The proliferation of massive datasets combined with the development of sophisticated analytical techniques have enabled a wide variety of novel appli…

The goal of this paper is to analyze the geometric properties of deep neural network classifiers in the input space. We specifically study the topolo…

We propose a novel model to address the task of Visual Dialog which exhibits complex dialog structures. To obtain a reasonable answer based on the cu…

Following the recent progress in image classification and captioning using deep learning, we develop a novel natural language person retrieval system…

The Gale-Shapley algorithm for the Stable Marriage Problem is known to take $\Theta(n^2)$ steps to find a stable marriage in the worst case, but only…

Exploiting the efficiency and stability of Position-Based Dynamics (PBD), we introduce a novel crowd simulation method that runs at interactive rates…

Smart cities rely on dynamic and real-time data to enable smart urban applications such as intelligent transport and epidemics detection. However, th…

Graph Neural Nets (GNNs) have received increasing attentions, partially due to their superior performance in many node and graph classification tasks…

The unsupervised training of GANs and VAEs has enabled them to generate realistic images mimicking real-world distributions and perform image-based u…

Video summarization has unprecedented importance to help us digest, browse, and search today's ever-growing video collections. We propose a novel sub…

A recent line of research has shown that gradient-based algorithms with random initialization can converge to the global minima of the training loss …

We present a new algorithm to train a robust neural network against adversarial attacks. Our algorithm is motivated by the following two ideas. First…

We introduce an asymmetric distance in the space of learning tasks, and a framework to compute their complexity. These concepts are foundational to t…

In this paper, we propose a method for clustering image-caption pairs by simultaneously learning image representations and text representations that …

The biological literature is rich with sentences that describe causal relations. Methods that automatically extract such sentences can help biologist…

In this section we prove the main theorem.

We introduce a new coordination problem in distributed computing that we call the population stability problem. A system of agents each with limited …

We propose a data structure obtained by hierarchically averaging bag-of-word descriptors during a sequence of views that achieves average speedups in…

Gaussian Graphical Models (GGMs) have wide-ranging applications in machine learning and the natural and social sciences. In most of the settings in w…

In this paper, we extend graph-based identification methods by allowing background knowledge in the form of non-zero parameter values. Such informati…

Data parallelism has become a dominant method to scale Deep Neural Network (DNN) training across multiple nodes. Since synchronizing a large number o…

By signing up you accept our content policy

Already have an account? Sign in

No a member yet? Create an account