The United States is engaged in an increasingly bitter trade war with China. And while American companies like Google and Amazon are now leaders in A.I., experts in the field are concerned that China could surpass the United States in the development of technologies that will power surveillance systems and autonomous weapons as well as driverless cars and a wide range of internet services. In July 2017, Chinese unveiled a plan to become the world leader in A.I., aiming to create an industry worth $150 billion to its economy by 2030, and two Chinese cities promised to invest $7 billion in the effort. Other governments, too, began making large investments, including South Korea, Britain, France and Canada. In the United States, the Defense Department has accelerated efforts to embrace A.I., shifting $75 million of its annual budget to a new office that will develop these technologies. Other government agencies also have major projects in the works.

Graph based semi-supervised learning (GSSL) has intuitive representation and can be improved by exploiting the matrix calculation. However, it has to perform iterative optimization to achieve a preset objective, which usually leads to low efficiency. Another inconvenience lying in GSSL is that when new data come, the graph construction and the optimization have to be conducted all over again. We propose a sound assumption, arguing that: the neighboring data points are not in peer-to-peer relation, but in a partial-ordered relation induced by the local density and distance between the data; and the label of a center can be regarded as the contribution of its followers. Starting from the assumption, we develop a highly efficient non-iterative label propagation algorithm based on a novel data structure named as optimal leading forest (LaPOLeaF). The major weaknesses of the traditional GSSL are addressed by this study. We further scale LaPOLeaF to accommodate big data by utilizing block distance matrix technique, parallel computing, and Locality-Sensitive Hashing (LSH). Experiments on large datasets have shown the promising results of the proposed methods.

Due to massive amounts of data distributed across multiple locations, distributed machine learning has attracted a lot of research interests. Alternating Direction Method of Multipliers (ADMM) is a powerful method of designing distributed machine learning algorithm, whereby each agent computes over local datasets and exchanges computation results with its neighbor agents in an iterative procedure. There exists significant privacy leakage during this iterative process if the local data is sensitive. In this paper, we propose a differentially private ADMM algorithm (P-ADMM) to provide dynamic zero-concentrated differential privacy (dynamic zCDP), by inserting Gaussian noise with linearly decaying variance. We prove that P-ADMM has the same convergence rate compared to the non-private counterpart, i.e., $\mathcal{O}(1/K)$ with $K$ being the number of iterations and linear convergence for general convex and strongly convex problems while providing differentially private guarantee. Moreover, through our experiments performed on real-world datasets, we empirically show that P-ADMM has the best-known performance among the existing differentially private ADMM based algorithms.

In this work, we have proposed several enhancements to improve the performance of any facial emotion recognition (FER) system. We believe that the changes in the positions of the fiducial points and the intensities capture the crucial information regarding the emotion of a face image. We propose the use of the gradient and the Laplacian of the input image together with the original input into a convolutional neural network (CNN). These modifications help the network learn additional information from the gradient and Laplacian of the images. However, the plain CNN is not able to extract this information from the raw images. We have performed a number of experiments on two well known datasets KDEF and FERplus. Our approach enhances the already high performance of state-of-the-art FER systems by 3 to 5%.

Data privacy is an important concern in machine learning, and is fundamentally at odds with the task of training useful learning models, which typically require the acquisition of large amounts of private user data. One possible way of fulfilling the machine learning task while preserving user privacy is to train the model on a transformed, noisy version of the data, which does not reveal the data itself directly to the training procedure. In this work, we analyze the privacy-utility trade-off of two such schemes for the problem of linear regression: additive noise, and random projections. In contrast to previous work, we consider a recently proposed notion of differential privacy that is based on conditional mutual information (MI-DP), which is stronger than the conventional $(\epsilon, \delta)$-differential privacy, and use relative objective error as the utility metric. We find that projecting the data to a lower-dimensional subspace before adding noise attains a better trade-off in general. We also make a connection between privacy problem and (non-coherent) SIMO, which has been extensively studied in wireless communication, and use tools from there for the analysis. We present numerical results demonstrating the performance of the schemes.

