English
Related papers

Related papers: Proof of a perfect platonic representation hypothe…

200 papers

Graph neural networks (GNNs) have become a core paradigm for learning on relational data. In materials science, equivariant GNNs (EGNNs) have emerged as a compelling backbone for crystalline-structure prediction, owing to their ability to…

Machine Learning · Computer Science 2025-10-08 Yang Cao , Zhao Song , Jiahao Zhang , Jiale Zhao

There is mounting evidence of emergent phenomena in the capabilities of deep learning methods as we scale up datasets, model sizes, and training times. While there are some accounts of how these resources modulate statistical capacity, far…

Machine Learning · Computer Science 2023-01-18 Boaz Barak , Benjamin L. Edelman , Surbhi Goel , Sham Kakade , Eran Malach , Cyril Zhang

In the last decade, deep learning has become a major component of artificial intelligence. The workhorse of deep learning is the optimization of loss functions by stochastic gradient descent (SGD). Traditionally in deep learning, neural…

Machine Learning · Computer Science 2021-04-27 Benjamin Scellier

Both the Dictionary Learning (DL) and Convolutional Neural Networks (CNN) are powerful image representation learning systems based on different mechanisms and principles, however whether we can seamlessly integrate them to improve the…

Computer Vision and Pattern Recognition · Computer Science 2020-01-16 Zhao Zhang , Yulin Sun , Yang Wang , Zhengjun Zha , Shuicheng Yan , Meng Wang

In many image-related tasks, learning expressive and discriminative representations of images is essential, and deep learning has been studied for automating the learning of such representations. Some user-centric tasks, such as image…

Computer Vision and Pattern Recognition · Computer Science 2017-02-21 Chenyi Lei , Dong Liu , Weiping Li , Zheng-Jun Zha , Houqiang Li

In this paper, we introduces a Pseudo-Symplectic Neural Network (PSNN) for learning general Hamiltonian systems (both separable and non-separable) from data. To address the limitations of existing structure-preserving methods (e.g.,…

Numerical Analysis · Mathematics 2025-03-07 Xupeng Cheng , Lijin Wang , Yanzhao Cao , Chen Chen

A deep equilibrium model uses implicit layers, which are implicitly defined through an equilibrium point of an infinite sequence of computation. It avoids any explicit computation of the infinite sequence by finding an equilibrium point…

Machine Learning · Computer Science 2021-02-19 Kenji Kawaguchi

The paper presents a novel deep learning approach, which extracts latent information from trained Deep Neural Networks (DNNs) and derives concise representations that are analyzed in an effective, unified way for prediction purposes. It is…

Machine Learning · Computer Science 2020-09-22 D. Kollias , N. Bouas , Y. Vlaxos , V. Brillakis , M. Seferis , I. Kollia , L. Sukissian , J. Wingate , S. Kollias

Hyperbolic geometry has emerged as an effective latent space for representing complex networks, owing to its ability to capture hierarchical organization and heterogeneous connectivity patterns using low-dimensional embeddings. As a result,…

Machine Learning · Computer Science 2026-05-01 Sofía Pérez Casulo , Marcelo Fiori , Bernardo Marenco , Federico Larroca

In this paper, we theoretically prove that gradient descent can find a global minimum of non-convex optimization of all layers for nonlinear deep neural networks of sizes commonly encountered in practice. The theory developed in this paper…

Machine Learning · Statistics 2020-06-18 Kenji Kawaguchi , Jiaoyang Huang

The Strong Lottery Ticket Hypothesis (SLTH) states that randomly-initialised neural networks likely contain subnetworks that perform well without any training. Although unstructured pruning has been extensively studied in this context, its…

Machine Learning · Computer Science 2026-03-11 Arthur da Cunha , Francesco d'Amore , Emanuele Natale

Recent papers in the graph machine learning literature have introduced a number of approaches for hyperbolic representation learning. The asserted benefits are improved performance on a variety of graph tasks, node classification and link…

Machine Learning · Computer Science 2025-02-26 Isay Katsman , Anna Gilbert

In this paper, we present a novel deep learning approach, deeply-fused nets. The central idea of our approach is deep fusion, i.e., combine the intermediate representations of base networks, where the fused output serves as the input of the…

Computer Vision and Pattern Recognition · Computer Science 2016-05-26 Jingdong Wang , Zhen Wei , Ting Zhang , Wenjun Zeng

Representation learning on graphs has emerged as a powerful mechanism to automate feature vector generation for downstream machine learning tasks. The advances in representation on graphs have centered on both homogeneous and heterogeneous…

Machine Learning · Statistics 2020-11-23 Piotr Bielak , Kamil Tagowski , Maciej Falkiewicz , Tomasz Kajdanowicz , Nitesh V. Chawla

Deep unfolding networks have recently gained popularity in the context of solving imaging inverse problems. However, the computational and memory complexity of data-consistency layers within traditional deep unfolding networks scales with…

Image and Video Processing · Electrical Eng. & Systems 2021-06-04 Jiaming Liu , Yu Sun , Weijie Gan , Xiaojian Xu , Brendt Wohlberg , Ulugbek S. Kamilov

Deep neural networks progressively transform their inputs across multiple processing layers. What are the geometrical properties of the representations learned by these networks? Here we study the intrinsic dimensionality (ID) of…

Machine Learning · Computer Science 2019-10-29 Alessio Ansuini , Alessandro Laio , Jakob H. Macke , Davide Zoccolan

Despite their empirical success, pushing Transformer architectures to extreme depth often leads to a paradoxical failure: representations become increasingly redundant, lose rank, and ultimately collapse. Existing explanations largely…

Machine Learning · Computer Science 2026-01-16 Haoran Su , Chenyu You

Set representation has become ubiquitous in deep learning for modeling the inductive bias of neural networks that are insensitive to the input order. DeepSets is the most widely used neural network architecture for set representation. It…

Machine Learning · Computer Science 2024-03-08 Peihao Wang , Shenghao Yang , Shu Li , Zhangyang Wang , Pan Li

A burgeoning line of research leverages deep neural networks to approximate the solutions to high dimensional PDEs, opening lines of theoretical inquiry focused on explaining how it is that these models appear to evade the curse of…

Machine Learning · Computer Science 2023-03-28 Tanya Marwah , Zachary C. Lipton , Jianfeng Lu , Andrej Risteski

Recently, deep learning approaches with various network architectures have achieved significant performance improvement over existing iterative reconstruction methods in various imaging problems. However, it is still unclear why these deep…

Machine Learning · Statistics 2018-01-26 Jong Chul Ye , Yoseob Han , Eunju Cha