CARVIEW |
Select Language
HTTP/2 200
date: Thu, 31 Jul 2025 11:41:20 GMT
content-type: text/html; charset=utf-8
vary: X-PJAX, X-PJAX-Container, Turbo-Visit, Turbo-Frame, X-Requested-With,Accept-Encoding, Accept, X-Requested-With
etag: W/"6e80155e9af81cb24bfef1a40572c62d"
cache-control: max-age=0, private, must-revalidate
strict-transport-security: max-age=31536000; includeSubdomains; preload
x-frame-options: deny
x-content-type-options: nosniff
x-xss-protection: 0
referrer-policy: no-referrer-when-downgrade
content-security-policy: default-src 'none'; base-uri 'self'; child-src github.githubassets.com github.com/assets-cdn/worker/ github.com/assets/ gist.github.com/assets-cdn/worker/; connect-src 'self' uploads.github.com www.githubstatus.com collector.github.com raw.githubusercontent.com api.github.com github-cloud.s3.amazonaws.com github-production-repository-file-5c1aeb.s3.amazonaws.com github-production-upload-manifest-file-7fdce7.s3.amazonaws.com github-production-user-asset-6210df.s3.amazonaws.com *.rel.tunnels.api.visualstudio.com wss://*.rel.tunnels.api.visualstudio.com objects-origin.githubusercontent.com copilot-proxy.githubusercontent.com proxy.individual.githubcopilot.com proxy.business.githubcopilot.com proxy.enterprise.githubcopilot.com *.actions.githubusercontent.com wss://*.actions.githubusercontent.com productionresultssa0.blob.core.windows.net/ productionresultssa1.blob.core.windows.net/ productionresultssa2.blob.core.windows.net/ productionresultssa3.blob.core.windows.net/ productionresultssa4.blob.core.windows.net/ productionresultssa5.blob.core.windows.net/ productionresultssa6.blob.core.windows.net/ productionresultssa7.blob.core.windows.net/ productionresultssa8.blob.core.windows.net/ productionresultssa9.blob.core.windows.net/ productionresultssa10.blob.core.windows.net/ productionresultssa11.blob.core.windows.net/ productionresultssa12.blob.core.windows.net/ productionresultssa13.blob.core.windows.net/ productionresultssa14.blob.core.windows.net/ productionresultssa15.blob.core.windows.net/ productionresultssa16.blob.core.windows.net/ productionresultssa17.blob.core.windows.net/ productionresultssa18.blob.core.windows.net/ productionresultssa19.blob.core.windows.net/ github-production-repository-image-32fea6.s3.amazonaws.com github-production-release-asset-2e65be.s3.amazonaws.com insights.github.com wss://alive.github.com wss://alive-staging.github.com api.githubcopilot.com api.individual.githubcopilot.com api.business.githubcopilot.com api.enterprise.githubcopilot.com; font-src github.githubassets.com; form-action 'self' github.com gist.github.com copilot-workspace.githubnext.com objects-origin.githubusercontent.com; frame-ancestors 'none'; frame-src viewscreen.githubusercontent.com notebooks.githubusercontent.com; img-src 'self' data: blob: github.githubassets.com media.githubusercontent.com camo.githubusercontent.com identicons.github.com avatars.githubusercontent.com private-avatars.githubusercontent.com github-cloud.s3.amazonaws.com objects.githubusercontent.com release-assets.githubusercontent.com secured-user-images.githubusercontent.com/ user-images.githubusercontent.com/ private-user-images.githubusercontent.com opengraph.githubassets.com copilotprodattachments.blob.core.windows.net/github-production-copilot-attachments/ github-production-user-asset-6210df.s3.amazonaws.com customer-stories-feed.github.com spotlights-feed.github.com objects-origin.githubusercontent.com *.githubusercontent.com; manifest-src 'self'; media-src github.com user-images.githubusercontent.com/ secured-user-images.githubusercontent.com/ private-user-images.githubusercontent.com github-production-user-asset-6210df.s3.amazonaws.com gist.github.com; script-src github.githubassets.com; style-src 'unsafe-inline' github.githubassets.com; upgrade-insecure-requests; worker-src github.githubassets.com github.com/assets-cdn/worker/ github.com/assets/ gist.github.com/assets-cdn/worker/
server: github.com
content-encoding: gzip
accept-ranges: bytes
set-cookie: _gh_sess=5Ybig3do2aETyG48WN3dR3ZsJIop3lW437HAWOAwATqF2MT1rC9KqK8bg9PPjGYZIZPeV5lO9LERqFOIx%2F1gS08hWW4gCcr7JKbaE4AJ4DNfhfCGswgLCEPMJpFLPWvIUjRhfYnilAhfs5oNOyVMb7Lg%2FGPk7IrY01IDaQDFcZeeu1ATehsu%2Fst1A3FjV1ceZut38Is1fL%2BV6yGZI7U%2BnI%2B3fd0AufCIGfYRVtbHVOPzbY7%2BXBFtz5HWlb2fK3OkollRODuW1fEqW7R9bArG7Q%3D%3D--23btLywGLrIZzRqB--GPBuZ9RblYPefXtOTuXFYg%3D%3D; Path=/; HttpOnly; Secure; SameSite=Lax
set-cookie: _octo=GH1.1.1669041295.1753962079; Path=/; Domain=github.com; Expires=Fri, 31 Jul 2026 11:41:19 GMT; Secure; SameSite=Lax
set-cookie: logged_in=no; Path=/; Domain=github.com; Expires=Fri, 31 Jul 2026 11:41:19 GMT; HttpOnly; Secure; SameSite=Lax
x-github-request-id: D688:373F91:65AAD3:715BD2:688B565F
Releases Β· google/neural-tangents Β· GitHub
11 Dec 14:10
Loading
25 Aug 00:01
Loading
11 Feb 00:45
Loading
14 Sep 04:58
Loading
18 Jul 19:09
Loading
23 Feb 16:58
Loading
17 Feb 00:57
Loading
17 Nov 06:35
Loading
07 Oct 00:14
Loading
23 Aug 23:15
Loading
Skip to content
Navigation Menu
{{ message }}
This repository was archived by the owner on May 6, 2025. It is now read-only.
