{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "4d21b2c4",
   "metadata": {},
   "source": [
    "# Diagnosing barren plateaus with PyQit\n",
    "\n",
    "A barren plateau is a flat gradient landscape. The optimizer gets no signal, so the model does not train.\n",
    "\n",
    "This notebook:\n",
    "- Diagnoses a deep model with `check_barren_plateau`.\n",
    "- Runs the same check as a pre-flight with `Trainer(check_bp=True)`."
   ]
  },
  {
   "cell_type": "code",
   "id": "25fcbcba",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2026-10-02T18:50:01.589651923Z",
     "start_time": "2026-10-02T18:50:00.244795247Z"
    }
   },
   "source": [
    "from sklearn.datasets import make_moons\n",
    "\n",
    "import pyqit\n",
    "from pyqit import DataModule, Trainer\n",
    "from pyqit.ansatzes import SELAnsatz, SimplifiedTwoDesignAnsatz\n",
    "from pyqit.core import AngleEmbedding\n",
    "from pyqit.models import VQCClassifier\n",
    "from pyqit.utils.diagnostic import check_barren_plateau\n",
    "\n",
    "# The backend picks the training loop. It is not the PennyLane device.\n",
    "pyqit.set_backend(\"pennylane\")"
   ],
   "outputs": [],
   "execution_count": 1
  },
  {
   "cell_type": "markdown",
   "id": "adfcdc16",
   "metadata": {},
   "source": [
    "### 1. Data\n",
    "\n",
    "- `make_moons`, 200 samples, nonlinear.\n",
    "- `normalize=\"minmax\"` scales to [0, 1].\n",
    "- `AngleEmbedding` prescaling multiplies by pi, giving [0, pi]."
   ]
  },
  {
   "cell_type": "code",
   "id": "8890756a",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2026-10-02T18:50:01.625421625Z",
     "start_time": "2026-10-02T18:50:01.596157265Z"
    }
   },
   "source": [
    "# Generate a toy dataset\n",
    "X, y = make_moons(n_samples=200, noise=0.1, random_state=42)\n",
    "# AngleEmbedding prescaling multiplies by pi in setup(), so minmax here\n",
    "# lands the circuit inputs in [0, pi].\n",
    "dm = DataModule(\n",
    "    X=X,\n",
    "    y=y,\n",
    "    normalize=\"minmax\",\n",
    "    batch_size=16,\n",
    "    split=(0.7, 0.15, 0.15),\n",
    "    seed=42,\n",
    ")"
   ],
   "outputs": [],
   "execution_count": 2
  },
  {
   "cell_type": "markdown",
   "id": "84dce0dd",
   "metadata": {},
   "source": [
    "### 2. Standalone diagnostic\n",
    "\n",
    "- 8 qubits, 15 layers.\n",
    "- Deep circuits at this width are likely to plateau (McClean et al.).\n",
    "- `check_barren_plateau` samples gradients at random weights, before any training."
   ]
  },
  {
   "cell_type": "code",
   "id": "d0f587e3",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2026-10-02T18:50:40.166006086Z",
     "start_time": "2026-10-02T18:50:01.660484431Z"
    }
   },
   "source": [
    "# Create an untrainable, deep VQC\n",
    "bad_model = VQCClassifier(\n",
    "    n_qubits=8, n_layers=15, n_classes=2, ansatz=SELAnsatz, encoder=AngleEmbedding\n",
    ")\n",
    "dm.setup()  # Prepare dataloaders (required for diagnostics)\n",
    "\n",
    "# Run the standalone diagnostic tool to check for barren plateaus\n",
    "result = check_barren_plateau(\n",
    "    model=bad_model,\n",
    "    datamodule_or_X=dm,\n",
    "    num_samples=100,  # 100 random weight initializations\n",
    "    plot=True,\n",
    ")\n",
    "\n",
    "print(result)"
   ],
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<Figure size 900x300 with 1 Axes>"
      ],
      "image/png": "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"
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [],
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"></pre>\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\u001B[3m           BP Diagnostic Result : \u001B[0m\u001B[1;3;31mBARREN PLATEAU\u001B[0m\u001B[3m            \u001B[0m\n",
      "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━┳━━━━━━━━━━━━━━━━┓\n",
      "┃\u001B[1;36m \u001B[0m\u001B[1;36mMetric / Layer             \u001B[0m\u001B[1;36m \u001B[0m┃\u001B[1;36m \u001B[0m\u001B[1;36m    Value\u001B[0m\u001B[1;36m \u001B[0m┃\u001B[1;36m \u001B[0m\u001B[1;36m        Status\u001B[0m\u001B[1;36m \u001B[0m┃\n",
      "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━╇━━━━━━━━━━━━━━━━┩\n",
