Welcome to ShortScience.org! 
[link]
This is an interestingly pragmatic paper that makes a super simple observation. Often, we may want a usable network with fewer parameters, to make our network more easily usable on small devices. It's been observed (by these same authors, in fact), that pruned networks can achieve comparable weights to their fully trained counterparts if you rewind and retrain from early in the training process, to compensate for the loss of the (not ultimately important) pruned weights. This observation has been dubbed the "Lottery Ticket Hypothesis", after the idea that there's some small effective subnetwork you can find if you sample enough networks. Given these two facts  the usefulness of pruning, and the success of weight rewinding  the authors explore the effectiveness of various ways to train after pruning. Current standard practice is to prune lowmagnitude weights, and then continue training remaining weights from values they had at pruning time, keeping the final learning rate of the network constant. The authors find that: 1. Weight rewinding, where you rewind weights to *near* their starting value, and then retrain using the learning rates of early in training, outperforms fine tuning from the place weights were when you pruned but, also 2. Learning rate rewinding, where you keep weights as they are, but rewind learning rates to what they were early in training, are actually the most effective for a given amount of training time/search cost To me, this feels a little bit like burying the lede: the takeaway seems to be that when you prune, it's beneficial to make your network more "elastic" (in the metaphortoneuroscience sense) so it can more effectively learn to compensate for the removed neurons. So, what was really valuable in weight rewinding was the ability to "heat up" learning on a smaller set of weights, so they could adapt more quickly. And the fact that learning rate rewinding works better than weight rewinding suggests that there is value in the learned weights after all, that value is just outstripped by the benefit of rolling back to old learning rates. All in all, not a super radical conclusion, but a useful and practical one to have so clearly laid out in a paper. 
[link]
Rakelly et al. propose a method to do offpolicy meta reinforcement learning (rl). The method achieves a 20100x improvement on sample efficiency compared to onpolicy meta rl like MAML+TRPO. The key difficulty for offline meta rl arises from the metalearning assumption, that metatraining and metatest time match. However during test time the policy has to explore and sees as such onpolicy data which is in contrast to the offpolicy data that should be used at metatraining. The key contribution of PEARL is an algorithm that allows for online task inference in a latent variable at train and test time, which is used to train a Soft Actor Critic, a very sample efficient offpolicy algorithm, with additional dependence of the latent variable. The implementation of Rakelly et al. proposes to capture knowledge about the current task in a latent stochastic variable Z. A inference network $q_{\Phi}(z \vert c)$ is used to predict the posterior over latents given context c of the current task in from of transition tuples $(s,a,r,s')$ and trained with an information bottleneck. Note that the task inference is done on samples according to a sampling strategy sampling more recent transitions. The latent z is used as an additional input to policy $\pi(a \vert s, z)$ and Qfunction $Q(a,s,z)$ of a soft actor critic algorithm which is trained with offline data of the full replay buffer. https://i.imgur.com/wzlmlxU.png So the challenge of differing conditions at test and train times is resolved by sampling the content for the latent context variable at train time only from very recent transitions (which is almost onpolicy) and at test time by construction onpolicy. Sampling $z \sim q(z \vert c)$ at test time allows for posterior sampling of the latent variable, yielding efficient exploration. The experiments are performed across 6 Mujoco tasks with ProMP, MAML+TRPO and $RL^2$ with PPO as baselines. They show:  PEARL is 20100x more sampleefficient  the posterior sampling of the latent context variable enables deep exploration that is crucial for sparse reward settings  the inference network could be also a RNN, however it is crucial to train it with uncorrelated transitions instead of trajectories that have high correlated transitions  using a deterministic latent variable, i.e. reducing $q_{\Phi}(z \vert c)$ to a point estimate, leaves the algorithm unable to solve sparse reward navigation tasks which is attributed to the lack of temporally extended exploration. The paper introduces an algorithm that allows to combine meta learning with an offpolicy algorithm that dramatically increases the sampleefficiency compared to onpolicy meta learning approaches. This increases the chance of seeing meta rl in any sort of real world applications. 
