Welcome to ShortScience.org! 
[link]
This paper describes a class of algorithms for classification or regression in the online setting. That is, the data is a bunch of pairs $(X_t,Y_t)$ (where X may be a vector), and these data items arrive in some order: the algorithm must predict each $\hat{Y}_t$ using only the $X_t$ and previously seen pairs. In the regression setting, each misprediction has a loss that is like $(Y_t  \hat{Y}_t)^2$, and in the classification setting $Y_t$ is always 0 or 1 and the loss is $ Y_t  \hat{Y}_t $. Roughly, the algorithm makes linear predictions using some internal weight vector $(\hat{y} = w * X)$, and does a gradientdescent like weight update. However, it tries to keep the qnorm (q can be any number) of the weight vector "small", preventing the weights themselves from becoming too large. The algorithm is actually simple, and the weight update takes advantage of link functions, which the author defines. The majority of the paper is focused on deriving loss bounds, showing that the loss incurred by this algorithm isn't much worse than that incurred by the best weight vector, chosen in hindsight. Typical readers will be interested in the first few pages, as the latter part of the paper is mainly technical proofs. 
[link]
This paper derives an algorithm for passing gradients through a sample from a mixture of Gaussians. While the reparameterization trick allows to get the gradients with respect to the Gaussian means and covariances, the same trick cannot be invoked for the mixing proportions parameters (essentially because they are the parameters of a multinomial discrete distribution over the Gaussian components, and the reparameterization trick doesn't extend to discrete distributions). One can think of the derivation as proceeding in 3 steps: 1. Deriving an estimator for gradients a sample from a 1dimensional density $f(x)$ that is such that $f(x)$ is differentiable and its cumulative distribution function (CDF) $F(x)$ is tractable: $\frac{\partial \hat{x}}{\partial \theta} =  \frac{1}{f(\hat{x})}\int_{t=\infty}^{\hat{x}} \frac{\partial f(t)}{\partial \theta} dt$ where $\hat{x}$ is a sample from density $f(x)$ and $\theta$ is any parameter of $f(x)$ (the above is a simplified version of Equation 6). This is probably the most important result of the paper, and is based on a really clever use of the general form of the Leibniz integral rule. 2. Noticing that one can sample from a $D$dimensional Gaussian mixture by decomposing it with the product rule $f({\bf x}) = \prod_{d=1}^D f(x_d{\bf x}_{<d})$ and using ancestral sampling, where each $f(x_d{\bf x}_{<d})$ are themselves 1dimensional mixtures (i.e. with differentiable densities and tractable CDFs) 3. Using the 1dimensional gradient estimator (of Equation 6) and the chain rule to backpropagate through the ancestral sampling procedure. This requires computing the integral in the expression for $\frac{\partial \hat{x}}{\partial \theta}$ above, where $f(x)$ is one of the 1D conditional Gaussian mixtures and $\theta$ is a mixing proportion parameter $\pi_j$. As it turns out, this integral has an analytical form (see Equation 22). **My two cents** This is a really surprising and neat result. The author mentions it could be applicable to variational autoencoders (to support posteriors that are mixtures of Gaussians), and I'm really looking forward to read about whether that can be successfully done in practice. The paper provides the derivation only for mixtures of Gaussians with diagonal covariance matrices. It is mentioned that extending to nondiagonal covariances is doable. That said, ancestral sampling with nondiagonal covariances would become more computationally expensive, since the conditionals under each Gaussian involves a matrix inverse. Beyond the case of Gaussian mixtures, Equation 6 is super interesting in itself as its application could go beyond that case. This is probably why the paper also derived a samplingbased estimator for Equation 6, in Equation 9. However, that estimator might be inefficient, since it involves sampling from Equation 10 with rejection, and it might take a lot of time to get an accepted sample if $\hat{x}$ is very small. Also, a good estimate of Equation 6 might require *multiple* samples from Equation 10. Finally, while I couldn't find any obvious problem with the mathematical derivation, I'd be curious to see whether using the same approach to derive a gradient on one of the Gaussian mean or standard deviation parameters gave a gradient that is consistent with what the reparameterization trick provides.
