{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "intro",
   "metadata": {},
   "source": [
    "# Ansatz Comparison: PZ vs RPZ vs Real\n",
    "\n",
    "QKAN supports several quantum circuit ansatzes for its variational activation functions.\n",
    "Each ansatz defines a different circuit structure, affecting the parameter count,\n",
    "expressiveness, and training speed.\n",
    "\n",
    "## Ansatzes\n",
    "\n",
    "| Ansatz | Circuit | Params per layer | Data encoding |\n",
    "|--------|---------|-----------------|---------------|\n",
    "| `pz_encoding` | H -> [RZ(\\u03b8₀) -> RY(\\u03b8₁) -> RZ(x)]^reps -> RZ(\\u03b8) -> RY(\\u03b8) | 2 (RZ + RY) | RZ |\n",
    "| `rpz_encoding` | H -> [RY(\\u03b8) -> RZ(wx+b)]^reps -> RY(\\u03b8) | 2 (RY + RZ_encoded) | RZ(encoded) |\n",
    "| `real` | H -> [X -> RY(\\u03b8) -> Z -> RY(x)]^reps | 1 (RY only) | RY |\n",
    "\n",
    "**Key trade-offs:**\n",
    "- **pz_encoding** has the most variational parameters (2 per layer) and uses complex-valued gates\n",
    "- **rpz_encoding** (reduced pz) halves the variational parameters but always uses trainable data encoding (w\\u00b7x + b)\n",
    "- **real** uses only real-valued gates (no complex arithmetic), which can be faster on hardware\n",
    "\n",
    "We compare these ansatzes on CIFAR-100 using the HQKAN-44 architecture."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "imports",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Device: cuda\n"
     ]
    }
   ],
   "source": [
    "import time\n",
    "\n",
    "import numpy as np\n",
    "import torch\n",
    "import torch.nn as nn\n",
    "import torch.nn.functional as F\n",
    "import torch.optim as optim\n",
    "import torchvision\n",
    "import torchvision.transforms as transforms\n",
    "from torch.utils.data import DataLoader\n",
    "from tqdm import tqdm\n",
    "\n",
    "from qkan import QKAN\n",
    "\n",
    "device = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\n",
    "print(f\"Device: {device}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "cnet",
   "metadata": {},
   "outputs": [],
   "source": [
    "class CNet(nn.Module):\n",
    "    def __init__(self, device):\n",
    "        super(CNet, self).__init__()\n",
    "        self.device = device\n",
    "        self.cnn1 = nn.Conv2d(3, 32, kernel_size=3, device=device)\n",
    "        self.relu = nn.ReLU()\n",
    "        self.maxpool1 = nn.MaxPool2d(kernel_size=2, stride=2)\n",
    "        self.cnn2 = nn.Conv2d(32, 64, kernel_size=3, device=device)\n",
    "        self.maxpool2 = nn.MaxPool2d(kernel_size=2, stride=2)\n",
    "        self.cnn3 = nn.Conv2d(64, 64, kernel_size=3, device=device)\n",
    "        self.maxpool3 = nn.MaxPool2d(kernel_size=2, stride=2)\n",
    "\n",
    "    def forward(self, x):\n",
    "        x = x.to(self.device)\n",
    "        x = self.relu(self.cnn1(x))\n",
    "        x = self.maxpool1(x)\n",
    "        x = self.relu(self.cnn2(x))\n",
    "        x = self.maxpool2(x)\n",
    "        x = self.relu(self.cnn3(x))\n",
    "        x = self.maxpool3(x)\n",
    "        return x.flatten(start_dim=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "data",
   "metadata": {},
   "outputs": [],
   "source": [
    "transform = transforms.Compose(\n",
    "    [transforms.ToTensor(), transforms.Normalize((0.5,), (0.5,))]\n",
    ")\n",
    "trainset = torchvision.datasets.CIFAR100(\n",
    "    root=\"./data\", train=True, download=True, transform=transform\n",
    ")\n",
    "testset = torchvision.datasets.CIFAR100(\n",
    "    root=\"./data\", train=False, download=True, transform=transform\n",
    ")\n",
    "trainloader = DataLoader(trainset, batch_size=1000, shuffle=True)\n",
    "testloader = DataLoader(testset, batch_size=1000, shuffle=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "helpers",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "CNN backbone params: 56320\n",
      "HQKAN-44 shape: QKAN([32, 28])\n"
     ]
    }
   ],
   "source": [
    "in_feat = 2 * 2 * 64  # 256 (CNet output)\n",
    "out_feat = 100\n",
    "in_resize = int(np.ceil(np.log2(in_feat))) * 4  # 32\n",
    "out_resize = int(np.ceil(np.log2(out_feat))) * 4  # 28\n",
    "N_EPOCHS = 50\n",
    "criterion = nn.CrossEntropyLoss()\n",
    "\n",
    "cnn_param = sum(p.numel() for p in CNet(\"cpu\").parameters())\n",
    "print(f\"CNN backbone params: {cnn_param}\")\n",
    "print(f\"HQKAN-44 shape: QKAN([{in_resize}, {out_resize}])\")\n",
    "\n",
    "\n",
    "def train_and_eval(model, label):\n",
    "    \"\"\"Train for N_EPOCHS and return results dict.\"\"\"\n",
    "    optimizer = optim.Adam(model.parameters(), lr=1e-3)\n",
    "    best_top1, best_top5 = 0, 0\n",
    "    test_accs, test_top5_accs = [], []\n",
