{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Variational GPs w/ Multiple Outputs\n",
    "\n",
    "## Introduction\n",
    "\n",
    "In this example, we will demonstrate how to construct approximate/variational GPs that can model vector-valued functions (e.g. multitask/multi-output GPs).\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import math\n",
    "import torch\n",
    "import gpytorch\n",
    "import tqdm\n",
    "from matplotlib import pyplot as plt\n",
    "\n",
    "%matplotlib inline\n",
    "%load_ext autoreload\n",
    "%autoreload 2"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Set up training data\n",
    "\n",
    "In the next cell, we set up the training data for this example. We'll be using 100 regularly spaced points on [0,1] which we evaluate the function on and add Gaussian noise to get the training labels.\n",
    "\n",
    "We'll have four functions - all of which are some sort of sinusoid. Our `train_targets` will actually have two dimensions: with the second dimension corresponding to the different tasks."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "torch.Size([100]) torch.Size([100, 4])\n"
     ]
    }
   ],
   "source": [
    "train_x = torch.linspace(0, 1, 100)\n",
    "\n",
    "train_y = torch.stack([\n",
    "    torch.sin(train_x * (2 * math.pi)) + torch.randn(train_x.size()) * 0.2,\n",
    "    torch.cos(train_x * (2 * math.pi)) + torch.randn(train_x.size()) * 0.2,\n",
    "    torch.sin(train_x * (2 * math.pi)) + 2 * torch.cos(train_x * (2 * math.pi)) + torch.randn(train_x.size()) * 0.2,\n",
    "    -torch.cos(train_x * (2 * math.pi)) + torch.randn(train_x.size()) * 0.2,\n",
    "], -1)\n",
    "\n",
    "print(train_x.shape, train_y.shape)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Define a multitask model\n",
    "\n",
    "We are going to construct a batch variational GP - using a `CholeskyVariationalDistribution` and a `VariationalStrategy`. Each of the batch dimensions is going to correspond to one of the outputs. In addition, we will wrap the variational strategy to make the output appear as a `MultitaskMultivariateNormal` distribution. Here are the changes that we'll need to make:\n",
    "\n",
    "1. Our inducing points will need to have shape `4 x m x 1` (where `m` is the number of inducing points). This ensures that we learn a different set of inducing points for each output dimension.\n",
    "1. The `CholeskyVariationalDistribution`, mean module, and covariance modules will all need to include a `batch_shape=torch.Size([4])` argument. This ensures that we learn a different set of variational parameters and hyperparameters for each output dimension.\n",
    "1. The `VariationalStrategy` object should be wrapped by a variational strategy that handles multitask models. We describe them below:\n",
    "\n",
    "\n",
    "### Types of Variational Multitask Models\n",
    "\n",
    "The most general purpose multitask model is the **Linear Model of Coregionalization** (LMC), which assumes that each output dimension (task) is the linear combination of some latent functions $\\mathbf g(\\cdot) = [g^{(1)}(\\cdot), \\ldots, g^{(Q)}(\\cdot)]$:\n",
    "\n",
    "$$ f_\\text{task}(\\mathbf x) = \\sum_{i=1}^Q a^{(i)} g^{(i)}(\\mathbf x), $$\n",
    "\n",
    "where $a^{(i)}$ are learnable parameters."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "num_latents = 3\n",
    "num_tasks = 4\n",
    "\n",
    "class MultitaskGPModel(gpytorch.models.ApproximateGP):\n",
    "    def __init__(self, num_latents, num_tasks):\n",
    "        # Let's use a different set of inducing points for each latent function\n",
    "        inducing_points = torch.rand(num_latents, 16, 1)\n",
    "        \n",
    "        # We have to mark the CholeskyVariationalDistribution as batch\n",
    "        # so that we learn a variational distribution for each task\n",
    "        variational_distribution = gpytorch.variational.CholeskyVariationalDistribution(\n",
    "            inducing_points.size(-2), batch_shape=torch.Size([num_latents])\n",
    "        )\n",
    "        \n",
    "        # We have to wrap the VariationalStrategy in a LMCVariationalStrategy\n",
    "        # so that the output will be a MultitaskMultivariateNormal rather than a batch output\n",
    "        variational_strategy = gpytorch.variational.LMCVariationalStrategy(\n",
    "            gpytorch.variational.VariationalStrategy(\n",
    "                self, inducing_points, variational_distribution, learn_inducing_locations=True\n",
    "            ),\n",
