bigi , Michele Ceriotti

Building effective imitation learning methods that enable robots to learn from limited data and still generalize across diverse real-world environments is a long-standing problem in robot learning. We propose Equibot, a robust,…

Robotics · Computer Science 2024-10-30 Jingyun Yang , Zi-ang Cao , Congyue Deng , Rika Antonova , Shuran Song , Jeannette Bohg

Equivariance is a powerful inductive bias in neural networks, improving generalisation and physical consistency. Recently, however, non-equivariant models have regained attention, due to their better runtime performance and imperfect…

Machine Learning · Computer Science 2026-05-27 Torben Berndt , Jan Stühmer

Improving sampling efficiency and generalization capability is critical for the successful data-driven control of quadrotor unmanned aerial vehicles (UAVs) that are inherently unstable. While various reinforcement learning (RL) approaches…

Robotics · Computer Science 2025-03-03 Beomyeol Yu , Taeyoung Lee

Multi-task learning (MTL) has achieved great success in various research domains, such as CV, NLP and IR etc. Due to the complex and competing task correlation, naive training all tasks may lead to inequitable learning, i.e. some tasks are…

Machine Learning · Computer Science 2023-06-21 Jun Yuan , Rui Zhang

Recent attempts at introducing rotation invariance or equivariance in 3D deep learning approaches have shown promising results, but these methods still struggle to reach the performances of standard 3D neural networks. In this work we study…

Computer Vision and Pattern Recognition · Computer Science 2020-12-09 Hugues Thomas

Learning a shared policy that guides the locomotion of different agents is of core interest in Reinforcement Learning (RL), which leads to the study of morphology-agnostic RL. However, existing benchmarks are highly restrictive in the…

Machine Learning · Computer Science 2023-05-31 Runfa Chen , Jiaqi Han , Fuchun Sun , Wenbing Huang

Representation learning has been widely studied in the context of meta-learning, enabling rapid learning of new tasks through shared representations. Recent works such as MAML have explored using fine-tuning-based metrics, which measure the…

Machine Learning · Computer Science 2021-05-06 Kurtland Chua , Qi Lei , Jason D. Lee

Constrained robot motion planning is a widely used technique to solve complex robot tasks. We consider the problem of learning representations of constraints from demonstrations with a deep neural network, which we call Equality Constraint…

As representation learning becomes a powerful technique to reduce sample complexity in reinforcement learning (RL) in practice, theoretical understanding of its advantage is still limited. In this paper, we theoretically characterize the…

Machine Learning · Computer Science 2022-06-14 Yuan Cheng , Songtao Feng , Jing Yang , Hong Zhang , Yingbin Liang

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

Deep metric learning for vision is trained by optimizing a representation network to map (non-)matching image pairs to (non-)similar representations. During testing, which typically corresponds to image retrieval, both database and query…

Computer Vision and Pattern Recognition · Computer Science 2022-10-12 Pavel Suma , Giorgos Tolias

Incorporating inductive bias by embedding geometric entities (such as rays) as input has proven successful in multi-view learning. However, the methods adopting this technique typically lack equivariance, which is crucial for effective 3D…

Computer Vision and Pattern Recognition · Computer Science 2024-11-13 Yinshuang Xu , Dian Chen , Katherine Liu , Sergey Zakharov , Rares Ambrus , Kostas Daniilidis , Vitor Guizilini

This paper presents a deep relational metric learning (DRML) framework for image clustering and retrieval. Most existing deep metric learning methods learn an embedding space with a general objective of increasing interclass distances and…

Computer Vision and Pattern Recognition · Computer Science 2021-08-24 Wenzhao Zheng , Borui Zhang , Jiwen Lu , Jie Zhou

Multi-Agent Reinforcement Learning (MARL) struggles with sample inefficiency and poor generalization [1]. These challenges are partially due to a lack of structure or inductive bias in the neural networks typically used in learning the…

Machine Learning · Computer Science 2024-10-23 Joshua McClellan , Naveed Haghani , John Winder , Furong Huang , Pratap Tokekar

Convolutional networks are successful, but they have recently been outperformed by new neural networks that are equivariant under rotations and translations. These new networks work better because they do not struggle with learning each…

Computer Vision and Pattern Recognition · Computer Science 2021-02-16 Philip Müller , Vladimir Golkov , Valentina Tomassini , Daniel Cremers