Intelligent features in email service applications aim to increase productivity by helping people organize their folders, compose their emails and respond to pending tasks.In this work, we explore a new application, Smart-To-Do, that helps users with task management over emails.We introduce a new task and dataset for automatically generating To-Do items from emails where the sender has promised to perform an action.We design a two-stage process leveraging recent advances in neural text generation and sequenceto-sequence learning, obtaining BLEU and ROUGE scores of 0.23 and 0.63 for this task.To the best of our knowledge, this is the first work to address the problem of composing To-Do items from emails.

Estimation of information theoretic quantities such as mutual information and its conditional variant has drawn interest in recent times owing to their multifaceted applications. Newly proposed neural estimators for these quantities have overcome severe drawbacks of classical $k$NN-based estimators in high dimensions. In this work, we focus on conditional mutual information (CMI) estimation by utilizing its formulation as a \textit{minmax} optimization problem. Such a formulation leads to a joint training procedure similar to that of generative adversarial networks. We find that our proposed estimator provides better estimates than the existing approaches on a variety of simulated datasets comprising linear and non-linear relations between variables. As an application of CMI estimation, we deploy our estimator for conditional independence (CI) testing on real data and obtain better results than state-of-the-art CI testers.

BACKGROUND: Single-cell RNA sequencing (scRNA-seq) is an emerging technology that can assess the function of an individual cell and cell-to-cell variability at the single cell level in an unbiased manner. Dimensionality reduction is an essential first step in downstream analysis of the scRNA-seq data. However, the scRNA-seq data are challenging for traditional methods due to their high dimensional measurements as well as an abundance of dropout events (that is, zero expression measurements). RESULTS: To overcome these difficulties, we propose DR-A (Dimensionality Reduction with Adversarial variational autoencoder), a data-driven approach to fulfill the task of dimensionality reduction. DR-A leverages a novel adversarial variational autoencoder-based framework, a variant of generative adversarial networks. DR-A is well-suited for unsupervised learning tasks for the scRNA-seq data, where labels for cell types are costly and often impossible to acquire. Compared with existing methods, DR-A is able to provide a more accurate low dimensional representation of the scRNA-seq data. We illustrate this by utilizing DR-A for clustering of scRNA-seq data. CONCLUSIONS: Our results indicate that DR-A significantly enhances clustering performance over state-of-the-art methods.

Generative Adversarial networks (GANs) have obtained remarkable success in many unsupervised learning tasks and unarguably, clustering is an important unsupervised learning problem. While one can potentially exploit the latent-space back-projection in GANs to cluster, we demonstrate that the cluster structure is not retained in the GAN latent space. In this paper, we propose ClusterGAN as a new mechanism for clustering using GANs. By sampling latent variables from a mixture of one-hot encoded variables and continuous latent variables, coupled with an inverse network (which projects the data to the latent space) trained jointly with a clustering specific loss, we are able to achieve clustering in the latent space. Our results show a remarkable phenomenon that GANs can preserve latent space interpolation across categories, even though the discriminator is never exposed to such vectors. We compare our results with various clustering baselines and demonstrate superior performance on both synthetic and real datasets.

Modeling of crowd and pedestrian dynamics has intrigued engineers, physicists, and sociologists alike, even in recent times. Scientists have long sought to model the collective motion of large groups of individuals and study the mathematical basis of what seems to be apparently random behavior. A large number of macroscopic models have been proposed that describe crowd motion as a whole, much like the partial differential equations of fluid mechanics. This paper proposes a Lagrangian approach to the modeling of crowd dynamics by taking into consideration the various forces that act between the members of a crowd while they are in motion in a 2-D field. We attempt a realistic modeling of the attractive and repulsive forces between the members and seek to give a definite mathematical backbone to the terms “panic” and “evacuation.” That the dynamics is stable is demonstrated by constructing an appropriate Lyapunov energy function. We then linearize the dynamics to obtain mathematical expressions for the small perturbations about an equilibrium point. Through machine simulations and by tracking the motion of actual crowd systems, we show the validity of the mathematics of group formation and evacuation that we have proposed.