The task of representing entire graphs has seen a surge of prominent results, mainly due to learning convolutional neural networks (CNNs) on graph-structured data. While CNNs demonstrate state-of-the-art performance in graph classification task, such methods are supervised and therefore steer away from the original problem of network representation in task-agnostic manner. Here, we coherently propose an approach for embedding entire graphs and show that our feature representations with SVM classifier increase classification accuracy of CNN algorithms and traditional graph kernels. For this we describe a recently discovered graph object, anonymous walk, on which we design task-independent algorithms for learning graph representations in explicit and distributed way. Overall, our work represents a new scalable unsupervised learning of state-of-the-art representations of entire graphs.

Analyzing large-scale, multi-experiment studies requires scientists to test each experimental outcome for statistical significance and then assess the results as a whole. We present Black Box FDR (BB-FDR), an empirical-Bayes method for analyzing multi-experiment studies when many covariates are gathered per experiment. BB-FDR learns a series of black box predictive models to boost power and control the false discovery rate (FDR) at two stages of study analysis. In Stage 1, it uses a deep neural network prior to report which experiments yielded significant outcomes. In Stage 2, a separate black box model of each covariate is used to select features that have significant predictive power across all experiments. In benchmarks, BB-FDR outperforms competing state-of-the-art methods in both stages of analysis. We apply BB-FDR to two real studies on cancer drug efficacy. For both studies, BB-FDR increases the proportion of significant outcomes discovered and selects variables that reveal key genomic drivers of drug sensitivity and resistance in cancer.

Neural message passing on molecular graphs is one of the most promising methods for predicting formation energy and other properties of molecules and materials. In this work we extend the neural message passing model with an edge update network which allows the information exchanged between atoms to depend on the hidden state of the receiving atom. We benchmark the proposed model on three publicly available datasets (QM9, The Materials Project and OQMD) and show that the proposed model yields superior prediction of formation energies and other properties on all three datasets in comparison with the best published results. Furthermore we investigate different methods for constructing the graph used to represent crystalline structures and we find that using a graph based on K-nearest neighbors achieves better prediction accuracy than using maximum distance cutoff or the Voronoi tessellation graph.

We study the complexity of the entire regularization path for least squares regression with 1-norm penalty, known as the Lasso. Every regression parameter in the Lasso changes linearly as a function of the regularization value. The number of changes is regarded as the Lasso's complexity. Experimental results using exact path following exhibit polynomial complexity of the Lasso in the problem size. Alas, the path complexity of the Lasso on artificially designed regression problems is exponential. We use smoothed analysis as a mechanism for bridging the gap between worst case settings and the de facto low complexity. Our analysis assumes that the observed data has a tiny amount of intrinsic noise. We then prove that the Lasso's complexity is polynomial in the problem size. While building upon the seminal work of Spielman and Teng on smoothed complexity, our analysis is morally different as it is divorced from specific path following algorithms. We verify the validity of our analysis in experiments with both worst case settings and real datasets. The empirical results we obtain closely match our analysis.

We provide theoretical investigation of curriculum learning in the context of stochastic gradient descent when optimizing the convex linear regression loss. We prove that the rate of convergence of an ideal curriculum learning method is monotonically increasing with the difficulty of the examples. Moreover, among all equally difficult points, convergence is faster when using points which incur higher loss with respect to the current hypothesis. We then analyze curriculum learning in the context of training a CNN. We describe a method which infers the curriculum by way of transfer learning from another network, pre-trained on a different task. While this approach can only approximate the ideal curriculum, we observe empirically similar behavior to the one predicted by the theory, namely, a significant boost in convergence speed at the beginning of training. When the task is made more difficult, improvement in generalization performance is also observed. Finally, curriculum learning exhibits robustness against unfavorable conditions such as excessive regularization.

The last few years have seen extensive empirical study of the robustness of neural networks, with a concerning conclusion: several state-of-the-art approaches are highly sensitive to adversarial perturbations of their inputs. There has been an accompanying surge of interest in learning including defense mechanisms against specific adversaries, known as adversarial training. Despite some impressive advances, little remains known on how to best frame a resource-bounded adversary so that it can be severely detrimental to learning, a non-trivial problem which entails at a minimum the choice of loss and classifiers. We suggest here a formal answer to this question, and pin down a simple sufficient property for any given class of adversaries to be detrimental to learning. This property involves a central measure of "harmfulness" which generalizes the well-known class of integral probability metrics, and thus the maximum mean discrepancy. A key feature of our result is that it holds for all proper losses, and for a popular subset of these, the optimisation of this central measure appears to be \textit{independent of the loss}. We then deliver a sufficient condition for this sufficient property to hold for Lipschitz classifiers, which relies on framing it into optimal transport theory. We finally deliver a negative boosting result which shows how weakly contractive adversaries for a RKHS can be combined to build a maximally detrimental adversary, show that some implemented existing adversaries involve proxies of our optimal transport adversaries and finally provide a toy experiment assessing such adversaries in a simple context, displaying that additional robustness on testing can be granted through adversarial training.

First, we need to understand what is a Markov chain. Consider the following weather example from Wikipedia. Suppose that weather on any given day can be classified into two states only: sunny and rainy. Since, the next day's weather is either sunny or rainy it follows that: Q1: If the weather is sunny today then what is the weather likely to be tomorrow? A1: Since, we do not know what is going to happen for sure, the best we can say is that there is a $90\%$ chance that it is likely to be sunny and $10\%$ that it will be rainy.

Quants are in the business of making helpful assumptions around modelling the characteristics of an asset. But when it comes to interest rates, many of those simplifying conventions tend to break down. That has prompted a growing number of quants to explore the use of machine-learning techniques to better predict the term structure of interest rates. For instance, it is not uncommon to model stock price returns by assuming they are driven by a normal distribution and a volatility that is independent of the level of the stock. But movements in interest rates have been shown to depend heavily on the absolute level of rates at a given point in time.

There are many ways to reduce trading risk through hedging. Funds typically use futures and options to hedge each trade. Similar to insurance, this safety net comes at a price. Using an AI-based strategy, though, there is a way to protect a position at a much lower cost. Before McDonald's could introduce Chicken McNuggets, they had to hedge against the cost of chicken. If chicken prices rose dramatically, they would no longer be able to offer the product.

As a response to this sort of criticism, many have promoted parameter estimation as a better method over hypothesis testing. For example, you could estimate the difference in the treatment and placebo groups, along with the 95% confidence interval as a measure of the uncertainty in that estimate. However, confidence intervals are often misinterpreted as meaning there is a X% change the parameter falls in the interval. Instead, the correct interpretation is obtuse: if you did your experiment an infinite number of times and calculated the confidence interval for each of those experiments, then X% of the time the X% confidence interval would contain the true parameter. For any one experiment though, there is no probability calculated to tell you if your confidence interval actually contains the true parameter, the parameter is either in the interval or not.