      "│\u001B[1m \u001B[0m\u001B[1mQubits                     \u001B[0m\u001B[1m \u001B[0m│         8 │                │\n",
      "│\u001B[1m \u001B[0m\u001B[1mSamples                    \u001B[0m\u001B[1m \u001B[0m│       100 │                │\n",
      "│\u001B[1m \u001B[0m\u001B[1mCircuit Executions         \u001B[0m\u001B[1m \u001B[0m│       100 │                │\n",
      "│\u001B[1m \u001B[0m\u001B[1mDead Parameters            \u001B[0m\u001B[1m \u001B[0m│ 16 of 360 │       \u001B[2mExcluded\u001B[0m │\n",
      "│\u001B[1m \u001B[0m\u001B[1mExpected Variance          \u001B[0m\u001B[1m \u001B[0m│  9.77e-04 │       \u001B[2mBaseline\u001B[0m │\n",
      "│\u001B[1m \u001B[0m\u001B[1mQuantum Variance           \u001B[0m\u001B[1m \u001B[0m│  \u001B[31m4.90e-04\u001B[0m │ \u001B[1;31mBARREN PLATEAU\u001B[0m │\n",
      "├─────────────────────────────┼───────────┼────────────────┤\n",
      "│\u001B[1m \u001B[0m\u001B[1mLayer: main_circuit.weights\u001B[0m\u001B[1m \u001B[0m│    \u001B[31m0.502x\u001B[0m │      \u001B[1;31m← plateau\u001B[0m │\n",
      "└─────────────────────────────┴───────────┴────────────────┘\n"
     ]
    }
   ],
   "execution_count": 3
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Gradient variance sits well below the baseline, and the histogram collapses to zero.\n",
    "\n",
    "### 3. A shallow two-design at the same width\n",
    "\n",
    "- `SimplifiedTwoDesignAnsatz` is the circuit Cerezo et al. proved trainable with a local cost at shallow depth.\n",
    "- A binary `VQCClassifier` measures one wire, so the check compares against the local-cost floor `1 / 2**n_qubits`.\n",
    "- Same 8 qubits, 2 layers instead of 15."
   ],
   "id": "455ae1d185a70b58"
  },
  {
   "cell_type": "code",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2026-10-02T18:50:43.438278998Z",
     "start_time": "2026-10-02T18:50:40.175685647Z"
    }
   },
   "source": [
    "shallow_model = VQCClassifier(\n",
    "    n_qubits=8,\n",
    "    n_layers=2,\n",
    "    n_classes=2,\n",
    "    ansatz=SimplifiedTwoDesignAnsatz,\n",
    "    encoder=AngleEmbedding,\n",
    ")\n",
    "\n",
    "result = check_barren_plateau(model=shallow_model, datamodule_or_X=dm, num_samples=100)\n",
    "print(result)"
   ],
   "id": "8cbc561d72608e50",
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<Figure size 900x600 with 2 Axes>"
      ],
      "image/png": "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"
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [],
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"></pre>\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\u001B[3m                  BP Diagnostic Result : \u001B[0m\u001B[1;3;32mHEALTHY\u001B[0m\u001B[3m                   \u001B[0m\n",
      "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━┳━━━━━━━━━━┓\n",
      "┃\u001B[1;36m \u001B[0m\u001B[1;36mMetric / Layer                           \u001B[0m\u001B[1;36m \u001B[0m┃\u001B[1;36m \u001B[0m\u001B[1;36m   Value\u001B[0m\u001B[1;36m \u001B[0m┃\u001B[1;36m \u001B[0m\u001B[1;36m  Status\u001B[0m\u001B[1;36m \u001B[0m┃\n",
      "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━╇━━━━━━━━━━┩\n",
      "│\u001B[1m \u001B[0m\u001B[1mQubits                                   \u001B[0m\u001B[1m \u001B[0m│        8 │          │\n",
      "│\u001B[1m \u001B[0m\u001B[1mSamples                                  \u001B[0m\u001B[1m \u001B[0m│      100 │          │\n",
      "│\u001B[1m \u001B[0m\u001B[1mCircuit Executions                       \u001B[0m\u001B[1m \u001B[0m│      100 │          │\n",
      "│\u001B[1m \u001B[0m\u001B[1mDead Parameters                          \u001B[0m\u001B[1m \u001B[0m│ 27 of 36 │ \u001B[2mExcluded\u001B[0m │\n",
      "│\u001B[1m \u001B[0m\u001B[1mExpected Variance                        \u001B[0m\u001B[1m \u001B[0m│ 9.77e-04 │ \u001B[2mBaseline\u001B[0m │\n",
      "│\u001B[1m \u001B[0m\u001B[1mQuantum Variance                         \u001B[0m\u001B[1m \u001B[0m│ \u001B[32m2.62e-02\u001B[0m │  \u001B[1;32mHEALTHY\u001B[0m │\n",
      "├───────────────────────────────────────────┼──────────┼──────────┤\n",