    "\n",
    "    t0 = time.time()\n",
    "    for epoch in range(N_EPOCHS):\n",
    "        model.train()\n",
    "        with tqdm(trainloader, desc=f\"{label} ep{epoch+1}\", leave=False) as pbar:\n",
    "            for images, labels in pbar:\n",
    "                optimizer.zero_grad()\n",
    "                output = model(images)\n",
    "                loss = criterion(output, labels.to(device))\n",
    "                loss.backward()\n",
    "                optimizer.step()\n",
    "                acc = (output.argmax(1) == labels.to(device)).float().mean()\n",
    "                pbar.set_postfix(loss=f\"{loss.item():.3f}\", acc=f\"{acc.item():.3f}\")\n",
    "\n",
    "        model.eval()\n",
    "        t_loss = t_acc = t_top5 = 0\n",
    "        with torch.no_grad():\n",
    "            for images, labels in testloader:\n",
    "                output = model(images)\n",
    "                t_loss += criterion(output, labels.to(device)).item()\n",
    "                t_acc += (output.argmax(1) == labels.to(device)).float().mean().item()\n",
    "                t_top5 += (\n",
    "                    (output.topk(5, 1).indices == labels.to(device).unsqueeze(1))\n",
    "                    .any(1)\n",
    "                    .float()\n",
    "                    .mean()\n",
    "                    .item()\n",
    "                )\n",
    "        t_loss /= len(testloader)\n",
    "        t_acc /= len(testloader)\n",
    "        t_top5 /= len(testloader)\n",
    "        test_accs.append(t_acc)\n",
    "        test_top5_accs.append(t_top5)\n",
    "\n",
    "        if (epoch + 1) % 10 == 0:\n",
    "            print(\n",
    "                f\"  [{label}] Epoch {epoch+1}: \"\n",
    "                f\"loss={t_loss:.3f} top1={t_acc:.1%} top5={t_top5:.1%}\"\n",
    "            )\n",
    "\n",
    "    elapsed = time.time() - t0\n",
    "    n_params = sum(p.numel() for p in model.parameters())\n",
    "    head_params = n_params - cnn_param\n",
    "\n",
    "    return {\n",
    "        \"label\": label,\n",
    "        \"n_params\": n_params,\n",
    "        \"head_params\": head_params,\n",
    "        \"top1\": max(test_accs),\n",
    "        \"top5\": max(test_top5_accs),\n",
    "        \"time_s\": elapsed,\n",
    "        \"test_accs\": test_accs,\n",
    "        \"test_top5_accs\": test_top5_accs,\n",
    "    }"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "pz-title",
   "metadata": {},
   "source": [
    "## PZ Encoding\n",
    "\n",
    "The default ansatz. Each repetition applies RZ(θ₀) → RY(θ₁) → RZ(x), giving 2 variational parameters per layer."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "pz",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "                                                                               \r"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "  [pz] Epoch 10: loss=3.335 top1=19.1% top5=47.0%\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "                                                                               \r"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "  [pz] Epoch 20: loss=2.875 top1=27.8% top5=58.9%\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "                                                                               \r"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "  [pz] Epoch 30: loss=2.691 top1=31.5% top5=62.9%\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "                                                                               \r"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "  [pz] Epoch 40: loss=2.608 top1=34.0% top5=64.5%\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "                                                                               \r"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "  [pz] Epoch 50: loss=2.576 top1=35.4% top5=65.8%\n"
     ]
    }
   ],
   "source": [
    "torch.manual_seed(42)\n",
    "model_pz = nn.Sequential(\n",
    "    CNet(device=device),\n",
    "    nn.Linear(in_feat, in_resize, device=device),\n",
    "    QKAN([in_resize, out_resize], device=device, ansatz=\"pz_encoding\", ba_trainable=True),\n",
    "    nn.Linear(out_resize, out_feat, device=device),\n",
    ")\n",
    "results_pz = train_and_eval(model_pz, \"pz\")\n",
    "del model_pz\n",
    "torch.cuda.empty_cache()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "rpz-title",
   "metadata": {},
   "source": [
    "## RPZ Encoding (Reduced PZ)\n",
    "\n",
    "Uses only RY(θ) per layer (no RZ(θ)), halving the variational parameters.\n",
    "Data is encoded via a trainable linear transform: RZ(w·x + b)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "rpz",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "rpz ep3:  66%|██████▌   | 33/50 [00:01<00:00, 22.97it/s, acc=0.116, loss=3.845]"
