In this work, we present an interesting attempt on mixture generation: absorbing different image concepts (e.g., content and style) from different domains and thus generating a new domain with learned concepts. In particular, we propose a mixture generative adversarial network (MIXGAN). MIXGAN learns concepts of content and style from two domains respectively, and thus can join them for mixture generation in a new domain, i.e., generating images with content from one domain and style from another. MIXGAN overcomes the limitation of current GAN-based models which either generate new images in the same domain as they observed in training stage, or require off-the-shelf content templates for transferring or translation. Extensive experimental results demonstrate the effectiveness of MIXGAN as compared to related state-of-the-art GAN-based models.

Generating datasets that "look like" given real ones is an interesting tasks for healthcare applications of ML and many other fields of science and engineering. In this paper we propose a new method of general application to binary datasets based on a method for learning the parameters of a latent variable moment that we have previously used for clustering patient datasets. We compare our method with a recent proposal (MedGan) based on generative adversarial methods and find that the synthetic datasets we generate are globally more realistic in at least two senses: real and synthetic instances are harder to tell apart by Random Forests, and the MMD statistic. The most likely explanation is that our method does not suffer from the "mode collapse" which is an admitted problem of GANs. Additionally, the generative models we generate are easy to interpret, unlike the rather obscure GANs. Our experiments are performed on two patient datasets containing ICD-9 diagnostic codes: the publicly available MIMIC-III dataset and a dataset containing admissions for congestive heart failure during 7 years at Hospital de Sant Pau in Barcelona.

Many machine learning problems involve Monte Carlo gradient estimators. As a prominent example, we focus on Monte Carlo variational inference (MCVI) in this paper. The performance of MCVI crucially depends on the variance of its stochastic gradients. We propose variance reduction by means of Quasi-Monte Carlo (QMC) sampling. QMC replaces N i.i.d. samples from a uniform probability distribution by a deterministic sequence of samples of length N. This sequence covers the underlying random variable space more evenly than i.i.d. draws, reducing the variance of the gradient estimator. With our novel approach, both the score function and the reparameterization gradient estimators lead to much faster convergence. We also propose a new algorithm for Monte Carlo objectives, where we operate with a constant learning rate and increase the number of QMC samples per iteration. We prove that this way, our algorithm can converge asymptotically at a faster rate than SGD. We furthermore provide theoretical guarantees on QMC for Monte Carlo objectives that go beyond MCVI, and support our findings by several experiments on large-scale data sets from various domains.

Differential privacy comes equipped with multiple analytical tools for the design of private data analyses. One important tool is the so called "privacy amplification by subsampling" principle, which ensures that a differentially private mechanism run on a random subsample of a population provides higher privacy guarantees than when run on the entire population. Several instances of this principle have been studied for different random subsampling methods, each with an ad-hoc analysis. In this paper we present a general method that recovers and improves prior analyses, yields lower bounds and derives new instances of privacy amplification by subsampling. Our method leverages a characterization of differential privacy as a divergence which emerged in the program verification community. Furthermore, it introduces new tools, including advanced joint convexity and privacy profiles, which might be of independent interest.

Multi-step temporal difference (TD) learning is an important approach in reinforcement learning, as it unifies one-step TD learning with Monte Carlo methods in a way where intermediate algorithms can outperform either extreme. They address a bias-variance trade off between reliance on current estimates, which could be poor, and incorporating longer sampled reward sequences into the updates. Especially in the off-policy setting, where the agent aims to learn about a policy different from the one generating its behaviour, the variance in the updates can cause learning to diverge as the number of sampled rewards used in the estimates increases. In this paper, we introduce per-decision control variates for multi-step TD algorithms, and compare them to existing methods. Our results show that including the control variates can greatly improve performance on both on and off-policy multi-step temporal difference learning tasks.