-
Notifications
You must be signed in to change notification settings - Fork 232
Releases: google/neural-tangents
Releases Β· google/neural-tangents
v0.6.5
Compare
Maintenance release:
- refactoring and minor improvements
- Support and require
Assets 4
v0.6.4
Compare
Improvements:
- Support Python 3.11
- Use modern generic type annotations
- Various bugfixes, compatibility and documentation improvements
Breaking changes:
Assets 4
2 people reacted
v0.6.2
Compare
New features:
nt.stax.repeat
layer allowing fast compilation of very deep networks (see #168 and thanks @jglaser!)- Add a Colab notebook accompanying Precise Learning Curves and Higher-Order Scaling Limits for Dot Product Kernel Regression
Improvements:
Breaking changes:
Assets 4
v0.6.1
Compare
New features:
-
nt.stax
: -
nt.empirical
:- An efficient NTK-vector product function
nt.empirical_ntk_vp_fn
(without instantiating the NTK).
- An efficient NTK-vector product function
Improvements:
Assets 4
1 person reacted
v0.6.0
Compare
New features:
-
nt.empirical
:- New
implementation=3
fornt.empirical
, allowing to often speed-up or reduce the memory of the empirical NTK by orders of magnitude. Please see our ICML2022 paper Fast Finite Width Neural Tangent Kernel, new empirical NTK examples, and visit us on Thursday at ICML in-person! - New experimental prototype of using our empirical NTK implementations in Tensorflow via
nt.experimental.empirical_ntk_fn_tf
. - Make
nt.empircial
work with arbitrary pytrees.
- New
-
nt.stax
:
Improvements:
- Slightly lower memory usage in batching.
- Many improvements to documentation and type annotations.
- Simplify test specifications and avoid relying on JAX testing utilities.
Bugfixes:
Breaking changes:
Assets 4
1 person reacted
v0.5.0
Compare
Potentially breaking changes:
- Significant internal refactoring, notably splitting
stax
into multiple sub-modules, and moving implementations into an_src
folder. This could break your code if you use internal function likent.utils.typing
,nt.utils.utils
,nt.utils.Kernel
etc. (public API will remain unchanged). This should be easily fixed by updating the imports, e.g.nt.utils -> nt._src.utils
.
New features:
Assets 4
v0.4.0
Compare
WARNING:
Our next major release (v0.5.0) will include significant refactoring, and could break your code if you use internal function like nt.utils.typing
, nt.utils.utils
, nt.utils.Kernel
etc. (public API will remain unchanged). This should be easily fixed by updating the imports, e.g. nt.utils -> nt._src.utils
.
This release (v0.4.0):
New feature:
Improvements:
- Various internal refactoring and tighter tests.
Bugfixes:
- Fix values and gradients of non-differentiable
kernel_fn
at zero inputs to be consistent with finite-width kernels, and how JAX defines gradients of non-differentiable functions to be the mean sub-gradient, see also #123. - Fix wrong treatment of
b_std=None
in the infinite-width limit withparameterization='standard'
, see also #123. - Fix a bug in
nt.batch
whenx2 = None
and inputs are PyTrees.
Breaking changes:
- Bump requirements to
jax==0.3
andfrozendict==2.3
.
Assets 4
v0.3.9
Compare
Assets 4
v0.3.8
Compare
New Features:
stax.Elementwise
- a layer for generic elementwise functions requiring the user to specify only scalar-valuednngp_fn : (cov12, var1, var2) |-> E[fn(x_1) * fn(x_2)]
. The NTK computation (thanks to @SiuMath) and vectorization over the underlyingKernel
happen automatically under the hood. If you can't derive thenngp_fn
for your function, usestax.ElementwiseNumerical
. See docs for more details.
Bugfixes:
- Compatibility with JAX 0.2.21.
Full Changelog: v0.3.7...v0.3.8
Assets 4
v0.3.7
Compare
New Features:
nt.stax.Cos
nt.stax.ImageResize
- New implementation
implementation="SPARSE"
innt.stax.Aggregate
for efficient handling of sparse graphs (see #86, #9) - Support
approximate=True
innt.stax.Gelu
Bugfixes:
- Fix a bug that might alter
Kernel
requirements - Fix
nt.batch
handling ofdiagonal_axes
(see #87) - Remove the frequent but redundant warning about type conversion in
kernel_fn
- Minor fixes to documentation and code clean-up
Breaking changes:
Assets 4
1 person reacted
Previous Next
You canβt perform that action at this time.