     ]
    }
   ],
   "source": [
    "torch.manual_seed(42)\n",
    "model_rpz = nn.Sequential(\n",
    "    CNet(device=device),\n",
    "    nn.Linear(in_feat, in_resize, device=device),\n",
    "    QKAN([in_resize, out_resize], device=device, ansatz=\"rpz_encoding\"),\n",
    "    nn.Linear(out_resize, out_feat, device=device),\n",
    ")\n",
    "results_rpz = train_and_eval(model_rpz, \"rpz\")\n",
    "del model_rpz\n",
    "torch.cuda.empty_cache()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "real-title",
   "metadata": {},
   "source": [
    "## Real Encoding\n",
    "\n",
    "Uses only real-valued gates (X, RY, Z) — no complex arithmetic.\n",
    "Data is encoded via RY(x). 1 variational parameter per layer."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "real",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "                                                                                 \r"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "  [real] Epoch 10: loss=3.039 top1=25.0% top5=54.6%\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "                                                                                 \r"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "  [real] Epoch 20: loss=2.771 top1=30.1% top5=60.8%\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "                                                                                 \r"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "  [real] Epoch 30: loss=2.616 top1=34.1% top5=64.8%\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "                                                                                 \r"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "  [real] Epoch 40: loss=2.590 top1=34.6% top5=65.4%\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "                                                                                 \r"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "  [real] Epoch 50: loss=2.552 top1=35.5% top5=66.7%\n"
     ]
    }
   ],
   "source": [
    "torch.manual_seed(42)\n",
    "model_real = nn.Sequential(\n",
    "    CNet(device=device),\n",
    "    nn.Linear(in_feat, in_resize, device=device),\n",
    "    QKAN([in_resize, out_resize], device=device, ansatz=\"real\", ba_trainable=True),\n",
    "    nn.Linear(out_resize, out_feat, device=device),\n",
    ")\n",
    "results_real = train_and_eval(model_real, \"real\")\n",
    "del model_real\n",
    "torch.cuda.empty_cache()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "mlp-title",
   "metadata": {},
   "source": [
    "## MLP Baseline\n",
    "\n",
    "Classical 3-layer MLP for comparison."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "mlp",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "                                                                                \r"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "  [mlp] Epoch 10: loss=3.083 top1=24.9% top5=53.0%\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "                                                                                \r"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "  [mlp] Epoch 20: loss=2.747 top1=31.7% top5=61.7%\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "                                                                                \r"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "  [mlp] Epoch 30: loss=2.600 top1=35.2% top5=65.0%\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "                                                                                \r"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "  [mlp] Epoch 40: loss=2.528 top1=37.0% top5=67.3%\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "                                                                                \r"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "  [mlp] Epoch 50: loss=2.511 top1=37.9% top5=67.9%\n"
     ]
    }
   ],
   "source": [
    "class CNN_MLP(nn.Module):\n",
    "    def __init__(self, device):\n",
    "        super().__init__()\n",
    "        self.cnet = CNet(device)\n",
    "        self.fc1 = nn.Linear(256, 192).to(device)\n",
    "        self.fc2 = nn.Linear(192, 128).to(device)\n",
    "        self.fc3 = nn.Linear(128, 100).to(device)\n",
    "\n",
    "    def forward(self, x):\n",
    "        x = self.cnet(x)\n",
    "        x = F.relu(self.fc1(x))\n",
    "        x = F.relu(self.fc2(x))\n",
    "        return self.fc3(x)\n",
    "\n",
    "\n",
    "torch.manual_seed(42)\n",
    "model_mlp = CNN_MLP(device=device)\n",
    "results_mlp = train_and_eval(model_mlp, \"mlp\")\n",
    "del model_mlp\n",
