Time series forecasting is one of the most active research topics. Machine learning methods have been increasingly adopted to solve these predictive tasks. However, in a recent work, evidence was shown that these approaches systematically present a lower predictive performance relative to simple statistical methods. In this work, we counter these results. We show that these are only valid under an extremely low sample size. Using a learning curve method, our results suggest that machine learning methods improve their relative predictive performance as the sample size grows.

Artificial intelligence is known as the most effective technological field for rapid developments shaping the future of the world. Even today, it is possible to see intense use of intelligence systems in all fields of the life. Although advantages of the Artificial Intelligence are widely observed, there is also a dark side employing efforts to design hacking oriented techniques against Artificial Intelligence. Thanks to such techniques, it is possible to trick intelligent systems causing directed results for unsuccessful outputs. That is critical for also cyber wars of the future as it is predicted that the wars will be done unmanned, autonomous intelligent systems. Moving from the explanations, objective of this study is to provide information regarding adversarial examples threatening the Artificial Intelligence and focus on details of some techniques, which are used for creating adversarial examples. Adversarial examples are known as training data, which can trick a Machine Learning technique to learn incorrectly about the target problem and cause an unsuccessful or maliciously directed intelligent system at the end. The study enables the readers to learn enough about details of recent techniques for creating adversarial examples.

Despite significant recent progress, machine vision systems lag considerably behind their biological counterparts in performance, scalability, and robustness. A distinctive hallmark of the brain is its ability to automatically discover and model objects, at multiscale resolutions, from repeated exposures to unlabeled contextual data and then to be able to robustly detect the learned objects under various nonideal circumstances, such as partial occlusion and different view angles. Replication of such capabilities in a machine would require three key ingredients: (i) access to large-scale perceptual data of the kind that humans experience, (ii) flexible representations of objects, and (iii) an efficient unsupervised learning algorithm. The Internet fortunately provides unprecedented access to vast amounts of visual data. This paper leverages the availability of such data to develop a scalable framework for unsupervised learning of object prototypes--brain-inspired flexible, scale, and shift invariant representations of deformable objects (e.g., humans, motorcycles, cars, airplanes) comprised of parts, their different configurations and views, and their spatial relationships. Computationally, the object prototypes are represented as geometric associative networks using probabilistic constructs such as Markov random fields. We apply our framework to various datasets and show that our approach is computationally scalable and can construct accurate and operational part-aware object models much more efficiently than in much of the recent computer vision literature. We also present efficient algorithms for detection and localization in new scenes of objects and their partial views.

Graph embeddings, a class of dimensionality reduction techniques designed for relational data, have proven useful in exploring and modeling network structure. Most dimensionality reduction methods allow out-of-sample extensions, by which an embedding can be applied to observations not present in the training set. Applied to graphs, the out-of-sample extension problem concerns how to compute the embedding of a vertex that is added to the graph after an embedding has already been computed. In this paper, we consider the out-of-sample extension problem for two graph embedding procedures: the adjacency spectral embedding and the Laplacian spectral embedding. In both cases, we prove that when the underlying graph is generated according to a latent space model called the random dot product graph, which includes the popular stochastic block model as a special case, an out-of-sample extension based on a least-squares objective obeys a central limit theorem about the true latent position of the out-of-sample vertex. In addition, we prove a concentration inequality for the out-of-sample extension of the adjacency spectral embedding based on a maximum-likelihood objective. Our results also yield a convenient framework in which to analyze trade-offs between estimation accuracy and computational expense, which we explore briefly.

We propose a deep amortized clustering (DAC), a neural architecture which learns to cluster datasets efficiently using a few forward passes. DAC implicitly learns what makes a cluster, how to group data points into clusters, and how to count the number of clusters in datasets. DAC is meta-learned using labelled datasets for training, a process distinct from traditional clustering algorithms which usually require hand-specified prior knowledge about cluster shapes/structures. We empirically show, on both synthetic and image data, that DAC can efficiently and accurately cluster new datasets coming from the same distribution used to generate training datasets.

Conventional inclusion criteria used in osteoarthritis clinical trials are not very effective in selecting patients who would benefit the most from a therapy under test. Typically these criteria select majority of patients who show no or limited disease progression during a short evaluation window of the study. As a consequence, less insight on the relative effect of the treatment can be gained from the collected data, and the efforts and resources invested in running the study are not paying off. This could be avoided, if selection criteria were more predictive of the future disease progression. In this article, we formulated the patient selection problem as a multi-class classification task, with classes based on clinically relevant measures of progression (over a time scale typical for clinical trials). Using data from two long-term knee osteoarthritis studies OAI and CHECK, we tested multiple algorithms and learning process configurations (including multi-classifier approaches, cost-sensitive learning, and feature selection), to identify the best performing machine learning models. We examined the behaviour of the best models, with respect to prediction errors and the impact of used features, to confirm their clinical relevance. We found that the model-based selection outperforms the conventional inclusion criteria, reducing by 20-25% the number of patients who show no progression and making the representation of the patient categories more even. This result indicates that our machine learning approach could lead to efficiency improvements in clinical trial design.

