Skip to main content

Research Repository

Advanced Search

All Outputs (4)

Invariance and identifiability issues for word embeddings (2019)
Conference Proceeding
Carrington, R., Bharath, K., & Preston, S. (2019). Invariance and identifiability issues for word embeddings. In Advances in Neural Information Processing Systems 32 (NIPS 2019)

Word embeddings are commonly obtained as optimisers of a criterion function f of 1 a text corpus, but assessed on word-task performance using a different evaluation 2 function g of the test data. We contend that a possible source of disparity in 3 pe... Read More about Invariance and identifiability issues for word embeddings.

Mutually disjoint, maximally commuting set of physical observables for optimum state determination (2019)
Journal Article
Smitha Rao, H. S., Sirsi, S., & Bharath, K. (2019). Mutually disjoint, maximally commuting set of physical observables for optimum state determination. Physica Scripta, 94(10), 1-7. https://doi.org/10.1088/1402-4896/ab2a85

We consider the state determination problem using mutually unbiased bases (MUBs). For spin-1, spin-3/2 and spin-2 systems, analogous to Pauli operators of spin-1/2 system, which are experimentally implementable and correspond to the optimum measureme... Read More about Mutually disjoint, maximally commuting set of physical observables for optimum state determination.

Distribution on warp maps for alignment of open and closed curves (2019)
Journal Article
Bharath, K., & Kurtek, S. (2019). Distribution on warp maps for alignment of open and closed curves. Journal of the American Statistical Association, 115(531), 1378-1392. https://doi.org/10.1080/01621459.2019.1632066

Alignment of curve data is an integral part of their statistical analysis, and can be achieved using model-or optimization-based approaches. The parameter space is usually the set of monotone, continuous warp maps of a domain. Infinite-dimensional na... Read More about Distribution on warp maps for alignment of open and closed curves.

A geometric variational approach to Bayesian inference (2019)
Journal Article
Saha, A., Bharath, K., & Kurtek, S. (2020). A geometric variational approach to Bayesian inference. Journal of the American Statistical Association, 115(530), 822-835. https://doi.org/10.1080/01621459.2019.1585253

We propose a novel Riemannian geometric framework for variational inference in Bayesian models based on the nonparametric Fisher–Rao metric on the manifold of probability density functions. Under the square-root density representation, the manifold c... Read More about A geometric variational approach to Bayesian inference.