An unsupervised learning classification model is described. It achieves classification error probability competitive with that of popular supervised learning classifiers such as SVM or kNN. The model is based on the incremental execution of small step shift and rotation operations upon selected discriminative hyperplanes at the arrival of input samples. When applied, in conjunction with a selected feature extractor, to a subset of the ImageNet dataset benchmark, it yields 6.2 % Top 3 probability of error; this exceeds by merely about 2 % the result achieved by (supervised) k-Nearest Neighbor, both using same feature extractor. This result may also be contrasted with popular unsupervised learning schemes such as k-Means which is shown to be practically useless on same dataset.

Dynamic treatment recommendation systems based on large-scale electronic health records (EHRs) become a key to successfully improve practical clinical outcomes. Prior relevant studies recommend treatments either use supervised learning (e.g. matching the indicator signal which denotes doctor prescriptions), or reinforcement learning (e.g. maximizing evaluation signal which indicates cumulative reward from survival rates). However, none of these studies have considered to combine the benefits of supervised learning and reinforcement learning. In this paper, we propose Supervised Reinforcement Learning with Recurrent Neural Network (SRL-RNN), which fuses them into a synergistic learning framework. Specifically, SRL-RNN applies an off-policy actor-critic framework to handle complex relations among multiple medications, diseases and individual characteristics. The "actor" in the framework is adjusted by both the indicator signal and evaluation signal to ensure effective prescription and low mortality. RNN is further utilized to solve the Partially-Observed Markov Decision Process (POMDP) problem due to the lack of fully observed states in real world applications. Experiments on the publicly real-world dataset, i.e., MIMIC-3, illustrate that our model can reduce the estimated mortality, while providing promising accuracy in matching doctors' prescriptions.

Domestic Violence (DV) is considered as big social issue and there exists a strong relationship between DV and health impacts of the public. Existing research studies have focused on social media to track and analyse real world events like emerging trends, natural disasters, user sentiment analysis, political opinions, and health care. However there is less attention given on social welfare issues like DV and its impact on public health. Recently, the victims of DV turned to social media platforms to express their feelings in the form of posts and seek the social and emotional support, for sympathetic encouragement, to show compassion and empathy among public. But, it is difficult to mine the actionable knowledge from large conversational datasets from social media due to the characteristics of high dimensions, short, noisy, huge volume, high velocity, and so on. Hence, this paper will propose a novel framework to model and discover the various themes related to DV from the public domain. The proposed framework would possibly provide unprecedentedly valuable information to the public health researchers, national family health organizations, government and public with data enrichment and consolidation to improve the social welfare of the community. Thus provides actionable knowledge by monitoring and analysing continuous and rich user generated content.

Online advertisement is the main source of revenue for Internet business. Advertisers are typically ranked according to a score that takes into account their bids and potential click-through rates(eCTR). Generally, the likelihood that a user clicks on an ad is often modeled by optimizing for the click through rates rather than the performance of the auction in which the click through rates will be used. This paper attempts to eliminate this dis-connection by proposing loss functions for click modeling that are based on final auction performance.In this paper, we address two feasible metrics (AUC^R and SAUC) to evaluate the on-line RPM (revenue per mille) directly rather than the CTR. And then, we design an explicit ranking function by incorporating the calibration fac-tor and price-squashed factor to maximize the revenue. Given the power of deep networks, we also explore an implicit optimal ranking function with deep model. Lastly, various experiments with two real world datasets are presented. In particular, our proposed methods perform better than the state-of-the-art methods with regard to the revenue of the platform.

Large labeled datasets for supervised learning are frequently constructed by assigning each instance to multiple human evaluators, and this leads to disagreement in the labels associated with a single instance. Here we consider the question of predicting the level of disagreement for a given instance, and we find an interesting phenomenon: direct prediction of uncertainty performs better than the two-step process of training a classifier and then using the classifier outputs to derive an uncertainty. We show stronger performance for predicting disagreement via this direct method both in a synthetic setting whose parameters we can fully control, and in a paradigmatic healthcare application involving multiple labels assigned by medical domain experts. We further show implications for allocating additional labeling effort toward instances with the greatest levels of predicted disagreement.