When it comes to effectiveness of machine learning, more data almost always yields better results--and the healthcare sector is sitting on a data goldmine. McKinsey estimates that big data and machine learning in pharma and medicine could generate a value of up to $100B annually, based on better decision-making, optimized innovation, improved efficiency of research/clinical trials, and new tool creation for physicians, consumers, insurers, and regulators. Where does all this data come from? If we could look at labeled data streams, we might see research and development (R&D); physicians and clinics; patients; caregivers; etc. The array of (at present) disparate origins is part of the issue in synchronizing this information and using it to improve healthcare infrastructure and treatments.

THE next time you visit the local hospital for a chest X-ray, scan, or even a check-up, artificial intelligence (AI) could be having more of a role in your health than you might expect. While we are many years away from a completely automated health service, AI can already help clinicians make better decisions and either augment or even replace human judgments in specific areas of healthcare. Researchers at the John Radcliffe Hospital in the UK have developed an AI diagnostics system that is highly accurate in diagnosing heart disease around 80 percent of the time. At Harvard University, researchers have created a microscope that can detect potentially lethal blood infections. Technologically-based systems help physicians by combing through the gigabytes of data available from journals and textbooks, as well as information from real-time clinical practices.

Low-rank matrix completion (MC) has achieved great success in many real-world data applications. A latent feature model formulation is usually employed and, to improve prediction performance, the similarities between latent variables can be exploited by pairwise learning, e.g., the graph regularized matrix factorization (GRMF) method. However, existing GRMF approaches often use a squared L2 norm to measure the pairwise difference, which may be overly influenced by dissimilar pairs and lead to inferior prediction. To fully empower pairwise learning for matrix completion, we propose a general optimization framework that allows a rich class of (non-)convex pairwise penalty functions. A new and efficient algorithm is further developed to uniformly solve the optimization problem, with a theoretical convergence guarantee. In an important situation where the latent variables form a small number of subgroups, its statistical guarantee is also fully characterized. In particular, we theoretically characterize the complexity-regularized maximum likelihood estimator, as a special case of our framework. It has a better error bound when compared to the standard trace-norm regularized matrix completion. We conduct extensive experiments on both synthetic and real datasets to demonstrate the superior performance of this general framework.

We extend variational autoencoders (VAEs) to collaborative filtering for implicit feedback. This non-linear probabilistic model enables us to go beyond the limited modeling capacity of linear factor models which still largely dominate collaborative filtering research.We introduce a generative model with multinomial likelihood and use Bayesian inference for parameter estimation. Despite widespread use in language modeling and economics, the multinomial likelihood receives less attention in the recommender systems literature. We introduce a different regularization parameter for the learning objective, which proves to be crucial for achieving competitive performance. Remarkably, there is an efficient way to tune the parameter using annealing. The resulting model and learning algorithm has information-theoretic connections to maximum entropy discrimination and the information bottleneck principle. Empirically, we show that the proposed approach significantly outperforms several state-of-the-art baselines, including two recently-proposed neural network approaches, on several real-world datasets. We also provide extended experiments comparing the multinomial likelihood with other commonly used likelihood functions in the latent factor collaborative filtering literature and show favorable results. Finally, we identify the pros and cons of employing a principled Bayesian inference approach and characterize settings where it provides the most significant improvements.

Stochastic convex optimization algorithms are the most popular way to train machine learning models on large-scale data. Scaling up the training process of these models is crucial in many applications, but the most popular algorithm, Stochastic Gradient Descent (SGD), is a serial algorithm that is surprisingly hard to parallelize. In this paper, we propose an efficient distributed stochastic optimization method based on adaptive step sizes and variance reduction techniques. We achieve a linear speedup in the number of machines, small memory footprint, and only a small number of synchronization rounds -- logarithmic in dataset size -- in which the computation nodes communicate with each other. Critically, our approach is a general reduction than parallelizes any serial SGD algorithm, allowing us to leverage the significant progress that has been made in designing adaptive SGD algorithms. We conclude by implementing our algorithm in the Spark distributed framework and exhibit dramatic performance gains on large-scale logistic regression problems.

We present a stochastic algorithm to compute the barycenter of a set of probability distributions under the Wasserstein metric from optimal transport. Unlike previous approaches, our method extends to continuous input distributions and allows the support of the barycenter to be adjusted in each iteration. We tackle the problem without regularization, allowing us to recover a sharp output whose support is contained within the support of the true barycenter. We give examples where our algorithm recovers a more meaningful barycenter than previous work. Our method is versatile and can be extended to applications such as generating super samples from a given distribution and recovering blue noise approximations.

We study the question of fair clustering under the {\em disparate impact} doctrine, where each protected class must have approximately equal representation in every cluster. We formulate the fair clustering problem under both the $k$-center and the $k$-median objectives, and show that even with two protected classes the problem is challenging, as the optimum solution can violate common conventions---for instance a point may no longer be assigned to its nearest cluster center! En route we introduce the concept of fairlets, which are minimal sets that satisfy fair representation while approximately preserving the clustering objective. We show that any fair clustering problem can be decomposed into first finding good fairlets, and then using existing machinery for traditional clustering algorithms. While finding good fairlets can be NP-hard, we proceed to obtain efficient approximation algorithms based on minimum cost flow. We empirically quantify the value of fair clustering on real-world datasets with sensitive attributes.

Clinical notes are text documents that are created by clinicians for each patient encounter. They are typically accompanied by medical codes, which describe the diagnosis and treatment. Annotating these codes is labor intensive and error prone; furthermore, the connection between the codes and the text is not annotated, obscuring the reasons and details behind specific diagnoses and treatments. We present an attentional convolutional network that predicts medical codes from clinical text. Our method aggregates information across the document using a convolutional neural network, and uses an attention mechanism to select the most relevant segments for each of the thousands of possible codes. The method is accurate, achieving precision @ 8 of 0.7 and a Micro-F1 of 0.52, which are both significantly better than the prior state of the art. Furthermore, through an interpretability evaluation by a physician, we show that the attention mechanism identifies meaningful explanations for each code assignment.

This paper investigates recently proposed approaches for defending against adversarial examples and evaluating adversarial robustness. The existence of adversarial examples in trained neural networks reflects the fact that expected risk alone does not capture the model's performance against worst-case inputs. We motivate the use of adversarial risk as an objective, although it cannot easily be computed exactly. We then frame commonly used attacks and evaluation metrics as defining a tractable surrogate objective to the true adversarial risk. This suggests that models may be obscured to adversaries, by optimizing this surrogate rather than the true adversarial risk. We demonstrate that this is a significant problem in practice by repurposing gradient-free optimization techniques into adversarial attacks, which we use to decrease the accuracy of several recently proposed defenses to near zero. Our hope is that our formulations and results will help researchers to develop more powerful defenses.

We propose a novel, projection based way to incorporate the conditional information into the discriminator of GANs that respects the role of the conditional information in the underlining probabilistic model. This approach is in contrast with most frameworks of conditional GANs used in application today, which use the conditional information by concatenating the (embedded) conditional vector to the feature vectors. With this modification, we were able to significantly improve the quality of the class conditional image generation on ILSVRC2012 (ImageNet) 1000-class image dataset from the current state-of-the-art result, and we achieved this with a single pair of a discriminator and a generator. We were also able to extend the application to super-resolution and succeeded in producing highly discriminative super-resolution images. This new structure also enabled high quality category transformation based on parametric functional transformation of conditional batch normalization layers in the generator.