Skip to content

[QDP] Add SVHN IQP encoding benchmark with PennyLane baseline and QDP pipeline #1186

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
guan404ming merged 2 commits into from
Apr 6, 2026
Merged

[QDP] Add SVHN IQP encoding benchmark with PennyLane baseline and QDP pipeline #1186

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
2ccffa3
Update uv.lock: Adjust revision and package specifications
ryankert01 Mar 29, 2026
38ff210
fix: update QDP encoding method and synchronize CUDA device in SVHN I…
ryankert01 Mar 29, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
57 changes: 57 additions & 0 deletions qdp/qdp-python/benchmark/encoding_benchmarks/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -117,13 +117,70 @@ uv run python benchmark/encoding_benchmarks/qdp_pipeline/mnist_amplitude.py \
--digits "3,6" --n-samples 100 --trials 3 --iters 500 --early-stop 0
```

## SVHN IQP baseline (pure PennyLane)

Pipeline: 2-class SVHN (digit 1 vs 7) → PCA (3072 → n_qubits) → custom IQP circuit (H^n · Diag · H^n) → variational classifier.

```bash
uv run python benchmark/encoding_benchmarks/pennylane_baseline/svhn_iqp.py
```

Common flags (only the key ones):

- `--n-qubits`: number of qubits / PCA components (default: 10)
- `--n-samples`: total samples after binary filter + subsample (default: 500)
- `--iters`: optimizer steps (default: 500)
- `--batch-size`: batch size (default: 10)
- `--layers`: number of variational layers (default: 6)
- `--lr`: learning rate (default: 0.01)
- `--optimizer`: `adam` or `nesterov` (default: `adam`)
- `--trials`: number of restarts; best test accuracy reported (default: 3)
- `--early-stop`: stop when test accuracy >= this; 0 = off (default: 0.85)
- `--backend`: `cpu` (default.qubit) or `gpu` (lightning.gpu)

Example (quick test):

```bash
uv run python benchmark/encoding_benchmarks/pennylane_baseline/svhn_iqp.py \
--n-qubits 6 --n-samples 200 --iters 200 --trials 1 --early-stop 0 --backend cpu
```

## SVHN IQP (QDP pipeline)

Pipeline is identical to the baseline except for encoding:
PCA-reduced vectors → QDP `QdpEngine.encode(encoding_method="iqp")` (one-shot, GPU) → `StatePrep(state_vector)` → same variational classifier.

```bash
uv run python benchmark/encoding_benchmarks/qdp_pipeline/svhn_iqp.py
```

The CLI mirrors the baseline, plus:

> **Note:** The QDP pipeline always performs the encoding step on a CUDA GPU via QDP. A CUDA-capable device is required even when you select `--backend cpu` for the training backend.

- **QDP-specific flags**
- `--device-id`: CUDA device id (default: 0)

Comment thread
ryankert01 marked this conversation as resolved.
Example (same settings as the baseline example, but with QDP encoding):

```bash
uv run python benchmark/encoding_benchmarks/qdp_pipeline/svhn_iqp.py \
--n-qubits 6 --n-samples 200 --iters 200 --trials 1 --early-stop 0 --backend cpu
```

## SVHN IQP experiments

Experiment logs are saved to `benchmark/encoding_benchmarks/logs/`.

## Full help

To see the full list of options and defaults, append `--help`:

```bash
uv run python benchmark/encoding_benchmarks/pennylane_baseline/iris_amplitude.py --help
uv run python benchmark/encoding_benchmarks/pennylane_baseline/mnist_amplitude.py --help
uv run python benchmark/encoding_benchmarks/pennylane_baseline/svhn_iqp.py --help
uv run python benchmark/encoding_benchmarks/qdp_pipeline/iris_amplitude.py --help
uv run python benchmark/encoding_benchmarks/qdp_pipeline/mnist_amplitude.py --help
uv run python benchmark/encoding_benchmarks/qdp_pipeline/svhn_iqp.py --help
```
Loading
Loading