Document tensor-network noise learning#554
Open
vedika-saravanan wants to merge 3 commits into
Open
Conversation
vedika-saravanan
force-pushed
the
noise-learning-docs
branch
from
4cb3728 to
d111f9a
Compare
Adds Sphinx API narrative and decoder docs for noise-learning integration, split from the integration PR for focused review. Signed-off-by: vedika-saravanan <vsaravanan@nvidia.com>
vedika-saravanan
force-pushed
the
noise-learning-docs
branch
from
d111f9a to
9de9dbb
Compare
3 tasks
vedika-saravanan
added a commit
that referenced
this pull request
May 26, 2026
…526) ## Summary Productizes Nico's `NMOptimizer` into the TN decoder. Fits per-error noise probabilities by backpropagating through a torch-backed tensor-network contraction. > `oe_torch` / `oe_torch_compiled` contractors aren't included, unused by `NMOptimizer`. ## What's in it - `NMOptimizer` + `make_compiled_step`, exposed top-level via `from cudaq_qec import NMOptimizer` - Three execute modes (`codegen` / `unrolled` / `opt_einsum`); optional `torch.compile`; prior auto-clamping - Unit tests parameterised over `(cpu, cuda)` × execute modes, plus `test_forward_parity_with_tn_decoder` against the base TN decoder - Example (`tn_noise_learning.py`) runs in CI as the end-to-end LER gate ## Test plan - [x] `pytest libs/qec/python/tests/test_nm_optimizer.py -v` - [x] `pytest libs/qec/python/tests/test_tensor_network_decoder.py -v` - [x] `python3 docs/sphinx/examples/qec/python/tn_noise_learning.py` ## Follow-ups - cuTensorNet backend (currently forced to torch for autograd), unlocks larger code distances (d=5+ surface codes) - KPI on real partner noise data - Decoder-agnostic mixin (QLDPC) - Docs: [#554](#554) NVBug for new deps: https://nvbugspro.nvidia.com/bug/6177164 --------- Signed-off-by: vedika-saravanan <vsaravanan@nvidia.com>
Signed-off-by: vedika-saravanan <vsaravanan@nvidia.com>
vedika-saravanan
changed the title
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Description
This PR documents tensor-network noise learning with
NMOptimizer.Runtime / performance impact
N/A. Documentation-only change.
Self-review checklist
Please confirm each item before requesting review. Check
[x]or strikethrough and explain.
Before requesting review
Scope and size
(if so, an issue has been raised).
Tests
just when it is missing.
EXPECT_*/assertchecks areinsufficient for algorithmic correctness. N/A: docs-only.
Documentation
tracked.
Code style
snake_casevscamelCase) forthe area being modified.
Dependencies
OSRB tickets filed.