ICTS:32494

Computationally efficient reductions between some statistical models (Online)

(2025). Computationally efficient reductions between some statistical models (Online). SciVideos. https://scivideos.org/icts-tifr/32494

Computationally efficient reductions between some statistical models (Online). SciVideos, Aug. 12, 2025, https://scivideos.org/icts-tifr/32494 

          @misc{ scivideos_ICTS:32494,
            doi = {},
            url = {https://scivideos.org/icts-tifr/32494},
            author = {},
            keywords = {},
            language = {en},
            title = {Computationally efficient reductions between some statistical models (Online)},
            publisher = {},
            year = {2025},
            month = {aug},
            note = {ICTS:32494 see, \url{https://scivideos.org/icts-tifr/32494}}
          }
Ashwin Pananjady
Talk numberICTS:32494
Source RepositoryICTS-TIFR

Abstract

Can a sample from one parametric statistical model (the source) be transformed into a sample from a different (target) model? Versions of this question were asked as far back as 1950, and a beautiful asymptotic theory of equivalence of experiments emerged in the latter half of the 20th century. Motivated by problems spanning information-computation gaps and differentially private data analysis, we ask the analogous non-asymptotic question in high-dimensional problems and with algorithmic considerations. We show how a single observation from some source models can be approximately transformed to a single observation from a large class of target models by a computationally efficient algorithm. I will present several such reductions and discuss their applications to the aforementioned problems.

This is joint work with Mengqi Lou and Guy Bresler.