MIT Building 32, Room 141

We describe a convergence acceleration technique for generic optimization problems. Our scheme computes estimates of the optimum from a nonlinear average of the iterates produced by any optimization method. The weights in this average are computed via a simple linear system, whose solution can be updated online. This acceleration scheme runs in parallel to the base algorithm, providing improved estimates of the solution on the fly, while the original optimization method is running. Numerical experiments are detailed on classical classification…

In the past couple of decades, non-smooth convex optimization has emerged as a powerful tool for the recovery of structured signals (sparse, low rank, finite constellation, etc.) from possibly noisy measurements in a variety applications in statistics, signal processing and machine learning. While the algorithms (basis pursuit, LASSO, etc.) are often fairly well established, rigorous frameworks for the exact analysis of the performance of such methods are only just emerging. The talk will introduce and describe a fairly general theory…

In many practical applications information is conveyed by means of electromagnetic radiation and a natural question concerns the fundamental limits of this process. Identifying information with entropy, one can ask about the maximum amount of entropy associated to the propagating wave. The standard statistical physics approach to compute entropy is to take the logarithm of the number of possible energy states of a system. Since any continuum field can assume an uncountably infinite number of energy configurations, the approach underlying…

We describe a convergence acceleration technique for generic optimization problems. Our scheme computes estimates of the optimum from a nonlinear average of the iterates produced by any optimization method. The weights in this average are computed via a simple linear system, whose solution can be updated online. This acceleration scheme runs in parallel to the base algorithm, providing improved estimates of the solution on the fly, while the original optimization method is running. Numerical experiments are detailed on classical classification…

How do our brains make sense of a complex and unpredictable world? In this talk, I will discuss an information theory approach to the neural topography of information processing in the brain. First I will review the brain's architecture, and how neural circuits map out the sensory and cognitive worlds. Then I will describe how highly complex sensory and cognitive tasks are carried out by the cooperative action of many specialized neurons and circuits, each of which has a simple…

The advent of Big Data is stimulating the development of new networking architectures which facilitate the acquisition, transmission, storage, and computation of data. In particular, Named Data Networking (NDN) is an emerging content-centric networking architecture which focuses on enabling end users to obtain the data they want, rather than to communicate with specific nodes. By naming content instead of their locations, NDN transforms data into a first-class network entity. In this talk, we present a new analytical and design framework…