[link]
A very simple (but impractical) discrete model of subclonal evolution would include the following events: * Division of a cell to create two cells: * **Mutation** at a location in the genome of the new cells * Cell death at a new timestep * Cell survival at a new timestep Because measurements of mutations are usually taken at one time point, this is taken to be at the end of a time series of these events, where a tiny of subset of cells are observed and a **genotype matrix** $A$ is produced, in which mutations and cells are arbitrarily indexed such that $A_{i,j} = 1$ if mutation $j$ exists in cell $i$. What this matrix allows us to see is the proportion of cells which *both have mutation $j$*. Unfortunately, I don't get to observe $A$, in practice $A$ has been corrupted by IID binary noise to produce $A'$. This paper focuses on difference inference problems given $A'$, including *inferring $A$*, which is referred to as **`noise_elimination`**. The other problems involve inferring only properties of the matrix $A$, which are referred to as: * **`noise_inference`**: predict whether matrix $A$ would satisfy the *three gametes rule*, which asks if a given genotype matrix *does not describe a branching phylogeny* because a cell has inherited mutations from two different cells (which is usually assumed to be impossible under the infinite sites assumption). This can be computed exactly from $A$. * **Branching Inference**: it's possible that all mutations are inherited between the cells observed; in which case there are *no branching events*. The paper states that this can be computed by searching over permutations of the rows and columns of $A$. The problem is to predict from $A'$ if this is the case. In both problems inferring properties of $A$, the authors use fully connected networks with two hidden layers on simulated datasets of matrices. For **`noise_elimination`**, computing $A$ given $A'$, the authors use a network developed for neural machine translation called a [pointer network][pointer]. They also find it necessary to map $A'$ to a matrix $A''$, turning every element in $A'$ to a fixed length row containing the location, mutation status and false positive/false negative rate. Unfortunately, reported results on real datasets are reported only for branching inference and are limited by the restriction on input dimension. The inferred branching probability reportedly matches that reported in the literature. [pointer]: https://arxiv.org/abs/1409.0473 
[link]
This paper is a bit provocative (especially in the light of the recent DeepMind MuZero paper), and poses some interesting questions about the value of modelbased planning. I'm not sure I agree with the overall argument it's making, but I think the experience of reading it made me hone my intuitions around why and when modelbased planning should be useful. The overall argument of the paper is: rather than learning a dynamics model of the environment and then using that model to plan and learn a value/policy function from, we could instead just keep a large replay buffer of actual past transitions, and use that in lieu of modelsampled transitions to further update our reward estimators without having to acquire more actual experience. In this paper's framing, the central value of having a learned model is this ability to update our policy without needing more actual experience, and it argues that actual real transitions from the environment are more reliable and less likely to diverge than transitions from a learned parametric model. It basically sees a big buffer of transitions as an empirical environment model that it can sample from, in a roughly equivalent way to being able to sample transitions from a learnt model. An obvious counterargument to this is the value of models in being able to simulate particular arbitrary trajectories (for example, potential actions you could take from your current point, as is needed for Monte Carlo Tree Search). Simply keeping around a big stock of historical transitions doesn't serve the use case of being able to get a probable next state *for a particular transition*, both because we might not have that state in our data, and because we don't have any way, just given a replay buffer, of knowing that an available state comes after an action if we haven't seen that exact combination before. (And, even if we had, we'd have to have some indexing/lookup mechanism atop the data). I didn't feel like the paper's response to this was all that convincing. It basically just argues that planning with model transitions can theoretically diverge (though acknowledges it empirically often doesn't), and that it's dangerous to update off of "fictional" modeled transitions that aren't grounded in real data. While it's obviously definitionally true that model transitions are in some sense fictional, that's just the basic tradeoff of how modeling works: some ability to extrapolate, but a realization that there's a risk you extrapolate poorly. https://i.imgur.com/8jp22M3.png The paper's empirical contribution to its argument was to argue that in a lowdata setting, modelfree RL (in the form of the "everything but the kitchen sink" Rainbow RL algorithm) with experience replay can outperform a modelbased SimPLe system on Atari. This strikes me as fairly weak support for the paper's overall claim, especially since historically Atari has been difficult to learn good models of when they're learnt in actualobservation pixel space. Nonetheless, I think this push against the utility of modelbased learning is a useful thing to consider if you do think models are useful, because it will help clarify the reasons why you think that's the case. 