3 Comments

[link]
This summary builds substantially on my summary of NERFs, so if you haven't yet read that, I recommend doing so first! The idea of a NERF is learn a neural network that represents a 3D scene, and from which you can, once the model is trained, sample an image of that scene from any desired angle. This involves structuring your neural network as a function that predicts the RGB color and density/opacity for a given point in 3D space (x, y, z), from a given viewing angle (theta, phi). With such a function, you can generate predictions of what images taken from certain angles would look like by sampling along a viewing ray, and integrating the combined hue and opacity into an aggregated view. This prediction can then be compared to a true image taken from that direction, and gradients passed backwards into the prediction model. An important assumption of this model is that the scene being photographed is static; specifically, that every point in space is always inhabited by the same part of the 3D object, regardless of what angle it's viewed from. This is a reasonable assumption for photos of inanimate objects, or of humans in highly controlled lab settings, but it is often not true for humans when you, say, ask them to take a selfie video of themselves. Even if they're trying to keep roughly still, there will be slight shifts in the location and position of their head between frames, and the authors of this paper show that this can lead to strange artifacts if you naively try to train a NERF from the images (including a particularly odd one where it hallucinates tiny copies of the image in the air surrounding the face). https://i.imgur.com/IUVh6uM.png The fix proposed by this paper is to apply a learnable deformation field to each image, where the notion is to deform each view into being in one canonical position (fixed per network, since, again, one network corresponds to a single scene). This means that, along with learning the parameters of the NERF itself, you're also learning what deformation to apply to each training image to get it into this canonical position. This is done by parametrizing the deformation in a particular way, and then having that deformation be conditioned by a latent vector that's trained similar to how you'd train an embedding (one learned vector per image example). The parametrization of the deformation is honestly a little bit over my head, given my lack of grounding in 3D modeling, but my general sense is that it applies some constraints and regularization to ensure that the learned deformations are realistic, insofar as humans are mostly rigid (one patch of skin on my forehead generally doesn't move except in concordance with the rest of my forehead), but with some possibility for elasticity (skin can stretch if I, say, smile). The authors also include an annealing scheme whereby, early in training, the model focuses on learning course (largescale) deformations, and later in training, it's allowed to also learn weights for more precise deformations. This is to hopefully match macroscale shifts before adding the noise of precise changes. This addition of a learned deformation is most of the contribution of this method: with it applied, they show that they're able to learn realistic NERFs from selfies, which they term "NERFIES". They mention a few pieces of concurrent work that try to solve the same problem of nonstatic human subjects in different ways, but I haven't had a chance to read those, so I can't really comment on how NERFIES stacks up to alternate approaches, but it appears to be as least one empirically convincing solution to the problem it's aiming at. 
[link]
This paper tests the following hypothesis, about features learned by a deep network trained on the ImageNet dataset: *Object features and anticausal features are closely related. Context features and causal features are not necessarily related.* First, some definitions. Let $X$ be a visual feature (i.e. value of a hidden unit) and $Y$ be information about a label (e.g. the logodds of probability of different object appearing in the image). A causal feature would be one for which the causal direction is $X \rightarrow Y$. An anticausal feature would be the opposite case, $X \leftarrow Y$. As for object features, in this paper they are features whose value tends to change a lot when computed on a complete original image versus when computed on an image whose regions *falling inside* object bounding boxes have been blacked out (see Figure 4). Contextual features are the opposite, i.e. values change a lot when blacking out the regions *outside* object bounding boxes. See section 4.2.1 for how "object scores" and "context scores" are computed following this description, to quantitatively measure to what extent a feature is an "object feature" or a "context feature". Thus, the paper investigates whether 1) for object features, their relationship with object appearance information is anticausal (i.e. whether the object feature's value seems to be caused by the presence of the object) and whether 2) context features are not clearly causal or anticausal. To perform this investigation, the paper first proposes a generic neural network model (dubbed the Neural Causation Coefficient architecture or