中文
相关论文

相关论文: Improved Generalization Bounds of Group Invariant …

200 篇论文

Equivariant networks capture the inductive bias about the symmetry of the learning task by building those symmetries into the model. In this paper, we study how equivariance relates to generalization error utilizing PAC Bayesian analysis…

机器学习 · 计算机科学 2022-10-25 Arash Behboodi , Gabriele Cesa , Taco Cohen

Equivariant neural networks play a pivotal role in analyzing datasets with symmetry properties, particularly in complex data structures. However, integrating equivariance with Markov properties presents notable challenges due to the…

机器学习 · 统计学 2025-03-04 Hui Li , Zhiguo Wang , Bohui Chen , Li Sheng

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…

机器学习 · 计算机科学 2022-06-22 Rui Wang , Robin Walters , Rose Yu

Equivariance w.r.t. geometric transformations in neural networks improves data efficiency, parameter efficiency and robustness to out-of-domain perspective shifts. When equivariance is not designed into a neural network, the network can…

计算机视觉与模式识别 · 计算机科学 2023-04-10 Robert-Jan Bruintjes , Tomasz Motyka , Jan van Gemert

Although equivariant machine learning has proven effective at many tasks, success depends heavily on the assumption that the ground truth function is symmetric over the entire domain matching the symmetry in an equivariant neural network. A…

机器学习 · 计算机科学 2023-10-31 Dian Wang , Xupeng Zhu , Jung Yeon Park , Mingxi Jia , Guanang Su , Robert Platt , Robin Walters

Recent research has used margin theory to analyze the generalization performance for deep neural networks (DNNs). The existed results are almost based on the spectrally-normalized minimum margin. However, optimizing the minimum margin…

机器学习 · 计算机科学 2024-07-10 Shen-Huan Lyu , Lu Wang , Zhi-Hua Zhou

Quantum neural network architectures that have little-to-no inductive biases are known to face trainability and generalization issues. Inspired by a similar problem, recent breakthroughs in machine learning address this challenge by…

Incorporating group symmetries via equivariance into neural networks has emerged as a robust approach for overcoming the efficiency and data demands of modern deep learning. While most existing approaches, such as group convolutions and…

Universality results for equivariant neural networks remain rare. Those that do exist typically hold only in restrictive settings: either they rely on regular or higher-order tensor representations, leading to impractically high-dimensional…

机器学习 · 统计学 2025-10-20 Marco Pacini , Mircea Petrache , Bruno Lepri , Shubhendu Trivedi , Robin Walters

Using deep neural networks that are either invariant or equivariant to permutations in order to learn functions on unordered sets has become prevalent. The most popular, basic models are DeepSets [Zaheer et al. 2017] and PointNet [Qi et al.…

机器学习 · 计算机科学 2020-01-27 Nimrod Segol , Yaron Lipman

It is often said that a deep learning model is "invariant" to some specific type of transformation. However, what is meant by this statement strongly depends on the context in which it is made. In this paper we explore the nature of…

机器学习 · 计算机科学 2022-10-11 Henry Kvinge , Tegan H. Emerson , Grayson Jorgenson , Scott Vasquez , Timothy Doster , Jesse D. Lew

Machine learning models that are developed with invariance to certain types of data transformations have demonstrated superior generalization performance in practice. However, the underlying mechanism that explains why invariance leads to…

机器学习 · 计算机科学 2023-02-24 Sicheng Zhu , Bang An , Furong Huang

Many real world data analysis problems exhibit invariant structure, and models that take advantage of this structure have shown impressive empirical performance, particularly in deep learning. While the literature contains a variety of…

机器学习 · 计算机科学 2020-05-04 Clare Lyle , Mark van der Wilk , Marta Kwiatkowska , Yarin Gal , Benjamin Bloem-Reddy

Invariant and equivariant networks have been successfully used for learning images, sets, point clouds, and graphs. A basic challenge in developing such networks is finding the maximal collection of invariant and equivariant linear layers.…

机器学习 · 计算机科学 2019-05-01 Haggai Maron , Heli Ben-Hamu , Nadav Shamir , Yaron Lipman

The accuracy of deep learning, i.e., deep neural networks, can be characterized by dividing the total error into three main types: approximation error, optimization error, and generalization error. Whereas there are some satisfactory…

机器学习 · 统计学 2021-11-03 Pengzhan Jin , Lu Lu , Yifa Tang , George Em Karniadakis

The explicit incorporation of task-specific inductive biases through symmetry has emerged as a general design precept in the development of high-performance machine learning models. For example, group equivariant neural networks have…

机器学习 · 计算机科学 2025-04-21 Mircea Petrache , Shubhendu Trivedi

We establish a margin based data dependent generalization error bound for a general family of deep neural networks in terms of the depth and width, as well as the Jacobian of the networks. Through introducing a new characterization of the…

机器学习 · 计算机科学 2019-07-05 Xingguo Li , Junwei Lu , Zhaoran Wang , Jarvis Haupt , Tuo Zhao

Data augmentation is one of the most widely used techniques to improve generalization in modern machine learning, often justified by its ability to promote invariance to label-irrelevant transformations. However, its theoretical role…

机器学习 · 计算机科学 2026-02-17 Abdelali Bouyahia , Frédéric LeBlanc , Mario Marchand

We address the problem of improving the performance and in particular the sample complexity of deep neural networks by enforcing and guaranteeing invariances to symmetry transformations rather than learning them from data. Group-equivariant…

机器学习 · 计算机科学 2023-03-06 Matthias Rath , Alexandru Paul Condurache

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…

数值分析 · 数学 2024-03-18 Matthias Beckmann , Nick Heilenkötter
‹ 上一页 1 2 3 10 下一页 ›