Research
Many real-world problems require making decisions that involve multiple possibly conflicting objectives. To succeed in such tasks, intelligent agents need algorithms that can efficiently find different ways of balancing the trade-offs that such objectives present.…
We proposed a doubly stochastic primal-dual coordinate optimization algorithm for regularized empirical risk minimization that can be formulated as a saddle-point problem using convex conjugate functions. Different from the existing coordinate methods, the proposed method…
By Jeannette M. Wing, corporate vice president, Microsoft Research “Not in my lifetime.” That’s what I said when I was asked whether we would ever see computer science taught in K-12. It was 2009, and…
In this talk I provide an overview of information-theoretic bounded-rationality for planning in sequential decision problems. I show how to ground the theory on a stochastic computation model for large-scale choice spaces and then derive…
Many problems in real-world applications involve predicting several random variables which are statistically related. A structured model, like a Markov random field, is a great mathematical tool to encode those dependencies. Within the first part…
Reconstructing a sequence from its short substrings, called reads, is a central problem in DNA sequencing. I will introduce an adversarial error model for the reads, and show that a simple algorithm leads to approximate…
We present the first non-trivial online algorithms for the classical multi-commodity buy-at-bulk problem. The goal is to provision a low-cost network over time to support bandwidth demands that also arrive over time. Previously, online algorithms…
It is quite easy to believe that the recently proposed approach to machine translation, called neural machine translation, is simply yet another approach to statistical machine translation. This belief may drive research effort toward (incrementally)…
