{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "# Initialization Schemes for Input Convex Neural Network" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "As input convex neural networks (ICNN) are notoriously difficult to train {cite}`richter-powell:21`, {cite}`bunne:22` propose to use closed-form solutions between Gaussian approximations to derive relevant parameter initializations for ICNNs: given two measures $\\mu$ and $\\nu$, one can initialize ICNN parameters so that they are (initially) meaningful in the context of OT, namely that its gradient is able to approximately map source measure $\\mu$ into a target measure $\\nu$. These initializations rely on closed-form solutions available for Gaussian measures {cite}`gelbrich:90`.\n", "\n", "In this notebook, we introduce the *identity* and *Gaussian approximation*-based initialization schemes, and illustrate how they can be used within the `OTT` library and its {class}`~ott.solvers.nn.icnn.ICNN`-based {class}`~ott.solvers.nn.neuraldual.NeuralDualSolver`." ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "import sys\n", "\n", "if \"google.colab\" in sys.modules:\n", " !pip install -q git+https://github.com/ott-jax/ott@main" ] }, { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [], "source": [ "import jax\n", "import jax.numpy as jnp\n", "import numpy as np\n", "import optax\n", "from torch.utils.data import DataLoader, IterableDataset\n", "\n", "import matplotlib.pyplot as plt\n", "\n", "from ott.geometry import pointcloud\n", "from ott.solvers.nn import icnn, neuraldual" ] }, { "cell_type": "markdown", "metadata": { "tags": [] }, "source": [ "## Helper Functions" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Let us define some helper functions which we use for the subsequent analysis." ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [], "source": [ "def plot_ot_map(neural_dual, source, target, inverse=False):\n", " \"\"\"Plot data and learned optimal transport map.\"\"\"\n", "\n", " def draw_arrows(a, b):\n", " plt.arrow(\n", " a[0], a[1], b[0] - a[0], b[1] - a[1], color=[0.5, 0.5, 1], alpha=0.3\n", " )\n", "\n", " if not inverse:\n", " grad_state_s = neural_dual.transport(source)\n", " else:\n", " grad_state_s = neural_dual.inverse_transport(source)\n", "\n", " fig = plt.figure()\n", " ax = fig.add_subplot(111)\n", "\n", " if not inverse:\n", " ax.scatter(\n", " target[:, 0],\n", " target[:, 1],\n", " color=\"#A7BED3\",\n", " alpha=0.5,\n", " label=r\"$target$\",\n", " )\n", " ax.scatter(\n", " source[:, 0],\n", " source[:, 1],\n", " color=\"#1A254B\",\n", " alpha=0.5,\n", " label=r\"$source$\",\n", " )\n", " ax.scatter(\n", " grad_state_s[:, 0],\n", " grad_state_s[:, 1],\n", " color=\"#F2545B\",\n", " alpha=0.5,\n", " label=r\"$\\nabla g(source)$\",\n", " )\n", " else:\n", " ax.scatter(\n", " target[:, 0],\n", " target[:, 1],\n", " color=\"#A7BED3\",\n", " alpha=0.5,\n", " label=r\"$source$\",\n", " )\n", " ax.scatter(\n", " source[:, 0],\n", " source[:, 1],\n", " color=\"#1A254B\",\n", " alpha=0.5,\n", " label=r\"$target$\",\n", " )\n", " ax.scatter(\n", " grad_state_s[:, 0],\n", " grad_state_s[:, 1],\n", " color=\"#F2545B\",\n", " alpha=0.5,\n", " label=r\"$\\nabla f(target)$\",\n", " )\n", "\n", " plt.legend()\n", "\n", " for i in range(source.shape[0]):\n", " draw_arrows(source[i, :], grad_state_s[i, :])" ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [], "source": [ "def get_optimizer(optimizer, lr, b1, b2, eps):\n", " \"\"\"Returns a flax optimizer object based on `config`.\"\"\"\n", "\n", " if optimizer == \"Adam\":\n", " optimizer = optax.adam(learning_rate=lr, b1=b1, b2=b2, eps=eps)\n", " elif optimizer == \"SGD\":\n", " optimizer = optax.sgd(learning_rate=lr, momentum=None, nesterov=False)\n", " else:\n", " raise NotImplementedError(f\"Optimizer {optimizer} not supported yet!\")\n", "\n", " return optimizer" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Setup Training and Validation Datasets" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "To test the ICNN initialization methods, we choose the {class}`~ott.solvers.nn.neuraldual.NeuralDualSolver` of the `OTT` library as an example. Here, we aim at computing the map between two toy datasets representing both, source and target distribution. For more details on the execution of the {class}`~ott.solvers.nn.neuraldual.NeuralDualSolver`, we refer the reader to {doc}`neural_dual` notebook.