Past Events

The following problem arose from the work of Fonio et al, a group of ecologists and computer scientists, who tried to understand the behaviour of longhorn crazy ants (Paratrechina longicomis) in navigating back to their nest after gathering food. Single ants were demonstrated to be laying pheromone ‘pointers’ to be followed by groups of ants carrying large loads. Sometimes the pointers are wrong. This leads to an optimization problem on networks with a destination node (the nest). A GPS or other system selects a direction (pointer) to the nest at every node.

In this talk, I will discuss some of my recent and surprising findings on the use of hashing algorithms for large-scale estimations. Locality Sensitive Hashing (LSH) is a hugely popular algorithm for sub-linear near neighbor search. However, it turns out that fundamentally LSH is a constant time (amortized) adaptive sampler from which efficient near-neighbor search is one of the many possibilities. Our observation adds another feather in the cap for LSH. LSH offers a unique capability to do smart sampling and statistical estimations at the cost of few hash lookups.

Abstract: Approximate probabilistic inference is a key computational task in modern machine learning, which allows us to reason with complex, structured, hierarchical (deep) probabilistic models to extract information and quantify uncertainty.

Abstract: We present a new statistical framework to quantify uncertainty (UQ) for recovering low-rank matrices from incomplete and noisy observations. We further develop a sequential active sampling approach guided by the uncertainties. The motivation comes from two related and widely studied problems, matrix completion, which aims to recover a low-rank matrix X from a partial, noisy observation of its entries, and low-rank matrix recovery, which recovers X from a set of linear combination its entries with additive noise.

Recent years have seen a flurry of activities in designing provably efficient nonconvex procedures for solving statistical estimation problems. The premise is that despite nonconvexity, the loss function may possess benign geometric properties that enable fast global convergence under carefully designed initializations, such as local strong convexity, local restricted convexity, etc.

*PLEASE NOTE CORRECTION: Seminar will take place in EER 3.646 (North Tower)This talk focuses on the statistical sample complexity and model reduction of Markov decision process (MDP).  We begin by surveying recent advances on the complexity for solving MDP, without any dimension reduction. In the first part we study the statistical state compression of general Markov processes. We propose a spectral state compression method for learning state features and aggregation structures from data.

The concept of a blockchain was invented by Satoshi Nakamoto to maintain a distributed ledger for an electronic payment system, Bitcoin. In addition to its security, important performance measures of a blockchain protocol are its transaction throughput, confirmation latency and confirmation reliability. These measures are limited by two underlying physical network attributes: communication capacity and speed-of-light propagation delay. Existing systems operate far away from these physical limits.

This year's Texas Wireless Summit, “AI and the Mobile Device,” will focus on how machine learning, artificial intelligence, and some key applications will interact with wireless technology. The Summit will examine how Artificial Intelligence and Machine Learning (AI/ML) will simultaneously enhance connectivity as well as place demands on both devices and connectivity.

Soft biomaterials such as human skin have very different mechanical properties from conventional electronics, requiring unusual materials and geometries to match the behavior of the skin.  One of the biggest challenges in stretchable electronics is the transfer of power and data signals, with physical wiring easily pulled out or damaged.  In my talk, I will be discussing all aspects of creating inductors and power circuits for wireless power transfer to stretchable systems.  I will focus on the use of room temperature liquid metals and stretchable magnetic materials to maximize

Recent years have witnessed significant progress in entropy estimation, in particular in the large alphabet regime. Concretely, there exist efficiently computable information theoretically optimal estimators whose performance with n samples is essentially that of the maximum likelihood estimator with n log(n) samples, a phenomenon termed ``effective sample size boosting''. Generalizations to processes with memory (estimation of the entropy rate) and continuous distributions (estimation of the differential entropy) have remained largely open.