[link]
In this tutorial paper, Carl E. Rasmussen gives an introduction to Gaussian Process Regression focusing on the definition, the hyperparameter learning and future research directions. A Gaussian Process is completely defined by its mean function $m(\pmb{x})$ and its covariance function (kernel) $k(\pmb{x},\pmb{x}')$. The mean function $m(\pmb{x})$ corresponds to the mean vector $\pmb{\mu}$ of a Gaussian distribution whereas the covariance function $k(\pmb{x}, \pmb{x}')$ corresponds to the covariance matrix $\pmb{\Sigma}$. Thus, a Gaussian Process $f \sim \mathcal{GP}\left(m(\pmb{x}), k(\pmb{x}, \pmb{x}')\right)$ is a generalization of a Gaussian distribution over vectors to a distribution over functions. A random function vector $\pmb{\mathrm{f}}$ can be generated by a Gaussian Process through the following procedure: 1. Compute the components $\mu_i$ of the mean vector $\pmb{\mu}$ for each input $\pmb{x}_i$ using the mean function $m(\pmb{x})$ 2. Compute the components $\Sigma_{ij}$ of the covariance matrix $\pmb{\Sigma}$ using the covariance function $k(\pmb{x}, \pmb{x}')$ 3. A function vector $\pmb{\mathrm{f}} = [f(\pmb{x}_1), \dots, f(\pmb{x}_n)]^T$ can be drawn from the Gaussian distribution $\pmb{\mathrm{f}} \sim \mathcal{N}\left(\pmb{\mu}, \pmb{\Sigma} \right)$ Applying this procedure to regression, means that the resulting function vector $\pmb{\mathrm{f}}$ shall be drawn in a way that a function vector $\pmb{\mathrm{f}}$ is rejected if it does not comply with the training data $\mathcal{D}$. This is achieved by conditioning the distribution on the training data $\mathcal{D}$ yielding the posterior Gaussian Process $f \rvert \mathcal{D} \sim \mathcal{GP}(m_D(\pmb{x}), k_D(\pmb{x},\pmb{x}'))$ for noisefree observations with the posterior mean function $m_D(\pmb{x}) = m(\pmb{x}) + \pmb{\Sigma}(\pmb{X},\pmb{x})^T \pmb{\Sigma}^{1}(\pmb{\mathrm{f}}  \pmb{\mathrm{m}})$ and the posterior covariance function $k_D(\pmb{x},\pmb{x}')=k(\pmb{x},\pmb{x}')  \pmb{\Sigma}(\pmb{X}, \pmb{x}')$ with $\pmb{\Sigma}(\pmb{X},\pmb{x})$ being a vector of covariances between every training case of $\pmb{X}$ and $\pmb{x}$. Noisy observations $y(\pmb{x}) = f(\pmb{x}) + \epsilon$ with $\epsilon \sim \mathcal{N}(0,\sigma_n^2)$ can be taken into account with a second Gaussian Process with mean $m$ and covariance function $k$ resulting in $f \sim \mathcal{GP}(m,k)$ and $y \sim \mathcal{GP}(m, k + \sigma_n^2\delta_{ii'})$. The figure illustrates the cases of noisy observations (variance at training points) and of noisefree observationshttps://i.imgur.com/BWvsB7T.png (no variance at training points). In the Machine Learning perspective, the mean and the covariance function are parametrised by hyperparameters and provide thus a way to include prior knowledge e.g. knowing that the mean function is a second order polynomial. To find the optimal hyperparameters $\pmb{\theta}$, 1. determine the log marginal likelihood $L= \mathrm{log}(p(\pmb{y} \rvert \pmb{x}, \pmb{\theta}))$, 2. take the first partial derivatives of $L$ w.r.t. the hyperparameters, and 3. apply an optimization algorithm. It should be noted that a regularization term is not necessary for the log marginal likelihood $L$ because it already contains a complexity penalty term. Also, the tradeoff between datafit and penalty is performed automatically. Gaussian Processes provide a very flexible way for finding a suitable regression model. However, they require the high computational complexity $\mathcal{O}(n^3)$ due to the inversion of the covariance matrix. In addition, the generalization of Gaussian Processes to nonGaussian likelihoods remains complicated. 
