neural tangent kernel
E457875
The neural tangent kernel is a theoretical construct that characterizes the training dynamics and generalization of infinitely wide neural networks by relating gradient descent to kernel methods.
All labels observed (2)
| Label | Occurrences |
|---|---|
| neural tangent kernel canonical | 1 |
| “Neural Tangent Kernel: Convergence and Generalization in Neural Networks” | 1 |
How this entity was disambiguated
This entity first appeared as the object of triple T4651293 — resolving that mention is where its identity was fixed. The disambiguator weighed these candidate entities and picked the highlighted one (or “None”, minting a new entity). This is how homonymy is resolved: the same surface form can point to different entities.
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: neural tangent kernel Context triple: [tensor programs framework, relatedTo, neural tangent kernel]
-
A.
Gaussian process
A Gaussian process is a collection of random variables indexed by a set (often time or space) such that every finite subset has a joint multivariate normal distribution, widely used to model functions in probability theory and machine learning.
-
B.
Intriguing properties of neural networks
"Intriguing properties of neural networks" is a highly influential research paper that revealed surprising vulnerabilities and behaviors of deep neural networks, particularly their susceptibility to adversarial examples.
-
C.
Cameron–Martin theorem
The Cameron–Martin theorem is a fundamental result in probability theory and functional analysis that characterizes how Gaussian measures on infinite-dimensional spaces change under shifts by elements of a special Hilbert subspace (the Cameron–Martin space).
-
D.
Neural Turing Machines (contributions)
Neural Turing Machines (contributions) refers to Oriol Vinyals’s work on augmenting neural networks with differentiable external memory to enable algorithmic reasoning and sequence learning beyond traditional architectures.
-
E.
Adam: A Method for Stochastic Optimization
"Adam: A Method for Stochastic Optimization" is a highly influential machine learning paper that introduces the Adam optimizer, a widely used adaptive gradient-based optimization algorithm for training deep neural networks.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: neural tangent kernel Target entity description: The neural tangent kernel is a theoretical construct that characterizes the training dynamics and generalization of infinitely wide neural networks by relating gradient descent to kernel methods.
-
A.
Gaussian process
A Gaussian process is a collection of random variables indexed by a set (often time or space) such that every finite subset has a joint multivariate normal distribution, widely used to model functions in probability theory and machine learning.
-
B.
Intriguing properties of neural networks
"Intriguing properties of neural networks" is a highly influential research paper that revealed surprising vulnerabilities and behaviors of deep neural networks, particularly their susceptibility to adversarial examples.
-
C.
Cameron–Martin theorem
The Cameron–Martin theorem is a fundamental result in probability theory and functional analysis that characterizes how Gaussian measures on infinite-dimensional spaces change under shifts by elements of a special Hilbert subspace (the Cameron–Martin space).
-
D.
Neural Turing Machines (contributions)
Neural Turing Machines (contributions) refers to Oriol Vinyals’s work on augmenting neural networks with differentiable external memory to enable algorithmic reasoning and sequence learning beyond traditional architectures.
-
E.
Adam: A Method for Stochastic Optimization
"Adam: A Method for Stochastic Optimization" is a highly influential machine learning paper that introduces the Adam optimizer, a widely used adaptive gradient-based optimization algorithm for training deep neural networks.
- F. None of above. chosen
Statements (47)
| Predicate | Object |
|---|---|
| instanceOf |
kernel method
ⓘ
reproducing kernel ⓘ theoretical construct in machine learning ⓘ |
| appliesTo |
convolutional neural networks
ⓘ
fully connected neural networks ⓘ residual neural networks ⓘ |
| approximates | finite-width network training dynamics when width is large ⓘ |
| associatedWith |
gradient flow
ⓘ
infinite-width limit of neural networks ⓘ linearization of neural networks around initialization ⓘ |
| characterizes |
generalization of infinitely wide neural networks
ⓘ
training dynamics of infinitely wide neural networks ⓘ |
| contrastedWith |
feature-learning regime of neural networks
ⓘ
finite-width non-linear training dynamics ⓘ |
| definedIn |
“Neural Tangent Kernel: Convergence and Generalization in Neural Networks”
ⓘ
linked to:
neural tangent kernel
|
| dependsOn |
activation function
ⓘ
network architecture ⓘ parameter initialization distribution ⓘ |
| describes |
evolution of network outputs under gradient descent
ⓘ
function space dynamics of neural networks ⓘ |
| field |
deep learning theory
ⓘ
machine learning ⓘ statistical learning theory ⓘ |
| formalism | kernel defined by inner products of network parameter gradients with respect to inputs ⓘ |
| framework |
lazy training regime
ⓘ
linearized neural network training ⓘ |
| hasVariant |
convolutional neural tangent kernel
ⓘ
graph neural tangent kernel ⓘ neural tangent kernel for residual networks ⓘ |
| inspired |
subsequent work on feature learning beyond the NTK regime
ⓘ
subsequent work on wide-network generalization bounds ⓘ |
| introducedBy |
Arthur Jacot
ⓘ
Clément Hongler ⓘ Franck Gabriel ⓘ |
| mathematicallyRelatedTo |
Gaussian process limits of neural networks
ⓘ
linked to:
Gaussian process
kernel ridge regression ⓘ random feature models ⓘ |
| property |
induces a kernel regression predictor at convergence
ⓘ
is positive semi-definite ⓘ remains constant during training in the infinite-width limit ⓘ |
| publicationYear | 2018 ⓘ |
| relatesTo |
gradient descent
ⓘ
kernel methods ⓘ |
| usedFor |
analyzing convergence of training in overparameterized networks
ⓘ
analyzing generalization in overparameterized networks ⓘ connecting neural networks to kernel regression ⓘ studying wide-network limits ⓘ |
How these facts were elicited
The pipeline generated the facts above by prompting gpt-5.1 with this entity's name + description and the instruction below.
Instruction
You are a knowledge base construction expert. Given a subject entity and a description of it, return factual statements that you know for the subject as a JSON list of dictionaries(triples), where keys must be "subject", "predicate" and "object". The number of facts may be very high, between 25 to 50 or more, for very popular subjects. For less popular subjects, the number of facts can be very low, like 5 or 10. # Requirements - If you don't know the subject at all, return an empty list. - If the subject is not a named entity, return an empty list. - Include at least one triple where predicate is "instanceOf". - Do not get too wordy. - Separate several objects into multiple triples with one object.
Input
Subject: neural tangent kernel Description of subject: The neural tangent kernel is a theoretical construct that characterizes the training dynamics and generalization of infinitely wide neural networks by relating gradient descent to kernel methods.
Referenced by (2)
Full triples — surface form annotated when it differs from this entity's canonical label.
neural tangent kernel
→
definedIn
→
“Neural Tangent Kernel: Convergence and Generalization in Neural Networks”
ⓘ
linked to: neural tangent kernel