SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2602.17080 · 2026

Adam Improves Muon Adam Improves Muon: Adaptive Moment Estimation with Orthogonalized Momentum

Yuxuan Liu, Hayden Schaeffer, Minxin Zhang

arXiv · PDF · Open in the Atlas

Code that ran

1 of 4 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 0 failures of our instrument; 3 no recorded run), measured 2026-11-22; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2602.17080.json · badge: /api/ran/2602.17080.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
minxin-zhg/namo canonical (classifier label)
classifier basis: census
1 ran · 3 no recorded run
FunctionStatusWhere it lives
get_lr Ran
ran, honoured the contract we drafted
minxin-zhg/namo/src/nanogpt/train_save.py
code served (permissive licence) · get_code("082b9b518e204fc8")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned float, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import math

learning_rate = 0.0006
warmup_iters = 2000
lr_decay_iters = 600000
min_lr = 6e-05

def get_lr(it):
    if it < warmup_iters:
        return learning_rate * (it + 1) / (warmup_iters + 1)
    if it > lr_decay_iters:
        return min_lr
    decay_ratio = (it - warmup_iters) / (lr_decay_iters - warmup_iters)
    assert 0 <= decay_ratio <= 1
    coeff = 0.5 * (1.0 + math.cos(math.pi * decay_ratio))
    return min_lr + coeff * (learning_rate - min_lr)

# Test with various iteration values
ARGS = {
    "it": 1000
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_batch Not yet run
unverified (harvested, no recorded run)
minxin-zhg/namo/src/nanogpt/train_save.py
code served (permissive licence) · get_code("99dce1e215c51cd5")
How it ran

no invocation recorded.

zeropower_via_newtonschulz5 Not yet run
unverified (harvested, no recorded run)
minxin-zhg/namo/src/namo.py
code served (permissive licence) · get_code("c6cbb0406b3d2e05")
How it ran

no invocation recorded.

zeropower_via_svd Not yet run
unverified (harvested, no recorded run)
minxin-zhg/namo/src/namo.py
code served (permissive licence) · get_code("f4467e041c01f1d1")
How it ran

no invocation recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 0 later) and 2 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
zeropower_via_newtonschulz5 2 other papers
2 dated earlier
2411.16085 (2024-11)
Cautious Optimizers: Improving Training with One Line of Code
2512.07112 (2025-12)
FOAM: Blocked State Folding for Memory-Efficient LLM Training
get_batch 1 other paper
1 dated earlier
1910.00643 (2019-10)
SlowMo: Improving Communication-Efficient Distributed SGD with Slow Momentum

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Efficient stochastic optimization typically integrates an update direction that performs well in the deterministic regime with a mechanism adapting to stochastic perturbations. While Adam uses adaptive moment estimates to promote stability, Muon utilizes the weight layers' matrix structure via orthogonalized momentum, showing superior performance in large language model training. We propose a new optimizer and a diagonal extension, NAMO and NAMO-D, providing the first principled integration of orthogonalized momentum with norm-based Adam-type noise adaptation. NAMO scales orthogonalized momentum using a single adaptive stepsize, preserving orthogonality while improving upon Muon at negligible additional cost. NAMO-D instead right-multiplies orthogonalized momentum by a diagonal matrix with clamped entries. This design enables neuron-wise noise adaptation and aligns with the common near block-diagonal Hessian structure. Under standard assumptions, we establish optimal convergence rates for both algorithms in the deterministic setting and show that, in the stochastic setting, their convergence guarantees adapt to the noise level of stochastic gradients. Experiments on pretraining GPT-2 models demonstrate improved performance of both NAMO and NAMO-D compared to the AdamW and Muon baselines, with NAMO-D achieving further gains over NAMO via an additional clamping hyperparameter that balances the competing goals of maintaining a well-conditioned update direction and leveraging fine-grained noise adaptation.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2602.17080")
get_code_for_paper("2602.17080")
have("2602.17080")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2602.17080.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2602.17080.svg)](https://syntology.ai/paper/2602.17080)

Connect an agent — have() is free.