Limited data access is a substantial barrier to data-driven networking research and development. Although many organizations are motivated to share data, privacy concerns often prevent the sharing of proprietary data, including between teams in the same organization and with outside stakeholders (e.g., researchers, vendors). Many researchers have therefore proposed synthetic data models, most of which have not gained traction because of their narrow scope. In this work, we present DoppelGANger, a synthetic data generation framework based on generative adversarial networks (GANs). DoppelGANger is designed to work on time series datasets with both continuous features (e.g. traffic measurements) and discrete ones (e.g., protocol name). Modeling time series and mixed-type data is known to be difficult; DoppelGANger circumvents these problems through a new conditional architecture that isolates the generation of metadata from time series, but uses metadata to strongly influence time series generation. We demonstrate the efficacy of DoppelGANger on three real-world datasets. We show that DoppelGANger achieves up to 43% better fidelity than baseline models, and captures structural properties of data that baseline methods are unable to learn. Additionally, it gives data holders an easy mechanism for protecting attributes of their data without substantial loss of data utility.

Jayanth Regatti Gaurav Tendolkar Yi Zhou Abhishek Gupta Yingbin Liang Abstract -- The performance of fully synchronized distributed systems has faced a bottleneck due to the big data trend, under which asynchronous distributed systems are becoming a major popularity due to their powerful scalability. In this paper, we study the generalization performance of stochastic gradient descent (SGD) on a distributed asynchronous system. The system consists of multiple worker machines that compute stochastic gradients which are further sent to and aggregated on a common parameter server to update the variables, and the communication in the system suffers from possible delays. Under the algorithm stability framework, we prove that distributed asynchronous SGD generalizes well given enough data samples in the training optimization. In particular, our results suggest to reduce the learning rate as we allow more asynchrony in the distributed system. Such adaptive learning rate strategy improves the stability of the distributed algorithm and reduces the corresponding generalization error . Then, we confirm our theoretical findings via numerical experiments. I NTRODUCTION Stochastic gradient descent (SGD) and its variants (e.g., Adagrad, Adam, etc) have been very effective in solving many challenging machine learning problems such as training deep neural networks. In practice, the solution found by SGD via solving an empirical risk minimization problem typically has good generalization performance on the test dataset.

We study the Kronecker product regression problem, in which the design matrix is a Kronecker product of two or more matrices. Given $A_i \in \mathbb{R}^{n_i \times d_i}$ for $i=1,2,\dots,q$ where $n_i \gg d_i$ for each $i$, and $b \in \mathbb{R}^{n_1 n_2 \cdots n_q}$, let $\mathcal{A} = A_1 \otimes A_2 \otimes \cdots \otimes A_q$. Then for $p \in [1,2]$, the goal is to find $x \in \mathbb{R}^{d_1 \cdots d_q}$ that approximately minimizes $\|\mathcal{A}x - b\|_p$. Recently, Diao, Song, Sun, and Woodruff (AISTATS, 2018) gave an algorithm which is faster than forming the Kronecker product $\mathcal{A}$ Specifically, for $p=2$ their running time is $O(\sum_{i=1}^q \text{nnz}(A_i) + \text{nnz}(b))$, where nnz$(A_i)$ is the number of non-zero entries in $A_i$. Note that nnz$(b)$ can be as large as $n_1 \cdots n_q$. For $p=1,$ $q=2$ and $n_1 = n_2$, they achieve a worse bound of $O(n_1^{3/2} \text{poly}(d_1d_2) + \text{nnz}(b))$. In this work, we provide significantly faster algorithms. For $p=2$, our running time is $O(\sum_{i=1}^q \text{nnz}(A_i) )$, which has no dependence on nnz$(b)$. For $p<2$, our running time is $O(\sum_{i=1}^q \text{nnz}(A_i) + \text{nnz}(b))$, which matches the prior best running time for $p=2$. We also consider the related all-pairs regression problem, where given $A \in \mathbb{R}^{n \times d}, b \in \mathbb{R}^n$, we want to solve $\min_{x} \|\bar{A}x - \bar{b}\|_p$, where $\bar{A} \in \mathbb{R}^{n^2 \times d}, \bar{b} \in \mathbb{R}^{n^2}$ consist of all pairwise differences of the rows of $A,b$. We give an $O(\text{nnz}(A))$ time algorithm for $p \in[1,2]$, improving the $\Omega(n^2)$ time needed to form $\bar{A}$. Finally, we initiate the study of Kronecker product low rank and low $t$-rank approximation. For input $\mathcal{A}$ as above, we give $O(\sum_{i=1}^q \text{nnz}(A_i))$ time algorithms, which is much faster than computing $\mathcal{A}$.

Working with any gradient-based machine learning algorithm involves the tedious task of tuning the optimizer's hyperparameters, such as the learning rate. There exist many techniques for automated hyperparameter optimization, but they typically introduce even more hyperparameters to control the hyperparameter optimization process. We propose to instead learn the hyperparameters themselves by gradient descent, and furthermore to learn the hyper-hyperparameters by gradient descent as well, and so on ad infinitum. As these towers of gradient-based optimizers grow, they become significantly less sensitive to the choice of top-level hyperparameters, hence decreasing the burden on the user to search for optimal values.