    "            num_tasks=num_tasks,\n",
    "            num_latents=num_latents,\n",
    "            latent_dim=-1\n",
    "        )\n",
    "        \n",
    "        super().__init__(variational_strategy)\n",
    "        \n",
    "        # The mean and covariance modules should be marked as batch\n",
    "        # so we learn a different set of hyperparameters\n",
    "        self.mean_module = gpytorch.means.ConstantMean(batch_shape=torch.Size([num_latents]))\n",
    "        self.covar_module = gpytorch.kernels.ScaleKernel(\n",
    "            gpytorch.kernels.RBFKernel(batch_shape=torch.Size([num_latents])),\n",
    "            batch_shape=torch.Size([num_latents])\n",
    "        )\n",
    "        \n",
    "    def forward(self, x):\n",
    "        # The forward function should be written as if we were dealing with each output\n",
    "        # dimension in batch\n",
    "        mean_x = self.mean_module(x)\n",
    "        covar_x = self.covar_module(x)\n",
    "        return gpytorch.distributions.MultivariateNormal(mean_x, covar_x)\n",
    "\n",
    "\n",
    "model = MultitaskGPModel(num_latents, num_tasks)\n",
    "likelihood = gpytorch.likelihoods.MultitaskGaussianLikelihood(num_tasks=num_tasks)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "With all of the `batch_shape` arguments - it may look like we're learning a batch of GPs. However, `LMCVariationalStrategy` objects convert this batch_dimension into a (non-batch) MultitaskMultivariateNormal."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "torch.Size([100, 4])"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "likelihood(model(train_x)).rsample().shape"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The LMC model allows there to be linear dependencies between outputs/tasks. Alternatively, if we want independent output dimensions, we can replace `LMCVariationalStrategy` with `IndependentMultitaskVariationalStrategy`:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "class IndependentMultitaskGPModel(gpytorch.models.ApproximateGP):\n",
    "    def __init__(self, num_tasks):\n",
    "        # Let's use a different set of inducing points for each task\n",
    "        inducing_points = torch.rand(num_tasks, 16, 1)\n",
    "        \n",
    "        # We have to mark the CholeskyVariationalDistribution as batch\n",
    "        # so that we learn a variational distribution for each task\n",
    "        variational_distribution = gpytorch.variational.CholeskyVariationalDistribution(\n",
    "            inducing_points.size(-2), batch_shape=torch.Size([num_tasks])\n",
    "        )\n",
    "        \n",
    "        variational_strategy = gpytorch.variational.IndependentMultitaskVariationalStrategy(\n",
    "            gpytorch.variational.VariationalStrategy(\n",
    "                self, inducing_points, variational_distribution, learn_inducing_locations=True\n",
    "            ),\n",
    "            num_tasks=num_tasks,\n",
    "        )\n",
    "        \n",
    "        super().__init__(variational_strategy)\n",
    "        \n",
    "        # The mean and covariance modules should be marked as batch\n",
    "        # so we learn a different set of hyperparameters\n",
    "        self.mean_module = gpytorch.means.ConstantMean(batch_shape=torch.Size([num_tasks]))\n",
    "        self.covar_module = gpytorch.kernels.ScaleKernel(\n",
    "            gpytorch.kernels.RBFKernel(batch_shape=torch.Size([num_tasks])),\n",
    "            batch_shape=torch.Size([num_tasks])\n",
    "        )\n",
    "        \n",
    "    def forward(self, x):\n",
    "        # The forward function should be written as if we were dealing with each output\n",
    "        # dimension in batch\n",
    "        mean_x = self.mean_module(x)\n",
    "        covar_x = self.covar_module(x)\n",
    "        return gpytorch.distributions.MultivariateNormal(mean_x, covar_x)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Note that all the batch sizes for `IndependentMultitaskVariationalStrategy` are now `num_tasks` rather than `num_latents`."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Output modes\n",
    "\n",
    "By default, `LMCVariationalStrategy` and `IndependentMultitaskVariationalStrategy` produce vector-valued outputs. In other words, they return a `MultitaskMultivariateNormal` distribution -- containing all task values for each input.\n",
    "\n",
    "This is similar to the ExactGP model described in the [multitask GP regression tutorial](../03_Multitask_Exact_GPs/Multitask_GP_Regression.ipynb)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "MultitaskMultivariateNormal torch.Size([100, 4])\n"
