English
Related papers

Related papers: Proof of a perfect platonic representation hypothe…

200 papers

Neural networks are complex functions of both their inputs and parameters. Much prior work in deep learning theory analyzes the distribution of network outputs at a fixed a set of inputs (e.g. a training dataset) over random initializations…

Disordered Systems and Neural Networks · Physics 2025-04-08 Mike Winer , Boris Hanin

First Rosenblatt's theorem about omnipotence of shallow networks states that elementary perceptrons can solve any classification problem if there are no discrepancies in the training set. Minsky and Papert considered elementary perceptrons…

Machine Learning · Computer Science 2023-12-19 A. N. Kirdin , S. V. Sidorov , N. Y. Zolotykh

Deep neural networks have been used in various machine learning applications and achieved tremendous empirical successes. However, training deep neural networks is a challenging task. Many alternatives have been proposed in place of…

Machine Learning · Computer Science 2020-09-09 Yeonjong Shin

Machine learning is a rapidly advancing field with diverse applications across various domains. One prominent area of research is the utilization of deep learning techniques for solving partial differential equations(PDEs). In this work, we…

Numerical Analysis · Mathematics 2024-05-21 Yuling Jiao , Yanming Lai , Yang Wang

In this paper, we prove a conjecture published in 1989 and also partially address an open problem announced at the Conference on Learning Theory (COLT) 2015. With no unrealistic assumption, we first prove the following statements for the…

Machine Learning · Statistics 2016-12-30 Kenji Kawaguchi

Physics informed neural networks (PINNs) represent a very popular class of neural solvers for partial differential equations. In practice, one often employs stochastic gradient descent type algorithms to train the neural network. Therefore,…

Machine Learning · Computer Science 2025-09-01 Bangti Jin , Longjun Wu

It is well known that (stochastic) gradient descent has an implicit bias towards flat minima. In deep neural network training, this mechanism serves to screen out minima. However, the precise effect that this has on the trained network is…

Machine Learning · Computer Science 2020-08-11 Rotem Mulayoff , Tomer Michaeli

There currently exist two extreme viewpoints for neural network feature learning -- (i) Neural networks simply implement a kernel method (a la NTK) and hence no features are learned (ii) Neural networks can represent (and hence learn)…

Machine Learning · Computer Science 2024-04-09 Mahesh Lorik Yadav , Harish Guruprasad Ramaswamy , Chandrashekar Lakshminarayanan

Deep neural networks (DNN) have achieved remarkable success in various fields, including computer vision and natural language processing. However, training an effective DNN model still poses challenges. This paper aims to propose a method…

Machine Learning · Computer Science 2024-07-03 Hejie Ying , Mengmeng Song , Yaohong Tang , Shungen Xiao , Zimin Xiao

Graph representation learning has attracted much attention in supporting high quality candidate search at scale. Despite its effectiveness in learning embedding vectors for objects in the user-item interaction network, the computational…

Information Retrieval · Computer Science 2020-03-05 Qiaoyu Tan , Ninghao Liu , Xing Zhao , Hongxia Yang , Jingren Zhou , Xia Hu

Training deep neural networks with stochastic gradient descent (SGD) can often achieve zero training loss on real-world tasks although the optimization landscape is known to be highly non-convex. To understand the success of SGD for…

Machine Learning · Statistics 2020-06-15 Yiping Lu , Chao Ma , Yulong Lu , Jianfeng Lu , Lexing Ying

Stochastic gradient descent (SGD) is widely believed to perform implicit regularization when used to train deep neural networks, but the precise manner in which this occurs has thus far been elusive. We prove that SGD minimizes an average…

Machine Learning · Computer Science 2018-01-17 Pratik Chaudhari , Stefano Soatto

Understanding the relation between deep and shallow neural networks is extremely important for the theoretical study of deep learning. In this work, we discover an embedding principle in depth that loss landscape of an NN "contains" all…

Machine Learning · Computer Science 2025-04-15 Zhiwei Bai , Tao Luo , Zhi-Qin John Xu , Yaoyu Zhang

Using established principles from Statistics and Information Theory, we show that invariance to nuisance factors in a deep neural network is equivalent to information minimality of the learned representation, and that stacking layers and…

Machine Learning · Computer Science 2018-06-29 Alessandro Achille , Stefano Soatto

Real-world data frequently exhibit latent hierarchical structures, which can be naturally represented by hyperbolic geometry. Although recent hyperbolic neural networks have demonstrated promising results, many existing architectures remain…

Machine Learning · Computer Science 2026-03-02 Xianglong Shi , Ziheng Chen , Yunhan Jiang , Nicu Sebe

Neural networks with randomly generated hidden weights (RaNNs) have been extensively studied, both as a standalone learning method and as an initialization for fully trainable deep learning methods. In this work, we study RaNN expressivity…

Numerical Analysis · Mathematics 2026-05-26 Muhammed Ali Mehmood , Lukas Gonon

Recently, deep learning has achieved huge successes in many important applications. In our previous studies, we proposed quadratic/second-order neurons and deep quadratic neural networks. In a quadratic neuron, the inner product of a vector…

Machine Learning · Computer Science 2019-08-29 Fenglei Fan , Jinjun Xiong , Ge Wang

There is some theoretical evidence that deep neural networks with multiple hidden layers have a potential for more efficient representation of multidimensional mappings than shallow networks with a single hidden layer. The question is…

Machine Learning · Computer Science 2019-10-08 Bernhard Bermeitinger , Tomas Hrycej , Siegfried Handschuh

The Error Diffusion Learning Algorithm (EDLA) is a learning scheme that performs synaptically local weight updates driven by a single, globally defined error signal. Although originally proposed as an alternative to backpropagation, its…

Machine Learning · Computer Science 2026-03-31 Kazuhisa Fujita

Conventional computer vision models rely on very deep, feedforward networks processing whole images and trained offline with extensive labeled data. In contrast, biological vision relies on comparatively shallow, recurrent networks that…

Neural and Evolutionary Computing · Computer Science 2024-11-27 Osvaldo M Velarde , Lucas C Parra
‹ Prev 1 8 9 10 Next ›