Events and Activities

I will describe recent breakthrough results in multiclass PAC learning that characterize the optimal sample complexity. The talk will discuss recent work of Chirag Pabbaraju, as well as work of Steve Hanneke, Qinglin Meng, Shay Moran, and Amirreza...

This semester, we will be beginning a *very informal* get-together every Monday of people interested in/working on phenomenology and new theories beyond the standard model.  The idea is to discuss over lunch, perhaps meet up around 12.20, grab lunch...

Abstract: Heavy quarks propagating through quark-gluon plasma provide a unique, experimentally accessible opportunity to study the real-time dynamics of QCD in its strongly coupled regime. In the infinite heavy quark mass limit, the momentum change...

Abstract: Conformal field theories are defined by the CFT data: the spectrum of primary operator dimensions and OPE coefficients. Over the last decade, our knowledge of CFT data has accelerated at many frontiers. This has been facilitated by the...

How does the choice of training data influence an AI model? This question is of central importance to interpretability, privacy, and basic science.  At its core is the data deletion problem: after a reasonable amount of precomputation, quickly...

Using Tougeron’s characterization of multisummable (in the positive real directions) series, the latter can be viewed as infinite series of convergent power series with radii of convergence shrinking to 0. In joint work with Jean-Philippe Rolin and...

In the noisy $k$-XOR problem, one is given $y \in \bF_2^\constraints$ and must distinguish between $y$ uniform and $y = A x + e$, where $A$ is the adjacency matrix of a $k$-left-regular bipartite graph with variables and constraints, $x\in \bF_2^...

By combining sparse graphs with local constraints, expander codes offer a powerful framework for achieving fast decoding algorithms while maintaining asymptotically good rate and minimum distance. However, the standard constraint-counting arguments...