     ]
    }
   ],
   "source": [
    "output = model(train_x)\n",
    "print(output.__class__.__name__, output.event_shape)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Alternatively, if each input is only associated **with a single task**, passing in the `task_indices` argument will specify which task to return for each input. The result will be a standard `MultivariateNormal` distribution -- where each output corresponds to each input's specified task.\n",
    "\n",
    "This is similar to the ExactGP model described in the [Hadamard multitask GP regression tutorial](../03_Multitask_Exact_GPs/Hadamard_Multitask_GP_Regression.ipynb)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "MultivariateNormal torch.Size([5])\n"
     ]
    }
   ],
   "source": [
    "x = train_x[..., :5]\n",
    "task_indices = torch.LongTensor([0, 1, 3, 2, 2])\n",
    "output = model(x, task_indices=task_indices)\n",
    "print(output.__class__.__name__, output.event_shape)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Train the model\n",
    "\n",
    "This code should look similar to the SVGP training code"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "scrolled": false
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/gpleiss/miniconda3/envs/gpytorch/lib/python3.7/site-packages/ipykernel_launcher.py:20: TqdmDeprecationWarning: This function will be removed in tqdm==5.0.0\n",
      "Please use `tqdm.notebook.tqdm` instead of `tqdm.tqdm_notebook`\n"
     ]
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "fffd43a1fd554e129b68581b060b0755",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(HTML(value='Epoch'), FloatProgress(value=0.0, max=500.0), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    }
   ],
   "source": [
    "# this is for running the notebook in our testing framework\n",
    "import os\n",
    "smoke_test = ('CI' in os.environ)\n",
    "num_epochs = 1 if smoke_test else 500\n",
    "\n",
    "\n",
    "model.train()\n",
    "likelihood.train()\n",
    "\n",
    "optimizer = torch.optim.Adam([\n",
    "    {'params': model.parameters()},\n",
    "    {'params': likelihood.parameters()},\n",
    "], lr=0.1)\n",
    "\n",
    "# Our loss object. We're using the VariationalELBO, which essentially just computes the ELBO\n",
    "mll = gpytorch.mlls.VariationalELBO(likelihood, model, num_data=train_y.size(0))\n",
    "\n",
    "# We use more CG iterations here because the preconditioner introduced in the NeurIPS paper seems to be less\n",
    "# effective for VI.\n",
    "epochs_iter = tqdm.tqdm_notebook(range(num_epochs), desc=\"Epoch\")\n",
    "for i in epochs_iter:\n",
    "    # Within each iteration, we will go over each minibatch of data\n",
    "    optimizer.zero_grad()\n",
    "    output = model(train_x)\n",
    "    loss = -mll(output, train_y)\n",
    "    epochs_iter.set_postfix(loss=loss.item())\n",
    "    loss.backward()\n",
    "    optimizer.step()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Make predictions with the model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1152x216 with 4 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Set into eval mode\n",
    "model.eval()\n",
    "likelihood.eval()\n",
    "\n",
    "# Initialize plots\n",
    "fig, axs = plt.subplots(1, num_tasks, figsize=(4 * num_tasks, 3))\n",
    "\n",
    "# Make predictions\n",
    "with torch.no_grad(), gpytorch.settings.fast_pred_var():\n",
    "    test_x = torch.linspace(0, 1, 51)\n",
    "    predictions = likelihood(model(test_x))\n",
    "    mean = predictions.mean\n",
    "    lower, upper = predictions.confidence_region()\n",
    "    \n",
    "for task, ax in enumerate(axs):\n",
    "    # Plot training data as black stars\n",
    "    ax.plot(train_x.detach().numpy(), train_y[:, task].detach().numpy(), 'k*')\n",
    "    # Predictive mean as blue line\n",
    "    ax.plot(test_x.numpy(), mean[:, task].numpy(), 'b')\n",
    "    # Shade in confidence \n",
    "    ax.fill_between(test_x.numpy(), lower[:, task].numpy(), upper[:, task].numpy(), alpha=0.5)\n",
    "    ax.set_ylim([-3, 3])\n",
    "    ax.legend(['Observed Data', 'Mean', 'Confidence'])\n",
    "    ax.set_title(f'Task {task + 1}')\n",
    "\n",
    "fig.tight_layout()\n",
    "None"
   ]
  }
 ],
 "metadata": {
  "anaconda-cloud": {},
  "kernelspec": {
   "display_name": "Python 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": "3.7.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}