no code implementations • 22 Dec 2023 • Karthik Bharath, Alexander Lewis, Akash Sharma, Michael V Tretyakov
Error bounds are derived for sampling and estimation using a discretization of an intrinsically defined Langevin diffusion with invariant measure $d\mu_\phi \propto e^{-\phi} \mathrm{dvol}_g $ on a compact Riemannian manifold.
no code implementations • 21 Sep 2022 • Carlos Soto, Karthik Bharath, Matthew Reimherr, Aleksandra Slavkovic
It is common for data structures such as images and shapes of 2D objects to be represented as points on a manifold.
no code implementations • 20 Jan 2021 • H S Smitha Rao, Swarnamala Sirsi, Karthik Bharath
We propose a method to define quasiprobability distributions for general spin-$j$ systems of dimension $n=2j+1$, where $n$ is a prime or power of prime.
Quantum Physics
no code implementations • 25 Mar 2020 • Huiling Le, Alexander Lewis, Karthik Bharath, Christopher Fallaize
We detail an approach to develop Stein's method for bounding integral metrics on probability measures defined on a Riemannian manifold $\mathbf M$.
no code implementations • NeurIPS 2019 • Rachel Carrington, Karthik Bharath, Simon Preston
Word embeddings are commonly obtained as optimizers of a criterion function $f$ of a text corpus, but assessed on word-task performance using a different evaluation function $g$ of the test data.