[link]
Interacting with the environment comes sometimes at a high cost, for example in high stake scenarios like health care or teaching. Thus instead of learning online, we might want to learn from a fixed buffer $B$ of transitions, which is filled in advance from a behavior policy. The authors show that several so called offpolicy algorithms, like DQN and DDPG fail dramatically in this pure offpolicy setting. They attribute this to the extrapolation error, which occurs in the update of a value estimate $Q(s,a)$, where the target policy selects an unfamiliar action $\pi(s')$ such that $(s', \pi(s'))$ is unlikely or not present in $B$. Extrapolation error is caused by the mismatch between the true stateaction visitation distribution of the current policy and the stateaction distribution in $B$ due to:  stateaction pairs (s,a) missing in $B$, resulting in arbitrarily bad estimates of $Q_{\theta}(s, a)$ without sufficient data close to (s,a).  the finiteness of the batch of transition tuples $B$, leading to a biased estimate of the transition dynamics in the Bellman operator $T^{\pi}Q(s,a) \approx \mathbb{E}_{\boldsymbol{s' \sim B}}\left[r + \gamma Q(s', \pi(s')) \right]$  transitions are sampled uniformly from $B$, resulting in a loss weighted w.r.t the frequency of data in the batch: $\frac{1}{\vert B \vert} \sum_{\boldsymbol{(s, a, r, s') \sim B}} \Vert r + \gamma Q(s', \pi(s'))  Q(s, a)\Vert^2$ The proposed algorithm BatchConstrained deep Qlearning (BCQ) aims to choose actions that: 1. minimize distance of taken actions to actions in the batch 2. lead to states contained in the buffer 3. maximizes the value function, where 1. is prioritized over the other two goals to mitigate the extrapolation error. Their proposed algorithm (for continuous environments) consists informally of the following steps that are repeated at each time $t$: 1. update generator model of the state conditional marginal likelihood $P_B^G(a \vert s)$ 2. sample n actions form the generator model 3. perturb each of the sampled actions to lie in a range $\left[\Phi, \Phi \right]$ 4. act according to the argmax of respective Qvalues of perturbed actions 5. update value function The experiments considers Mujoco tasks with four scenarios of batch data creation:  1 million time steps from training a DDPG agent with exploration noise $\mathcal{N}(0,0.5)$ added to the action.This aims for a diverse set of states and actions.  1 million time steps from training a DDPG agent with an exploration noise $\mathcal{N}(0,0.1)$ added to the actions as behavior policy. The batchRL agent and the behavior DDPG are trained concurrently from the same buffer.  1 million transitions from rolling out a already trained DDPG agent  100k transitions from a behavior policy that acts with probability 0.3 randomly and follows otherwise an expert demonstration with added exploration noise $\mathcal{N}(0,0.3)$ I like the fourth choice of behavior policy the most as this captures high stake scenarios like education or medicine the closest, in which training data would be acquired by human experts that are by the nature of humans not optimal but significantly better than learning from scratch. The proposed BCQ algorithm is the only algorithm that is successful across all experiments. It matches or outperforms the behavior policy. Evaluation of the value estimates showcases unstable and diverging value estimates for all algorithms but BCQ that exhibits a stable value function. The paper outlines a very important issue that needs to be tackled in order to use reinforcement learning in real world applications. 