      "│\u001B[1m \u001B[0m\u001B[1mLayer: main_circuit.initial_layer_weights\u001B[0m\u001B[1m \u001B[0m│  \u001B[32m21.790x\u001B[0m │  \u001B[32mHealthy\u001B[0m │\n",
      "│\u001B[1m \u001B[0m\u001B[1mLayer: main_circuit.weights              \u001B[0m\u001B[1m \u001B[0m│  \u001B[32m31.768x\u001B[0m │  \u001B[32mHealthy\u001B[0m │\n",
      "└───────────────────────────────────────────┴──────────┴──────────┘\n"
     ]
    }
   ],
   "execution_count": 4
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": "The variance clears the floor: depth, not width, is what flattened the first circuit.\n\n### 4. Integrated diagnostic\n\n- The same 8-qubit, 2-layer two-design, on the torch backend.\n- `Trainer(check_bp=True)` runs the check before epoch 1.\n- `bp_samples` sets the number of gradient samples.",
   "id": "79f007f90ee545fa"
  },
  {
   "cell_type": "code",
   "id": "0f82e823",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2026-10-02T18:50:43.464920803Z",
     "start_time": "2026-10-02T18:50:43.448700310Z"
    }
   },
   "source": [
    "pyqit.set_backend(\"torch\")  # Trying a different backend for the \"good\" model\n",
    "dm_new = DataModule(\n",
    "    X=X,\n",
    "    y=y,\n",
    "    normalize=\"minmax\",\n",
    "    batch_size=16,\n",
    "    split=(0.7, 0.15, 0.15),\n",
    "    seed=42,\n",
    ")"
   ],
   "outputs": [],
   "execution_count": 5
  },
  {
   "cell_type": "code",
   "id": "5da9fa79",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2026-10-02T18:50:47.413953155Z",
     "start_time": "2026-10-02T18:50:43.470250171Z"
    }
   },
   "source": "# Create a healthy, shallow VQC\ngood_model = VQCClassifier(\n    n_qubits=8,\n    n_layers=2,\n    n_classes=2,\n    ansatz=SimplifiedTwoDesignAnsatz,\n    encoder=AngleEmbedding,\n)\n\n# Initialize the Trainer with the check enabled\ntrainer = Trainer(\n    max_epochs=5,\n    learning_rate=0.05,\n    check_bp=True,  # Automated Barren Plateau check!\n    bp_samples=100,\n    verbose=1,  # Set to 1 to see the rich tables\n)\n\n# Fit the model\n# The trainer will automatically print the diagnostic table before Epoch 1 begins.\nhistory = trainer.fit(good_model, datamodule=dm_new)",
   "outputs": [
    {
     "data": {
      "text/plain": [
       "\u001B[1;36m[\u001B[0m\u001B[1;36mTrainer\u001B[0m\u001B[1;36m]\u001B[0m Starting \u001B[32mtorch\u001B[0m backend | \u001B[1;36m5\u001B[0m epochs | \u001B[33mlr\u001B[0m=\u001B[1;36m0\u001B[0m\u001B[1;36m.05\u001B[0m\n",
       "\n"
      ],
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">[Trainer]</span> Starting <span style=\"color: #008000; text-decoration-color: #008000\">torch</span> backend | <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">5</span> epochs | <span style=\"color: #808000; text-decoration-color: #808000\">lr</span>=<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">0.05</span>\n",
       "\n",
       "</pre>\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [],
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"></pre>\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "Output()"
      ],
      "application/vnd.jupyter.widget-view+json": {
       "version_major": 2,
       "version_minor": 0,
       "model_id": "ac40b76fef394d86b061391daa422340"
      }
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "/home/aryan/PyQit/.venv/lib/python3.12/site-packages/lightning/pytorch/utilities/_pytree.py:21: \n",
       "`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` \n",
       "instead.\n"
      ],
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">/home/aryan/PyQit/.venv/lib/python3.12/site-packages/lightning/pytorch/utilities/_pytree.py:21: \n",
       "`isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` \n",
       "instead.\n",
       "</pre>\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "/home/aryan/PyQit/.venv/lib/python3.12/site-packages/lightning/pytorch/trainer/connectors/data_connector.py:434: \n",
       "The 'val_dataloader' does not have many workers which may be a bottleneck. Consider increasing the value of the \n",
       "`num_workers` argument` to `num_workers=15` in the `DataLoader` to improve performance.\n"
      ],
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">/home/aryan/PyQit/.venv/lib/python3.12/site-packages/lightning/pytorch/trainer/connectors/data_connector.py:434: \n",