NCC) to predict a score of whether the relationship between an input variable $X$ and target variable $Y$ is causal. This model is trained by taking as input datasets of $X$ and $Y$ pairs synthetically generated in such a way that we know whether $X$ caused $Y$ or the opposite. The NCC architecture first embeds each individual $X$,$Y$ instance pair into some hidden representation, performs mean pooling of these representations and then feeds the result to fully connected layers (see Figure 3). The paper shows that the proposed NCC model actually achieves SOTA performance on the Tübingen dataset, a collection of realworld causeeffect observational samples. Then, the proposed NCC model is used to measure the average object score of features of a deep residual CNN identified as being most causal and most anticausal by NCC. The same is done with the context score. What is found is that indeed, the object score is always higher for the top anticausal features than for the top causal features. However, for the context score, no such clear trend is observed (see Figure 5). **My two cents** I haven't been following the growing literature on machine learning for causal inference, so it was a real pleasure to read this paper and catch up a little bit on that. Just for that I would recommend the reading of this paper. The paper does a really good job at explaining the notion of *observational causal inference*, which in short builds on the observation that if we assume IID noise on top of a causal (or anticausal) phenomenon, then causation can possibly be inferred by verifying in which direction of causation the IID assumption on the noise seems to hold best (see Figure 2 for a nice illustration, where in (a) the noise is clearly IID, but isn't in (b)). Also, irrespective of the study of causal phenomenon in images, the NCC architecture, which achieves SOTA causal prediction performance, is in itself a nice contribution. Regarding the application to image features, one thing that is hard to wrap your head around is that, for the $Y$ variable, instead of using the true image label, the logodds at the output layer are used instead in the study. The paper justifies this choice by highlighting that the NCC network was trained on examples where $Y$ is continuous, not discrete. On one hand, that justification makes sense. On the other, this is odd since the logodds were in fact computed directly from the visual features, meaning that technically the value of the logodds are directly caused by all the features (which goes against the hypothesis being tested). My best guess is that this isn't an issue only because NCC makes a causal prediction between *a single feature* and $Y$, not *from all features* to $Y$. I'd be curious to read the authors' perspective on this. Still, this paper at this point is certainly just scratching the surface on this topic. For instance, the paper mentions that NCC could be used to encourage the learning of causal or anticausal features, providing a new and intriguing type of regularization. This sounds like a very interesting future direction for research, which I'm looking forward to.
4 Comments

[link]
Hein and Andriushchenko give a intuitive bound on the robustness of neural networks based on the local Lipschitz constant. With robustness, the authors refer a small $\epsilon$ball around each sample; this ball is supposed to describe the region where the neural network predicts a constant class. This means that adversarial examples have to compute changes large enough to leave these robust areas. Larger $\epsilon$balls imply higher robustness to adversarial examples. When considering a single example $x$, and a classifier $f = (f_1, \ldots, f_K)^T$ (i.e. in a multiclass setting), the bound can be stated as follows. For $q$ and $p$ such that $\frac{1}{q} + \frac{1}{p} = 1$ and $c$ being the class predicted for $x$, the it holds $x = \arg\max_j f_j(x + \delta)$ for all $\delta$ with $\\delta\_p \leq \max_{R > 0}\min \left\{\min_{j \neq c} \frac{f_c(x) – f_j(x)}{\max_{y \in B_p(x, R)} \\nabla f_c(y)  \nabla f_j(y)\_q}, R\right\}$. Here, $B_p(x, R)$ describes the $R$ball around $x$ measured using the $p$norm. Based on the local Lipschitz constant (in the denominator), the bound essentially measures how far we can deviate from the sample $x$ (measured in the $p$norm) until $f_j(x) > f_c(x)$ for some $j \neq c$. The higher the local Lipschitz constant, the smaller deviations are allowed, i.e. adversarial examples are easier to find. Note that the bound also depends on the confidence, i.e. the edge $f_c(x)$ has in comparison to all other $f_j(x)$. In the remaining paper, the authors also provide bounds for simple classifiers including linear classifiers, kernel methods and twolayer perceptrons (i.e. one hidden layer). For the latter, they also propose a new type of regularization called crossLipschitz regularization: $P(f) = \frac{1}{nK^2} \sum_{i = 1}^n \sum_{l,m = 1}^K \\nabla f_l(x_i)  \nabla f_m(x_i)\_2^2$. This regularization term is intended to reduce the Lipschitz constant locally around training examples. They show experimental results using this regularization on MNIST and CIFAR, see the paper for details. Also view this summary at [davidstutz.de](https://davidstutz.de/category/reading/). 