\n", "\n", "In this tutorial, the user can choose between the datasets `simple` (data clustered in one center), `circle` (two-dimensional Gaussians arranged on a circle), `square_five` (two-dimensional Gaussians on a square with one Gaussian in the center), and `square_four` (two-dimensional Gaussians in the corners of a rectangle)." ] }, { "cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [], "source": [ "class ToyDataset(IterableDataset):\n", " def __init__(self, name):\n", " self.name = name\n", "\n", " def __iter__(self):\n", " return self.create_sample_generators()\n", "\n", " def create_sample_generators(self, scale=5.0, variance=0.5):\n", " # given name of dataset, select centers\n", " if self.name == \"simple\":\n", " centers = np.array([0, 0])\n", "\n", " elif self.name == \"circle\":\n", " centers = np.array(\n", " [\n", " (1, 0),\n", " (-1, 0),\n", " (0, 1),\n", " (0, -1),\n", " (1.0 / np.sqrt(2), 1.0 / np.sqrt(2)),\n", " (1.0 / np.sqrt(2), -1.0 / np.sqrt(2)),\n", " (-1.0 / np.sqrt(2), 1.0 / np.sqrt(2)),\n", " (-1.0 / np.sqrt(2), -1.0 / np.sqrt(2)),\n", " ]\n", " )\n", "\n", " elif self.name == \"square_five\":\n", " centers = np.array([[0, 0], [1, 1], [-1, 1], [-1, -1], [1, -1]])\n", "\n", " elif self.name == \"square_four\":\n", " centers = np.array([[1, 0], [0, 1], [-1, 0], [0, -1]])\n", "\n", " else:\n", " raise NotImplementedError()\n", "\n", " # create generator which randomly picks center and adds noise\n", " centers = scale * centers\n", " while True:\n", " center = centers[np.random.choice(len(centers))]\n", " point = center + variance**2 * np.random.randn(2)\n", "\n", " yield point\n", "\n", "\n", "def load_toy_data(\n", " name_source: str,\n", " name_target: str,\n", " batch_size: int = 1024,\n", " valid_batch_size: int = 1024,\n", "):\n", " dataloaders = (\n", " iter(DataLoader(ToyDataset(name_source), batch_size=batch_size)),\n", " iter(DataLoader(ToyDataset(name_target), batch_size=batch_size)),\n", " iter(DataLoader(ToyDataset(name_source), batch_size=valid_batch_size)),\n", " iter(DataLoader(ToyDataset(name_target), batch_size=valid_batch_size)),\n", " )\n", " input_dim = 2\n", " return dataloaders, input_dim" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Experimental Setup " ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "In order to solve the neural dual, we need to define our dataloaders. The only requirement is that the corresponding source and target train and validation datasets are *iterators*." ] }, { "cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [], "source": [ "(dataloader_source, dataloader_target, _, _), input_dim = load_toy_data(\n", " \"simple\", \"circle\"\n", ")" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "To visualize the initialization schemes, let's sample data from the source and target distribution." ] }, { "cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [], "source": [ "data_source = next(dataloader_source).numpy()\n", "data_target = next(dataloader_target).numpy()" ] }, { "cell_type": "code", "execution_count": 7, "metadata": {}, "outputs": [], "source": [ "# initialize optimizers\n", "optimizer_f = get_optimizer(\"Adam\", lr=0.0001, b1=0.5, b2=0.9, eps=1e-8)\n", "optimizer_g = get_optimizer(\"Adam\", lr=0.0001, b1=0.5, b2=0.9, eps=1e-8)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Identity Initialization Method" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Next, we define the architectures parameterizing the dual potentials $f$ and $g$. These need to be parameterized by ICNNs. You can adapt the size of the ICNNs by passing a sequence containing hidden layer sizes. While ICNNs are by default containing partially positive weights, we can solve the problem using approximations to this positivity constraint (via weight clipping and a weight penalization). For this, set `positive_weights` to `True` in both the {class}`~ott.solvers.nn.icnn.ICNN` architecture and {class}`~ott.solvers.nn.neuraldual.NeuralDualSolver` configuration. For more details on how to customize the ICNN architectures, we refer you to the documentation." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "We first explore the `identity` initialization method. This initialization method is the default choice of the current ICNN and data independent, thus no further arguments need to be passed to the ICNN architecture." ] }, { "cell_type": "code", "execution_count": 8, "metadata": {}, "outputs": [], "source": [ "# initialize models using identity initialization (default)\n", "neural_f = icnn.ICNN(dim_hidden=[64, 64, 64, 64], dim_data=2)\n", "neural_g = icnn.ICNN(dim_hidden=[64, 64, 64, 64], dim_data=2)" ] }, { "cell_type": "code", "execution_count": 9, "metadata": {}, "outputs": [ { "data": { "application/vnd.jupyter.widget-view+json": { "model_id": "6149d916e1ca484a94c4f5b218825e1d", "version_major": 2, "version_minor": 0 }, "text/plain": [ "0it [00:00, ?it/s]" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "neural_dual_solver = NeuralDualSolver(\n", " input_dim, neural_f, neural_g, optimizer_f, optimizer_g, num_train_iters=0\n", ")\n", "neural_dual = neural_dual_solver(\n", " dataloader_source, dataloader_target, dataloader_source, dataloader_target\n", ")" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Now, we can plot the corresponding transport from source to target using the gradient of the learning potential $g$, i.e., $\\nabla g(\\text{source})$, or from target to source via the gradient of the learning potential $f$, i.e., $\\nabla f(\\text{target})$." ] }, { "cell_type": "code", "execution_count": 10, "metadata": {}, "outputs": [ { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "plot_ot_map(neural_dual, data_source, data_target, inverse=False)" ] }, { "cell_type": "code", "execution_count": 11, "metadata": {}, "outputs": [ { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "plot_ot_map(neural_dual, data_target, data_source, inverse=True)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Before training, the `identity` initialization (`num_train_iters=0`) maps source or target sample onto itself. If source and target samples are not too dissimilar, this initialization method compared to a random vanilla weight initialization achieves a good approximation already." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Gaussian Initialization" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "The `Gaussian approximation`-based initialization schemes require samples from both, source and target distributions, in order to initialize the ICNNs with linear factors and means, as detailed in {cite}`bunne:22`." ] }, { "cell_type": "code", "execution_count": 12, "metadata": {}, "outputs": [], "source": [ "samples_source = jnp.concatenate(\n", " [next(dataloader_source).numpy() for _ in range(10)]\n", ")\n", "samples_target = jnp.concatenate(\n", " [next(dataloader_target).numpy() for _ in range(10)]\n", ")" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "To use the Gaussian initialization, the samples of source and target (`samples_source` and `samples_target`) need to be passed to the {class}`~ott.solvers.nn.icnn.ICNN` definition via the `gaussian_map` argument. Note that ICNN $f$ maps target to source (`gaussian_map=(samples_target, samples_source)`), and $g$ maps source to target cells (`gaussian_map=(samples_source, samples_target)`)." ] }, { "cell_type": "code", "execution_count": 13, "metadata": {}, "outputs": [], "source": [ "# initialize models using Gaussian initialization\n", "neural_f = icnn.ICNN(\n", " dim_hidden=[64, 64, 64, 64],\n", " dim_data=2,\n", " gaussian_map=(samples_target, samples_source),\n", ")\n", "neural_g = icnn.ICNN(\n", " dim_hidden=[64, 64, 64, 64],\n", " dim_data=2,\n", " gaussian_map=(samples_source, samples_target),\n", ")" ] }, { "cell_type": "code", "execution_count": 14, "metadata": {}, "outputs": [ { "data": { "application/vnd.jupyter.widget-view+json": { "model_id": "260b8efc648f42e98392e7884d5f3da2", "version_major": 2, "version_minor": 0 }, "text/plain": [ "0it [00:00, ?it/s]" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "neural_dual_solver = NeuralDualSolver(\n", " input_dim, neural_f, neural_g, optimizer_f, optimizer_g, num_train_iters=0\n", ")\n", "neural_dual = neural_dual_solver(\n", " dataloader_source, dataloader_target, dataloader_source, dataloader_target\n", ")" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Again, we can plot the corresponding transport from source to target using the gradient of the learning potential $g$, i.e., $\\nabla g(\\text{source})$, or from target to source via the gradient of the learning potential $f$, i.e., $\\nabla f(\\text{target})$." ] }, { "cell_type": "code", "execution_count": 15, "metadata": {}, "outputs": [ { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "plot_ot_map(neural_dual, data_source, data_target, inverse=False)" ] }, { "cell_type": "code", "execution_count": 16, "metadata": {}, "outputs": [ { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "plot_ot_map(neural_dual, data_target, data_source, inverse=True)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Using this initialization scheme maps the source (using $g$) or target measure (using $f$) to the Gaussian approximation of the respective counterpart. In the case of target $\\nu$ this represents almost the correct solution." ] } ], "metadata": { "kernelspec": { "display_name": "Python 3 (ipykernel)", "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": "3.10.8" }, "vscode": { "interpreter": { "hash": "ba22eb0a90cf9680fd06e72916a6996fb9b27a2ebc703f47aacd356a82bf9683" } } }, "nbformat": 4, "nbformat_minor": 2 }