       "The 'val_dataloader' does not have many workers which may be a bottleneck. Consider increasing the value of the \n",
       "`num_workers` argument` to `num_workers=15` in the `DataLoader` to improve performance.\n",
       "</pre>\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "/home/aryan/PyQit/.venv/lib/python3.12/site-packages/lightning/pytorch/trainer/connectors/data_connector.py:434: \n",
       "The 'train_dataloader' does not have many workers which may be a bottleneck. Consider increasing the value of the \n",
       "`num_workers` argument` to `num_workers=15` in the `DataLoader` to improve performance.\n"
      ],
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">/home/aryan/PyQit/.venv/lib/python3.12/site-packages/lightning/pytorch/trainer/connectors/data_connector.py:434: \n",
       "The 'train_dataloader' does not have many workers which may be a bottleneck. Consider increasing the value of the \n",
       "`num_workers` argument` to `num_workers=15` in the `DataLoader` to improve performance.\n",
       "</pre>\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\u001B[3m                  BP Diagnostic Result : \u001B[0m\u001B[1;3;32mHEALTHY\u001B[0m\u001B[3m                   \u001B[0m\n",
      "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━┳━━━━━━━━━━┓\n",
      "┃\u001B[1;36m \u001B[0m\u001B[1;36mMetric / Layer                           \u001B[0m\u001B[1;36m \u001B[0m┃\u001B[1;36m \u001B[0m\u001B[1;36m   Value\u001B[0m\u001B[1;36m \u001B[0m┃\u001B[1;36m \u001B[0m\u001B[1;36m  Status\u001B[0m\u001B[1;36m \u001B[0m┃\n",
      "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━╇━━━━━━━━━━┩\n",
      "│\u001B[1m \u001B[0m\u001B[1mQubits                                   \u001B[0m\u001B[1m \u001B[0m│        8 │          │\n",
      "│\u001B[1m \u001B[0m\u001B[1mSamples                                  \u001B[0m\u001B[1m \u001B[0m│      100 │          │\n",
      "│\u001B[1m \u001B[0m\u001B[1mCircuit Executions                       \u001B[0m\u001B[1m \u001B[0m│      100 │          │\n",
      "│\u001B[1m \u001B[0m\u001B[1mDead Parameters                          \u001B[0m\u001B[1m \u001B[0m│ 27 of 36 │ \u001B[2mExcluded\u001B[0m │\n",
      "│\u001B[1m \u001B[0m\u001B[1mExpected Variance                        \u001B[0m\u001B[1m \u001B[0m│ 9.77e-04 │ \u001B[2mBaseline\u001B[0m │\n",
      "│\u001B[1m \u001B[0m\u001B[1mQuantum Variance                         \u001B[0m\u001B[1m \u001B[0m│ \u001B[32m1.12e-02\u001B[0m │  \u001B[1;32mHEALTHY\u001B[0m │\n",
      "├───────────────────────────────────────────┼──────────┼──────────┤\n",
      "│\u001B[1m \u001B[0m\u001B[1mLayer: main_circuit.initial_layer_weights\u001B[0m\u001B[1m \u001B[0m│   \u001B[32m4.648x\u001B[0m │  \u001B[32mHealthy\u001B[0m │\n",
      "│\u001B[1m \u001B[0m\u001B[1mLayer: main_circuit.weights              \u001B[0m\u001B[1m \u001B[0m│  \u001B[32m18.276x\u001B[0m │  \u001B[32mHealthy\u001B[0m │\n",
      "└───────────────────────────────────────────┴──────────┴──────────┘\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/aryan/PyQit/.venv/lib/python3.12/site-packages/lightning/pytorch/trainer/setup.py:175: GPU available but not used. You can set it by doing `Trainer(accelerator='gpu')`.\n"
     ]
    },
    {
     "data": {
      "text/plain": [],
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"></pre>\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "\u001B[1;32m[\u001B[0m\u001B[1;32mTrainer\u001B[0m\u001B[1;32m]\u001B[0m Training complete.\n"
      ],
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">[Trainer]</span> Training complete.\n",
       "</pre>\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "execution_count": 6
  },
  {
   "cell_type": "code",
   "id": "0494b7d5",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2026-10-02T18:50:47.425658316Z",
     "start_time": "2026-10-02T18:50:47.416952522Z"
    }
   },
   "source": [],
   "outputs": [],
   "execution_count": 6
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": ".venv (3.12.3)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.12.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}