mndopt
PyTorch implementation of the Matrix Normal Diagonal (MND) optimizer from A Statistical Viewpoint on Adam, Shampoo and Muon by Tetiana Parshakova, Robert M. Gower, and Paulo Orenstein (2026).
Requires Python 3.10+ and PyTorch 2.2+. Supports dense float32 and float64 parameters.
pip install mndopt
import torch
from mndopt import MND
model = torch.nn.Linear(8, 4)
optimizer = MND(model.parameters(), lr=0.003)
x, y = torch.randn(32, 8), torch.randn(32, 4)
optimizer.zero_grad()
loss = torch.nn.functional.mse_loss(model(x), y)
loss.backward()
optimizer.step()
Matrices use MND; other parameters use AdamW. Both use decoupled weight decay.
Train a small GPT on Tiny Shakespeare for 2,000 MND steps: notebook.
Licensed under Apache 2.0.
1 maintainer
Metadata
1 maintainer
Release files for mndopt 0.1.2
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| mndopt-0.1.2.tar.gz | 13.3 kB | Without provenance | Details for mndopt-0.1.2.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| mndopt-0.1.2-py3-none-any.whl | Python 3 | none | any | Details for mndopt-0.1.2-py3-none-any.whl |
Total release size: 21.6 kB
Release files / mndopt-0.1.2.tar.gz
| Download URL | mndopt-0.1.2.tar.gz |
|---|---|
| Size | 13.3 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
26c5efe0dca1f914c75d2452375db813c23268251899b3a819b05abbc4ea20a3
|
|
BLAKE2b-256 checksum How to use checksums |
a08bbe2abc7cc67fd93e3bce6458a41ef3dfd4ac59223d39f1ef9db3ac697240
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.9.25
|
Release files / mndopt-0.1.2-py3-none-any.whl
| Download URL | mndopt-0.1.2-py3-none-any.whl |
|---|---|
| Size | 8.2 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
1ed0eb90a751dd40b7774b2df414d9186a3e564d803e47c752c2adc008a9b293
|
|
BLAKE2b-256 checksum How to use checksums |
951c90487e6665b2f587e09d0f27ac09e032f71906d16086e8213bc88efef038
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.9.25
|
Security for mndopt 0.1.2
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.