Many modern neural network architectures are trained in an overparameterized regime where the parameters of the model exceed the size of the training dataset. Sufficiently overparameterized neural network architectures in principle have the capacity to fit any set of labels including random noise. However, given the highly nonconvex nature of the training landscape it is not clear what level and kind of overparameterization is required for first order methods to converge to a global optima that perfectly interpolate any labels. A number of recent theoretical works have shown that for very wide neural networks where the number of hidden units is polynomially large in the size of the training data gradient descent starting from a random initialization does indeed converge to a global optima. However, in practice much more moderate levels of overparameterization seems to be sufficient and in many cases overparameterized models seem to perfectly interpolate the training data as soon as the number of parameters exceed the size of the training data by a constant factor. Thus there is a huge gap between the existing theoretical literature and practical experiments. In this paper we take a step towards closing this gap. Focusing on shallow neural nets and smooth activations, we show that (stochastic) gradient descent when initialized at random converges at a geometric rate to a nearby global optima as soon as the square-root of the number of network parameters exceeds the size of the training data. Our results also benefit from a fast convergence rate and continue to hold for non-differentiable activations such as Rectified Linear Units (ReLUs).

We prove that α-loss has an equivalent margin-based form and is classification-calibrated, two desirable properties for a good surrogate loss function for the ideal yet intractable 0-1 loss. For logistic regression-based classification, we provide an upper bound on the difference between the empirical and expected risk for α-loss by exploiting its Lipschitzianity along with recent results on the landscape features of empirical risk functions. Finally, we show that α-loss with α 2 performs better than log-loss on MNIST for logistic regression. I. INTRODUCTION In learning theory, the performance of a classification algorithm interms of accuracy, tractability, and convergence guarantees is contingent on the choice of a loss function. Consider a feature vector X X, an unknown finite label Y Y, and a hypothesis test h: X Y. The canonical 0-1 loss, given by 1[h(X) Y ], is considered an ideal loss function that captures the probability of incorrectly guessing the true label Y using h(X).

In this paper, we analyze PAC learnability from labels produced by crowdsourcing. In our setting, unlabeled examples are drawn from a distribution and labels are crowdsourced from workers who operate under classification noise, each with their own noise parameter. We develop an end-to-end crowdsourced PAC learning algorithm that takes unlabeled data points as input and outputs a trained classifier. Our three-step algorithm incorporates majority voting, pure-exploration bandits, and noisy-PAC learning. We prove several guarantees on the number of tasks labeled by workers for PAC learning in this setting and show that our algorithm improves upon the baseline by reducing the total number of tasks given to workers. We demonstrate the robustness of our algorithm by exploring its application to additional realistic crowdsourcing settings.

Variational autoencoders are powerful algorithms for identifying dominant latent structure in a single dataset. In many applications, however, we are interested in modeling latent structure and variation that are enriched in a target dataset compared to some background---e.g. enriched in patients compared to the general population. Contrastive learning is a principled framework to capture such enriched variation between the target and background, but state-of-the-art contrastive methods are limited to linear models. In this paper, we introduce the contrastive variational autoencoder (cVAE), which combines the benefits of contrastive learning with the power of deep generative models. The cVAE is designed to identify and enhance salient latent features. The cVAE is trained on two related but unpaired datasets, one of which has minimal contribution from the salient latent features. The cVAE explicitly models latent features that are shared between the datasets, as well as those that are enriched in one dataset relative to the other, which allows the algorithm to isolate and enhance the salient latent features. The algorithm is straightforward to implement, has a similar run-time to the standard VAE, and is robust to noise and dataset purity. We conduct experiments across diverse types of data, including gene expression and facial images, showing that the cVAE effectively uncovers latent structure that is salient in a particular analysis.

Online detection of instantaneous changes in the generative process of a data sequence generally focuses on retrospective inference of such change points without considering their future occurrences. We extend the Bayesian Online Change Point Detection algorithm to also infer the number of time steps until the next change point (i.e., the residual time). This enables us to handle observation models which depend on the total segment duration, which is useful to model data sequences with temporal scaling. In addition, we extend the model by removing the i.i.d. assumption on the observation model parameters. The resulting inference algorithm for segment detection can be deployed in an online fashion, and we illustrate applications to synthetic and to two medical real-world data sets.