Georgia Institute of Technology College of Sciences

A central goal in modern data science is to design algorithms for statistical inference tasks such as community detection, high-dimensional clustering, sparse PCA, and many others. Ideally these algorithms would be both statistically optimal and computationally efficient. However, it often seems impossible to achieve both these goals simultaneously: for many problems, the optimal statistical procedure involves a brute force search while all known polynomial-time algorithms are statistically sub-optimal (requiring more data or higher signal strength than is information-theoretically necessary). In the quest for optimal algorithms, it is therefore important to understand the fundamental statistical limitations of computationally efficient algorithms.

I will discuss an emerging theoretical framework for understanding these questions, based on studying the class of "low-degree polynomial algorithms." This is a powerful class of algorithms that captures the best known poly-time algorithms for a wide variety of statistical tasks. This perspective has led to the discovery of many new and improved algorithms, and also many matching lower bounds: we now have tools to prove failure of all low-degree algorithms, which provides concrete evidence for inherent computational hardness of statistical problems. This line of work illustrates that low-degree polynomials provide a unifying framework for understanding the computational complexity of a wide variety of statistical tasks, encompassing hypothesis testing, estimation, and optimization.

Quantum Teichmüller space was first introduced by Chekhov and Fock as a version of 2+1d quantum gravity. The definition was translated over time into an algebra of curves on surfaces, which coincides with an extension of the Kauffman bracket skein algebra. In this talk, we will discuss the relation between the Teichmüller space and the Kauffman bracket, and time permitting, the quantized version of this correspondence.

Meeting URL: https://bluejeans.com/106460449/5822

In this talk, I will discuss recent advances and challenges in modelling complex dynamics of pedestrian-bridge interactions,  These challenges include a proper understanding of the biomechanics of walking on a moving structure and of the psychology of walking in crowds. I will explain the fundamental mechanism behind pedestrian-induced lateral instability of bridges due to some positive feedback from uncorrelated walkers whose foot forces do not cancel each other but create a bias. I will also present the results of our past and ongoing work that reveal the role of foot placement strategies and social force dynamics in initiating bridge instabilities. In particular, I will show that  (i)  paradoxically, depending on the human balance law (and the frequency of bridge motion), larger crowds can stabilize  bridge motions and (ii)  crowd heterogeneity can promote large vibrations of bridges.

Recording link:  https://bluejeans.com/s/h0TpdyBRatJ 

Let M be a complex-hyperbolic n-manifold, i.e. a quotient of the complex-hyperbolic n-space $\mathbb{H}^n_\mathbb{C}$ by a torsion-free discrete group of isometries, $\Gamma = \pi_1(M)$. Suppose that M is  convex-cocompact, i.e. the convex core of M is a nonempty compact subset. In this talk, we will discuss a sufficient condition on $\Gamma$ in terms of the growth-rate of its orbits in $\mathbb{H}^n_\mathbb{C}$ for which M is a Stein manifold. We will also talk about some interesting questions related to this result. This is a joint work with Misha Kapovich.

https://bluejeans.com/196544719/9518