This paper is based on an intriguing idea of combining state-space models (SSMs) and recurrent neural networks (RNNs). Ideally, it is very much needed: For the sequences which have distinct structure and high variability, probabilistic modelling is a big problem. The handcrafted and parameterised feature representations are widely used to ease the problem and it is customary to develop the probabilistic model on top of these extracted features from the signal (such as using a short-time Fourier transform and _then_ probabilistic modelling over these features).

But machines should be able to handle learning the representation part as well. So the story of the paper. Here, it is termed neural network with stochastic layers but one can safely say that the model is a state-space model with a deterministic neural network layer which is tied to both hidden variables and observations. Still, due to the complicated nonlinearities, it is not easy to understand what's going on.

One thing I found missing from the paper is the exact form of nonlinearity used for the NN layer as I am looking at it from the perspective of probabilistic modelling. But this is probably because of space reasons.

# Very Short

The authors propose **learning** an optimizer **to** optimally **learn** a function (the *optimizee*) which is being trained **by gradient descent**.  This optimizer, a recurrent neural network, is trained to make optimal parameter updates to the optimizee **by gradient descent**.

# Short

Let's suppose we have a stochastic function $f: \mathbb R^{\text{dim}(\theta)} \rightarrow \mathbb R^+$, (the *optimizee*) which we wish to minimize with respect to $\theta$.  Note that this is the typical situation we encounter when training a neural network with Stochastic Gradient Descent - where the stochasticity comes from sampling random minibatches of the data (the data is omitted as an argument here).  

The "vanilla" gradient descent update is: $\theta_{t+1} = \theta_t - \alpha_t \nabla_{\theta_t} f(\theta_t)$, where $\alpha_t$ is some learning rate.  Other optimizers (Adam, RMSProp, etc) replace the multiplication of the gradient by $-\alpha_t$ with some sort of weighted sum of the history of gradients.

This paper proposes to apply an optimization step $\theta_{t+1} = \theta_t + g_t$, where the update $g_t \in \mathbb R^{\text{dim}(\theta)}$ is defined by a recurrent network $m_\phi$: 

$$(g_t, h_{t+1}) := m_\phi (\nabla_{\theta_t} f(\theta_t), h_t)$$

Where in their implementation, $h_t \in \mathbb R^{\text{dim}(\theta)}$ is the hidden state of the recurrent network.  To make the number of parameters in the optimizer manageable, they implement their recurrent network $m$ as a *coordinatewise* LSTM (i.e. A set of $\text{dim}(\theta)$ small LSTMs that share parameters $\phi$).   They train the optimizer networks's parameters $\phi$ by "unrolling" T subsequent steps of optimization, and minimizing:

$$\mathcal L(\phi) := \mathbb E_f[f(\theta^*(f, \phi))]  \approx \frac1T \sum_{t=1}^T f(\theta_t)$$

Where $\theta^*(f, \phi)$ are the final optimizee parameters.  In order to avoid computing second derivatives while calculating $\frac{\partial \mathcal L(\phi)}{\partial \phi}$, they make the approximation $\frac{\partial}{\partial \phi}  \nabla_{\theta_t}f(\theta_t) \approx 0$ (corresponding to the dotted lines in the figure, along which gradients are not backpropagated).  

https://i.imgur.com/HMaCeip.png
**The computational graph of the optimization of the optimizer, unrolled across 3 time-steps.  Note that $\nabla_t := \nabla_{\theta_t}f(\theta_t)$.  The dotted line indicates that we do not backpropagate across this path.**

The authors demonstrate that their method usually outperforms traditional optimizers (ADAM, RMSProp, SGD, NAG), on a synthetic dataset, MNIST, CIFAR-10, and Neural Style Transfer.  They argue that their algorithm constitutes a form of transfer learning, since a pre-trained optimizer can be applied to accelerate training of a newly initialized network.  

Zhang et al. combine interval bound propagation and CROWN, both approaches to obtain bounds on a network’s output, to efficiently train robust networks. Both interval bound propagation (IBP) and CROWN allow to bound a network’s output for a specific set of allowed perturbations around clean input examples. These bounds can be used for adversarial training. The motivation to combine BROWN and IBP stems from the fact that training using IBP bounds usually results in instabilities, while training with CROWN bounds usually leads to over-regularization.

Also find this summary at [davidstutz.de](https://davidstutz.de/category/reading/).

