Search

In this paper we present a large-scale visual object detection and tracking benchmark, named VisDrone2018, aiming at advancing visual understanding tasks on the drone platform. The images and video sequences in the benchmark were captured over various urban/suburban areas of 14 different cities...

This paper addresses consensus optimization problem in a multi-agent network, where all the agents collaboratively find a common minimizer to the sum of their private functions. Our goal is to develop a decentralized algorithm in which there is no center agent and each agent only communicates with...

Four Simple Steps to better interviews!

A White Paper created to improve your interviewing skills!
Karen A. Young, SPHR

Studies show the number one mistake interviewers make is talking too much. The candidate should be speaking about 80% of your time together.

Where do you start?

The best…

Harini Suresh, a PhD student at MIT CSAIL, studies how to make machine learning algorithms more understandable and less biased.

Harini Suresh, a PhD student at MIT CSAIL, studies how to make machine learning algorithms more understandable and less biased.

“RoadTracer” system from the Computer Science and Artificial Intelligence Laboratory could reduce workload for developers of apps like Google Maps.

Neuroscientists train a deep neural network to analyze speech and music.

We introduce a new family of deep neural network models. Instead of specifying a discrete sequence of hidden layers, we parameterize the derivative of the hidden state using a neural network. The output of the network is computed using a black-box differential equation solver. These continuous...

We prove that ϴ(k d^2 / ε^2) samples are necessary and sufficient for learning a mixture of k Gaussians in R^d, up to error ε in total variation distance. This improves both the known upper bounds and lower bounds for this problem. For mixtures of axis-aligned Gaussians, we show that O(k d / ε^2)...

In this work, we consider the distributed optimization of non-smooth convex functions using a network of computing units. We investigate this problem under two regularity assumptions: (1) the Lipschitz continuity of the global objective function, and (2) the Lipschitz continuity of local individual...

We identify a fundamental source of error in Q-learning and other forms of dynamic programming with function approximation. Delusional bias arises when the approximation architecture limits the class of expressible greedy policies. Since standard Q-updates make globally uncoordinated action choices...

This contribution develops a theoretical framework that takes into account the effect of approximate optimization on learning algorithms. The analysis shows distinct tradeoffs for the case of small-scale and large-scale learning problems. Small-scale learning problems are subject to the usual...

In imperfect-information games, the optimal strategy in a subgame may depend on the strategy in other, unreached subgames. Thus a subgame cannot be solved in isolation and must instead consider the strategy for the entire game as a whole, unlike perfect-information games. Nevertheless, it is...

We develop an approach to risk minimization and stochastic optimization that provides a convex surrogate for variance, allowing near-optimal and computationally efficient trading between approximation and estimation error. Our approach builds off of techniques for distributionally robust...

We propose a novel adaptive test of goodness-of-fit, with computational cost linear in the number of samples. We learn the test features that best indicate the differences between observed samples and a reference model, by minimizing the false negative rate. These features are constructed via Stein...

To accelerate the training of kernel machines, we propose to map the input data to a randomized low-dimensional feature space and then apply existing fast linear methods. The features are designed so that the inner products of the transformed data are approximately equal to those in the feature...

Method could illuminate features of biological tissues in low-exposure images.