English
Related papers

Related papers: Interpolation, extrapolation, and local generaliza…

200 papers

A common assumption about neural networks is that they can learn an appropriate internal representations on their own, see e.g. end-to-end learning. In this work we challenge this assumption. We consider two simple tasks and show that the…

Machine Learning · Computer Science 2019-11-19 Krisztian Buza

Modern deep learning models employ considerably more parameters than required to fit the training data. Whereas conventional statistical wisdom suggests such models should drastically overfit, in practice these models generalize remarkably…

Machine Learning · Statistics 2020-08-18 Ben Adlam , Jeffrey Pennington

Linear interpolation between initial neural network parameters and converged parameters after training with stochastic gradient descent (SGD) typically leads to a monotonic decrease in the training objective. This Monotonic Linear…

Machine Learning · Computer Science 2021-04-26 James Lucas , Juhan Bae , Michael R. Zhang , Stanislav Fort , Richard Zemel , Roger Grosse

This paper addresses the problem of accurately estimating a function on one domain when only its discrete samples are available on another domain. To answer this challenge, we utilize a neural network, which we train to incorporate prior…

Machine Learning · Computer Science 2024-05-20 Guy Hay , Nir Sharon

This work investigates theoretically the interplay between interpolation and aggregation in regression. We establish that the $\gamma$-graph dimension characterizes learnability for a broad class of natural aggregation procedures.…

Machine Learning · Computer Science 2026-05-29 Mikael Møller Høgsgaard , Kasper Green Larsen , Liang-Yu Zou

In this paper, we investigate the geometric structure of activation spaces of fully connected layers in neural networks and then show applications of this study. We propose an efficient approximation algorithm to characterize the convex…

Machine Learning · Computer Science 2019-04-03 Yuting Jia , Haiwen Wang , Shuo Shao , Huan Long , Yunsong Zhou , Xinbing Wang

Modern computer vision is all about the possession of powerful image representations. Deeper and deeper convolutional neural networks have been built using larger and larger datasets and are made publicly available. A large swath of…

Machine Learning · Computer Science 2016-04-29 Ragav Venkatesan , Baoxin Li

With the recent success of deep neural networks in computer vision, it is important to understand the internal working of these networks. What does a given neuron represent? The concepts captured by a neuron may be hard to understand or…

Computer Vision and Pattern Recognition · Computer Science 2020-12-29 Suryabhan Singh Hada , Miguel Á. Carreira-Perpiñán

Deep learning has received considerable empirical successes in recent years. However, while many ad hoc tricks have been discovered by practitioners, until recently, there has been a lack of theoretical understanding for tricks invented in…

Machine Learning · Computer Science 2020-12-29 Cong Fang , Hanze Dong , Tong Zhang

A significant effort has been made to train neural networks that replicate algorithmic reasoning, but they often fail to learn the abstract concepts underlying these algorithms. This is evidenced by their inability to generalize to data…

Machine Learning · Computer Science 2020-10-26 Yujun Yan , Kevin Swersky , Danai Koutra , Parthasarathy Ranganathan , Milad Hashemi

The training of neural networks is usually monitored with a validation (holdout) set to estimate the generalization of the model. This is done instead of measuring intrinsic properties of the model to determine whether it is learning…

Machine Learning · Computer Science 2021-06-02 Asier Gutiérrez-Fandiño , David Pérez-Fernández , Jordi Armengol-Estapé , Marta Villegas

We study the generalization error of functions that interpolate prescribed data points and are selected by minimizing a weighted norm. Under natural and general conditions, we prove that both the interpolants and their generalization errors…

Numerical Analysis · Mathematics 2021-02-11 Weilin Li

The pretraining-finetuning paradigm has become the prevailing trend in modern deep learning. In this work, we discover an intriguing linear phenomenon in models that are initialized from a common pretrained checkpoint and finetuned on…

Machine Learning · Computer Science 2024-05-29 Zhanpeng Zhou , Zijun Chen , Yilan Chen , Bo Zhang , Junchi Yan

The primary objective of learning methods is generalization. Classic uniform generalization bounds, which rely on VC-dimension or Rademacher complexity, fail to explain the significant attribute that over-parameterized models in deep…

Machine Learning · Computer Science 2025-03-07 Lijia Yu , Yibo Miao , Yifan Zhu , Xiao-Shan Gao , Lijun Zhang

In the present paper, we consider one-hidden layer ANNs with a feedforward architecture, also referred to as shallow or two-layer networks, so that the structure is determined by the number and types of neurons. The determination of the…

In 2020 Domingos introduced an interpolation formula valid for "every model trained by gradient descent". He concluded that such models behave approximately as kernel machines. In this work, we extend the Domingos formula to stochastic…

Machine Learning · Computer Science 2026-03-17 Jin Guo , Roy Y. He , Jean-Michel Morel

Convolutional neural networks (CNN's) are powerful and widely used tools. However, their interpretability is far from ideal. One such shortcoming is the difficulty of deducing a network's ability to generalize to unseen data. We use…

Computer Vision and Pattern Recognition · Computer Science 2019-10-21 Rickard Brüel Gabrielsson , Gunnar Carlsson

Spatial autocorrelation and spatial heterogeneity widely exist in spatial data, which make the traditional machine learning model perform badly. Spatial domain generalization is a spatial extension of domain generalization, which can…

Machine Learning · Computer Science 2022-12-29 Dazhou Yu , Guangji Bai , Yun Li , Liang Zhao

Convolution Neural Networks, known as ConvNets exceptionally perform well in many complex machine learning tasks. The architecture of ConvNets demands the huge and rich amount of data and involves with a vast number of parameters that leads…

Computer Vision and Pattern Recognition · Computer Science 2017-12-14 Pushparaja Murugan , Shanmugasundaram Durairaj

Modern practice for training classification deepnets involves a Terminal Phase of Training (TPT), which begins at the epoch where training error first vanishes; During TPT, the training error stays effectively zero while training loss is…

Machine Learning · Computer Science 2020-09-23 Vardan Papyan , X. Y. Han , David L. Donoho