This is follow-up work to the ResNets paper. It studies the propagation formulations behind the connections of deep residual networks and performs ablation experiments. A residual block can be represented with the equations $y_l = h(x_l) + F(x_l, W_l); x_{l+1} = f(y_l)$. $x_l$ is the input to the l-th unit and $x_{l+1}$ is the output of the l-th unit. In the original ResNets paper, $h(x_l) = x_l$, $f$ is ReLu, and F consists of 2-3 convolutional layers (bottleneck architecture) with BN and ReLU in between. In this paper, they propose a residual block with both $h(x)$ and $f(x)$ as identity mappings, which trains faster and performs better than their earlier baseline. Main contributions:

- Identity skip connections work much better than other multiplicative interactions that they experiment with:
    - Scaling $(h(x) = \lambda x)$: Gradients can explode or vanish depending on whether modulating scalar \lambda > 1 or < 1.
    - Gating ($1-g(x)$ for skip connection and $g(x)$ for function F):
    For gradients to propagate freely, $g(x)$ should approach 1, but
    F gets suppressed, hence suboptimal. This is similar to highway
    networks. $g(x)$ is a 1x1 convolutional layer.
    - Gating (shortcut-only): Setting high biases pushes initial $g(x)$
    towards identity mapping, and test error is much closer to baseline.
    - 1x1 convolutional shortcut: These work well for shallower networks
    (~34 layers), but training error becomes high for deeper networks,
    probably because they impede gradient propagation.

- Experiments on activations.
    - BN after addition messes up information flow, and performs considerably
    worse.
    - ReLU before addition forces the signal to be non-negative, so the signal is monotonically increasing, while ideally a residual function should be free to take values in (-inf, inf).
    - BN + ReLU pre-activation works best. This also prevents overfitting, due
    to BN's regularizing effect. Input signals to all weight layers are normalized.

## Strengths

- Thorough set of experiments to show that identity shortcut connections
are easiest for the network to learn. Activation of any deeper unit can
be written as the sum of the activation of a shallower unit and a residual
function. This also implies that gradients can be directly propagated to
shallower units. This is in contrast to usual feedforward networks, where
gradients are essentially a series of matrix-vector products, that may vanish, as networks grow deeper.

- Improved accuracies than their previous ResNets paper.

## Weaknesses / Notes

- Residual units are useful and share the same core idea that worked in
LSTM units. Even though stacked non-linear layers are capable of asymptotically
approximating any arbitrary function, it is clear from recent work that
residual functions are much easier to approximate than the complete function.
The [latest Inception paper](http://arxiv.org/abs/1602.07261) also reports
that training is accelerated and performance is improved by using identity
skip connections across Inception modules.

- It seems like the degradation problem, which serves as motivation for
residual units, exists in the first place for non-idempotent activation
functions such as sigmoid, hyperbolic tan. This merits further
investigation, especially with recent work on function-preserving transformations such as [Network Morphism](http://arxiv.org/abs/1603.01670), which expands the Net2Net idea to sigmoid, tanh, by using parameterized activations, initialized to identity mappings.

This paper combines two ideas. The first is stochastic gradient Langevin dynamics (SGLD), which is an efficient Bayesian learning method for larger datasets, allowing to efficiently sample from the posterior over the parameters of a model (e.g. a deep neural network). In short, SGLD is stochastic (minibatch) gradient descent, but where Gaussian noise is added to the gradients before each update. Each update thus results in a sample from the SGLD sampler. To make a prediction for a new data point, a number of previous parameter values are combined into an ensemble, which effectively corresponds to Monte Carlo estimate of the posterior predictive distribution of the model.

The second idea is distillation or dark knowledge, which in short is the idea of training a smaller model (student) in replicating the behavior and performance of a much larger model (teacher), by essentially training the student to match the outputs of the teacher. 

The observation made in this paper is that the step of creating an ensemble of several models (e.g. deep networks) can be expensive, especially if many samples are used and/or if each model is large. Thus, they propose to approximate the output of that ensemble by training a single network to predict to output of ensemble. Ultimately, this is done by having the student predict the output of a teacher corresponding to the model with the last parameter value sampled by SGLD.

Interestingly, this process can be operated in an online fashion, where one alternates between sampling from SGLD (i.e. performing a noisy SGD step on the teacher model) and performing a distillation update (i.e. updating the student model, given the current teacher model). The end result is a student model, whose outputs should be calibrated to the bayesian predictive distribution.