English
Related papers

Related papers: The Space Between: On Folding, Symmetries and Samp…

200 papers

Deep learning empirically achieves high performance in many applications, but its training dynamics has not been fully understood theoretically. In this paper, we explore theoretical analysis on training two-layer ReLU neural networks in a…

Machine Learning · Statistics 2021-06-30 Shunta Akiyama , Taiji Suzuki

Models trained on semantically related datasets and tasks exhibit comparable inter-sample relations within their latent spaces. We investigate in this study the aggregation of such latent spaces to create a unified space encompassing the…

Neural networks have to capture mathematical relationships in order to learn various tasks. They approximate these relations implicitly and therefore often do not generalize well. The recently proposed Neural Arithmetic Logic Unit (NALU) is…

Neural and Evolutionary Computing · Computer Science 2020-03-18 Daniel Schlör , Markus Ring , Andreas Hotho

This paper aims to understand the training solution, which is obtained by the back-propagation algorithm, of two-layer neural networks whose hidden layer is composed of the units with smooth activation functions, including the usual sigmoid…

Machine Learning · Computer Science 2025-07-22 Changcun Huang

This paper presents a novel framework for understanding trained ReLU networks as random, affine functions, where the randomness is induced by the distribution over the inputs. By characterizing the probability distribution of the network's…

Machine Learning · Computer Science 2025-03-31 Shreyas Chaudhari , José M. F. Moura

The "folding algorithm"\cite{fold1} is a matrix product state algorithm for simulating quantum systems that involves a spatial evolution of a matrix product state. Hence, the computational effort of this algorithm is controlled by the…

Quantum Physics · Physics 2015-03-18 M. B. Hastings , R. Mahajan

We can compare the expressiveness of neural networks that use rectified linear units (ReLUs) by the number of linear regions, which reflect the number of pieces of the piecewise linear functions modeled by such networks. However,…

Machine Learning · Computer Science 2019-12-17 Thiago Serra , Srikumar Ramalingam

A neural network with the widely-used ReLU activation has been shown to partition the sample space into many convex polytopes for prediction. However, the parameterized way a neural network and other machine learning models use to partition…

Machine Learning · Computer Science 2022-05-04 Dayang Wang , Feng-Lei Fan , Bo-Jian Hou , Hao Zhang , Zhen Jia , Boce Zhou , Rongjie Lai , Hengyong Yu , Fei Wang

Activation functions influence behavior and performance of DNNs. Nonlinear activation functions, like Rectified Linear Units (ReLU), Exponential Linear Units (ELU) and Scaled Exponential Linear Units (SELU), outperform the linear…

Neural and Evolutionary Computing · Computer Science 2019-02-05 Alberto Marchisio , Muhammad Abdullah Hanif , Semeen Rehman , Maurizio Martina , Muhammad Shafique

Despite the increasing prevalence of deep neural networks, their applicability in resource-constrained devices is limited due to their computational load. While modern devices exhibit a high level of parallelism, real-time latency is still…

Computer Vision and Pattern Recognition · Computer Science 2021-09-06 Amir Ben Dror , Niv Zehngut , Avraham Raviv , Evgeny Artyomov , Ran Vitek , Roy Jevnisek

Deep neural networks process data through a cascade of representations: input features, hidden activations, logits, and loss. While perturbations at the input, logit, and label levels have been systematically studied, the intermediate…

Machine Learning · Computer Science 2026-05-29 Hua Li

Recent papers on the theory of representation learning has shown the importance of a quantity called diversity when generalizing from a set of source tasks to a target task. Most of these papers assume that the function mapping shared…

Machine Learning · Statistics 2021-06-01 Ziping Xu , Ambuj Tewari

Covering numbers of (deep) ReLU networks have been used to characterize approximation-theoretic performance, to upper-bound prediction error in nonparametric regression, and to quantify classification capacity. These results rely on…

Machine Learning · Statistics 2026-03-04 Weigutian Ou , Helmut Bölcskei

Understanding implicit bias of gradient descent for generalization capability of ReLU networks has been an important research topic in machine learning research. Unfortunately, even for a single ReLU neuron trained with the square loss, it…

Machine Learning · Computer Science 2022-06-14 Sangmin Lee , Byeongsu Sim , Jong Chul Ye

Recent advances in theoretical Deep Learning have introduced geometric properties that occur during training, past the Interpolation Threshold -- where the training error reaches zero. We inquire into the phenomena coined Neural Collapse in…

Machine Learning · Computer Science 2022-06-14 Ido Ben-Shaul , Shai Dekel

Supervised contrastive loss (SCL) is a competitive and often superior alternative to the cross-entropy loss for classification. While prior studies have demonstrated that both losses yield symmetric training representations under balanced…

Machine Learning · Computer Science 2023-10-20 Ganesh Ramachandra Kini , Vala Vakilian , Tina Behnia , Jaidev Gill , Christos Thrampoulidis

We present empirical evidence that neural networks with ReLU and Absolute Value activations learn distance-based representations. We independently manipulate both distance and intensity properties of internal activations in trained models,…

Machine Learning · Computer Science 2024-11-28 Alan Oursland

Imitation learning enables robots to learn and replicate human behavior from training data. Recent advances in machine learning enable end-to-end learning approaches that directly process high-dimensional observation data, such as images.…

Robotics · Computer Science 2024-01-22 Koki Yamane , Sho Sakaino , Toshiaki Tsuji

The analysis of neural network training beyond their linearization regime remains an outstanding open question, even in the simplest setup of a single hidden-layer. The limit of infinitely wide networks provides an appealing route forward…

Machine Learning · Computer Science 2020-06-19 Jaume de Dios , Joan Bruna

In recent years, functional neural networks have been proposed and studied in order to approximate nonlinear continuous functionals defined on $L^p([-1, 1]^s)$ for integers $s\ge1$ and $1\le p<\infty$. However, their theoretical properties…

Machine Learning · Statistics 2023-04-11 Linhao Song , Jun Fan , Di-Rong Chen , Ding-Xuan Zhou