Microsoft Research

Jarnail Chudge, Andrei Ermilov, and Brad Cotier, Microsoft Cities Unlocked is a project that assists people with visual impairment to navigate through urban areas.

Patrick Baudisch and Stefanie Mueller, Hasso-Plattner Institute Computer science and mechanical engineering are about to unite.

Patrick Olivier and Vasilis Vlachokyriakos, Newcastle University PosterVote is an artifact that allows sustainable electronic voting by dropping the development and maintenance costs, while

In higher animals such as mammals, complex collective behaviors emerge from the microscopic properties of large structured ensembles of neurons.

Privacy-preserving data analysis has a large literature that spans several disciplines. Many early attempts have proved problematic either in practice or on paper.

G. Patrini, R. Nock, T. Caetano, P. Rivera (Almost) No Label No Cry O. Koyejo, N. Natarajan, P. Ravikumar, I. Dhillon Consistent Binary Classification with Generalized Performance Metrics D.

In this paper, we take a statistical decision-theoretic viewpoint on social choice, putting a focus on the decision to be made on behalf of a system of agents.

Type a summary that describes the content of your video.

B. Piot, M. Geist, O. Pietquin Difference of Convex Functions Programming for Reinforcement Learning S. Levine, P.

Game theory concerns how to form beliefs and act in settings with multiple self-interested agents. The best-known solution concept in game theory is that of Nash equilibrium.

M. Irfan, L. Ortiz Causal Strategic Inference in Networked Microfinance Economies D. Eigen, C. Puhrsch, R. Fergus Depth Map Prediction from a Single Image using a Multi-Scale Deep Network J.

A wild bootstrap method for nonparametric hypothesis tests based on kernel distribution embeddings is proposed.

Networks in Climate Science The El Ni├▒o is a powerful but irregular climate cycle that has huge consequences for agriculture and perhaps global warming.

PosterVote is an artifact that allows sustainable electronic voting by dropping the development and maintenance costs, while increasing the potential for social movements to engage in action and for

The Microsoft Research Fellow program enables bright, young minds in India to do world class research, and prepares them to become tomorrowΓÇÖs innovators and leaders.

David Nemer|

Konstantinos is a PhD student in CSE at City University of New York.

Microsoft researchers' innovations add a virtual keyboard and voice replies to Microsoft Band, along with machine-learning enhancements to canned responses. ΓÇï

Researchers at Microsoft have developed a system that can track -- in real time -- all the sophisticated and nuanced hand motions that people make in their everyday lives.

The science of consciousness has made great strides by focusing on the behavioral and neuronal correlates of experience.

When is working with private data safe, and when is it risky? Are the risks inherent to the computation?

S. Nie, D. Maua, C. de Campos, Q. Ji Advances in Learning Bayesian Networks of Bounded Treewidth J. Tristan, D. Huang, J. Tassarotti, A. Pocock, S. Green, G.

It was recently proved using graph covers (Ruozzi, 2012) that the Bethe partition function is upper bounded by the true partition function for a binary pairwise model that is attractive.

In Reinforcement Learning (RL), state-of-the-art algorithms require a large number of samples per state-action pair to estimate the transition kernel p .

A* Sampling The problem of drawing samples from a discrete distribution can be converted into a discrete optimization problem.

Probabilistic ODE Solvers with Runge-Kutta Means Runge-Kutta methods are the classic family of solvers for ordinary differential equations (ODEs), and the basis for the state of the art.

Subgradient Methods for Huge-Scale Optimization Problems ΓÇïWe consider a new class of huge-scale problems, the problems with sparse subgradients.

Asynchronous Anytime Sequential Monte Carlo We introduce a new sequential Monte Carlo algorithm we call the particle cascade.

C. Zhang, K. Chaudhuri Beyond Disagreement-Based Agnostic Active Learning A. Sani, G. Neu, A. Lazaric Exploiting easy data in online optimization P. Awasthi, A. Blum, O. Sheffet, A.

From Stochastic Mixability to Fast Rates Empirical risk minimization (ERM) is a fundamental learning rule for statistical learning problems where the data is generated according to some unknown