[link]
This paper deals with the question what / how exactly CNNs learn, considering the fact that they usually have more trainable parameters than data points on which they are trained. When the authors write "deep neural networks", they are talking about Inception V3, AlexNet and MLPs. ## Key contributions * Deep neural networks easily fit random labels (achieving a training error of 0 and a test error which is just randomly guessing labels as expected). $\Rightarrow$Those architectures can simply bruteforce memorize the training data. * Deep neural networks fit random images (e.g. Gaussian noise) with 0 training error. The authors conclude that VCdimension / Rademacher complexity, and uniform stability are bad explanations for generalization capabilities of neural networks * The authors give a construction for a 2layer network with $p = 2n+d$ parameters  where $n$ is the number of samples and $d$ is the dimension of each sample  which can easily fit any labeling. (Finite sample expressivity). See section 4. ## What I learned * Any measure $m$ of the generalization capability of classifiers $H$ should take the percentage of corrupted labels ($p_c \in [0, 1]$, where $p_c =0$ is a perfect labeling and $p_c=1$ is totally random) into account: If $p_c = 1$, then $m()$ should be 0, too, as it is impossible to learn something meaningful with totally random labels. * We seem to have built models which work well on image data in general, but not "natural" / meaningful images as we thought. ## Funny > deep neural nets remain mysterious for many reasons > Note that this is not exactly simple as the kernel matrix requires 30GB to store in memory. Nonetheless, this system can be solved in under 3 minutes in on a commodity workstation with 24 cores and 256 GB of RAM with a conventional LAPACK call. ## See also * [Deep Nets Don't Learn Via Memorization](https://openreview.net/pdf?id=rJv6ZgHYg) 
[link]
Proposes a twostage approach for continual learning. An active learning phase and a consolidation phase. The active learning stage optimizes for a specific task that is then consolidated into the knowledge base network via Elastic Weight Consolidation (Kirkpatrick et al., 2016). The active learning phases uses a separate network than the knowledge base, but is not always trained from scratch  authors suggest a heuristic based on tasksimilarity. Improves EWC by deriving a new online method so parameters don’t increase linearly with the number of tasks. Desiderata for a continual learning solution:  A continual learning method should not suffer from catastrophic forgetting. That is, it should be able to perform reasonably well on previously learned tasks.  It should be able to learn new tasks while taking advantage of knowledge extracted from previous tasks, thus exhibiting positive forward transfer to achieve faster learning and/or better final performance.  It should be scalable, that is, the method should be trainable on a large number of tasks.  It should enable positive backward transfer as well, which means gaining improved performance on previous tasks after learning a new task which is similar or relevant.  Finally, it should be able to learn without requiring task labels, and ideally, it should even be applicable in the absence of clear task boundaries. Experiments:  Sequential learning of handwritten characters of 50 alphabets taken from the Omniglot dataset.  Sequential learning of 6 games in the Atari suite (Bellemare et al., 2012) (“Space Invaders”, “Krull”, “Beamrider”, “Hero”, “Stargunner” and “Ms. Pacman”).  8 navigation tasks in 3D environments inspired by experiments with Distral (Teh et al., 2017). 
[link]
In the years before this paper came out in 2017, a number of different graph convolution architectures  which use weightsharing and orderinvariant operations to create representations at nodes in a graph that are contextualized by information in the rest of the graph  had been suggested for learning representations of molecules. The authors of this paper out of Google sought to pull all of these proposed models into a single conceptual framework, for the sake of better comparing and testing the design choices that went into them. All empirical tests were done using the QM9 dataset, where 134,000 molecules have predicted chemical properties attached to them, things like the amount of energy released if bombs are sundered and the energy of electrons at different electron shells. https://i.imgur.com/Mmp8KO6.png An interesting note is that these properties weren't measured empirically, but were simulated by a very expensive quantum simulation, because the former wouldn't be feasible for this large of a dataset. However, this is still a moderately interesting test because, even if we already have the capability to computationally predict these features, a neural network would do much more quickly. And, also, one might aspirationally hope that architectures which learn good representations of molecules for quantum predictions are also useful for tasks with a less available automated prediction mechanism. The framework assumes the existence of "hidden" feature vectors h at each node (atom) in the graph, as well as features that characterize the edges between nodes (whether that characterization comes through sorting into discrete bond categories or through a continuous representation). The features associated with each atom at the lowest input level of the moleculesummarizing networks trained here include: the element ID, the atomic number, whether it accepts electrons or donates them, whether it's in an aromatic system, and which shells its electrons are in. https://i.imgur.com/J7s0q2e.png Given these building blocks, the taxonomy lays out three broad categories of function, each of which different architectures implement in slightly different ways. 1. The Message function, M(). This function is defined with reference to a node w, that the message is coming from, and a node v, that it's being sent to, and is meant to summarize the information coming from w to