    "torch.cuda.empty_cache()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "results-title",
   "metadata": {},
   "source": [
    "## Results"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "results",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Model      Params     Head    Top-1    Top-5     Time\n",
      "----------------------------------------------------\n",
      "pz         83,572   27,252   35.2%   66.0%   127.2s\n",
      "rpz        79,988   23,668   35.2%   66.2%   127.4s\n",
      "real       79,092   22,772   35.7%   66.9%   110.7s\n",
      "mlp       167,908  111,588   38.2%   68.1%   105.8s\n"
     ]
    }
   ],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "\n",
    "all_results = [results_pz, results_rpz, results_real, results_mlp]\n",
    "\n",
    "print(f\"{'Model':<8} {'Params':>8} {'Head':>8} {'Top-1':>8} {'Top-5':>8} {'Time':>8}\")\n",
    "print(\"-\" * 52)\n",
    "for r in all_results:\n",
    "    print(\n",
    "        f\"{r['label']:<8} {r['n_params']:>8,} {r['head_params']:>8,} \"\n",
    "        f\"{r['top1']:>7.1%} {r['top5']:>7.1%} {r['time_s']:>7.1f}s\"\n",
    "    )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "plot",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1200x400 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig, axes = plt.subplots(1, 2, figsize=(12, 4))\n",
    "\n",
    "for r in all_results:\n",
    "    axes[0].plot(range(1, N_EPOCHS + 1), [a * 100 for a in r[\"test_accs\"]], label=r[\"label\"])\n",
    "    axes[1].plot(range(1, N_EPOCHS + 1), [a * 100 for a in r[\"test_top5_accs\"]], label=r[\"label\"])\n",
    "\n",
    "axes[0].set_xlabel(\"Epoch\")\n",
    "axes[0].set_ylabel(\"Test Top-1 Accuracy (%)\")\n",
    "axes[0].set_title(\"Top-1 Accuracy\")\n",
    "axes[0].legend()\n",
    "axes[0].grid(True, alpha=0.3)\n",
    "\n",
    "axes[1].set_xlabel(\"Epoch\")\n",
    "axes[1].set_ylabel(\"Test Top-5 Accuracy (%)\")\n",
    "axes[1].set_title(\"Top-5 Accuracy\")\n",
    "axes[1].legend()\n",
    "axes[1].grid(True, alpha=0.3)\n",
    "\n",
    "fig.suptitle(\"HQKAN-44 Ansatz Comparison on CIFAR-100\", fontsize=14)\n",
    "plt.tight_layout()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "bar",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1400x400 with 3 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig, axes = plt.subplots(1, 3, figsize=(14, 4))\n",
    "\n",
    "labels = [r[\"label\"] for r in all_results]\n",
    "colors = [\"#4C72B0\", \"#55A868\", \"#C44E52\", \"#8172B2\"]\n",
    "\n",
    "# Parameter count (head only)\n",
    "heads = [r[\"head_params\"] for r in all_results]\n",
    "axes[0].bar(labels, heads, color=colors)\n",
    "axes[0].set_ylabel(\"Head Parameters\")\n",
    "axes[0].set_title(\"Head Parameters (excl. CNN)\")\n",
    "for i, v in enumerate(heads):\n",
    "    axes[0].text(i, v + 500, f\"{v:,}\", ha=\"center\", fontsize=9)\n",
    "\n",
    "# Top-1 accuracy\n",
    "top1s = [r[\"top1\"] * 100 for r in all_results]\n",
    "axes[1].bar(labels, top1s, color=colors)\n",
    "axes[1].set_ylabel(\"Top-1 Accuracy (%)\")\n",
    "axes[1].set_title(\"Best Top-1 Accuracy\")\n",
    "axes[1].set_ylim(min(top1s) - 3, max(top1s) + 3)\n",
    "for i, v in enumerate(top1s):\n",
    "    axes[1].text(i, v + 0.3, f\"{v:.1f}%\", ha=\"center\", fontsize=9)\n",
    "\n",
    "# Training time\n",
    "times = [r[\"time_s\"] for r in all_results]\n",
    "axes[2].bar(labels, times, color=colors)\n",
    "axes[2].set_ylabel(\"Time (s)\")\n",
    "axes[2].set_title(f\"Training Time ({N_EPOCHS} epochs)\")\n",
    "for i, v in enumerate(times):\n",
    "    axes[2].text(i, v + 1, f\"{v:.0f}s\", ha=\"center\", fontsize=9)\n",
    "\n",
    "fig.suptitle(\"HQKAN-44 Ansatz Comparison on CIFAR-100\", fontsize=14)\n",
    "plt.tight_layout()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "conclusion",
   "metadata": {},
   "source": [
    "## Conclusion\n",
    "\n",
    "All three QKAN ansatzes achieve comparable accuracy to the MLP baseline while using significantly fewer parameters:\n",
    "\n",
    "- **pz_encoding** provides the most expressive circuit with 2 variational parameters per layer, but at higher computational cost due to complex arithmetic\n",
    "- **rpz_encoding** halves the variational parameters while maintaining accuracy through trainable data encoding\n",
    "- **real** avoids complex arithmetic entirely, offering the fastest training with competitive accuracy\n",
    "\n",
    "All QKAN variants use roughly **4-5x fewer head parameters** than the MLP baseline while achieving similar performance."
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "venv",
   "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": "3.13.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}