inform the node representation that will be calculated at v. It takes into account the feature vectors of one or both nodes at the next level down, and sometimes also incorporates feature vectors attached to the edge connecting the two nodes. In a notable example of weight sharing, you'd use the same Message function for every combination of v and w, because you need to be able to process an arbitrary number of pairs, with each v having a different number of neighbors. The simplest example you might imagine here is a simple concatenation of incoming node and edge features; a more typical example from the architectures reviewed is a concatenation followed by a neural network layer. The aggregate message being sent to the receiver node is calculated by summing together the messages from each incoming vector (though it seems like other options are possible; I'm a bit confused why the paper presented summing as the only orderinvariant option). 2. The Update function, U(). This function governs how to take the aggregated message vector sent to a particular node, and combine that with the priorlayer representation at that node, to come up with a nextlayer representation at that node. Similarly, the same Update function weights are shared across all atoms. 3. The Readout function, R(), which takes the finallayer representation of each atom node and aggregates the representations into a final graphlevel representation an orderinvariant way Rather than following in the footsteps of the paper by describing each proposed model type and how it can be described in this framework, I'll instead try to highlight some of the more interesting ways in which design choices differed across previously proposed architectures.  Does the message function being sent from w to v depend on the feature value at both w and v, or just v? To put the question more colloquially, you might imagine w wanting to contextually send different information based on different values of the feature vector at node v, and this extra degree of expressivity (not present in the earliest 2015 paper), seems like a quite valuable addition (in that all subsequent papers include it)  Are the edge features static, categorical things, or are they feature vectors that get iteratively updated in the same way that the node vectors do? For most of the architectures reviewed, the former is true, but the authors found that the highest performance in their tests came from networks with continuous edge vectors, rather than just having different weights for different category types of edge  Is the Readout function something as simple as a summation of all toplevel feature vectors, or is it more complex? Again, the authors found that they got the best performance by using a more complex approach, a Set2Set aggregator, which uses itemtoitem attention within the set of finallayer atom representations to construct an aggregated graplevel embedding The empirical tests within the paper highlight a few more interestingly relevant design choices that are less directly captured by the framework. The first is the fact that it's quite beneficial to explicitly include Hydrogen atoms as part of the graph, rather than just "attaching" them to their nearestby atoms as a count that goes on that atom's feature vector. The second is that it's valuable to start out your edge features with a continuous representation of the spatial distance between atoms, along with an embedding of the bond type. This is particularly worth considering because getting spatial distance data for a molecule requires solving the freeenergy problem to determine its spatial conformation, a costly process. We might ideally prefer a network that can work on bond information alone. The authors do find a nonspatialinformation network that can perform reasonably well  reaching full accuracy on 5 of 13 targets, compared to 11 with spatial information. However, the difference is notable, which, at least from my perspective, begs the question of whether it'd ever be possible to learn representations that can match the performance of spatiallyinformed ones without explicitly providing that information. 
[link]
[code](https://github.com/openai/improvedgan), [demo](http://infinitechamber35121.herokuapp.com/cifarminibatch/1/?), [related](http://www.inference.vc/understandingminibatchdiscriminationingans/) ### Feature matching problem: overtraining on the current discriminator solution: ￼$E_{x \sim p_{\text{data}}}f(x)  E_{z \sim p_{z}(z)}f(G(z))_{2}^{2}$ were f(x) activations intermediate layer in discriminator ### Minibatch discrimination problem: generator to collapse to a single point solution: for each sample i, concatenate to $f(x_i)$ features $b$ measuring its distance to other samples j (i and j are both real or generated samples in same batch): $\sum_j \exp(M_{i, b}  M_{j, b}_{L_1})$ ￼ this generates visually appealing samples very quickly ### Historical averaging problem: SGD fails by going into extended orbits solution: parameters revert to the mean $ \theta  \frac{1}{t} \sum_{i=1}^t \theta[i] ^2$ ￼ ### Onesided label smoothing problem: discriminator vulnerability to adversarial examples solution: discriminator target for positive samples is 0.9 instead of 1 ### Virtual batch normalization problem: using BN cause output of examples in batch to be dependent solution: use reference batch chosen once at start of training and each sample is normalized using itself and the reference. It's expensive so used only on generation ### Assessment of image quality problem: MTurk not reliable solution: use inception model p(yx) to compute ￼$\exp(\mathbb{E}_x \text{KL}(p(y  x)  p(y)))$ on 50K generated images x ### Semisupervised learning use the discriminator to also classify on K labels when known and use all real samples (labels and unlabeled) in the discrimination task ￼$D(x) = \frac{Z(x)}{Z(x) + 1}, \text{ where } Z(x) = \sum_{k=1}^{K} \exp[l_k(x)]$. In this case use feature matching but not minibatch discrimination. It also improves the quality of generated images.
3 Comments
