Search Results for author: Daniel Štefankovič

Found 5 papers, 0 papers with code

Complexity of High-Dimensional Identity Testing with Coordinate Conditional Sampling

no code implementations19 Jul 2022 Antonio Blanca, Zongchen Chen, Daniel Štefankovič, Eric Vigoda

We consider a significantly weaker conditional sampling oracle, which we call the $\mathsf{Coordinate\ Oracle}$, and provide a computational and statistical characterization of the identity testing problem in this new model.

Vocal Bursts Intensity Prediction

On Mixing of Markov Chains: Coupling, Spectral Independence, and Entropy Factorization

no code implementations12 Mar 2021 Antonio Blanca, Pietro Caputo, Zongchen Chen, Daniel Parisi, Daniel Štefankovič, Eric Vigoda

For general spin systems, we prove that a contractive coupling for any local Markov chain implies optimal bounds on the mixing time and the modified log-Sobolev constant for a large class of Markov chains including the Glauber dynamics, arbitrary heat-bath block dynamics, and the Swendsen-Wang dynamics.

Probability Discrete Mathematics Data Structures and Algorithms Mathematical Physics Functional Analysis Mathematical Physics

Hardness of Identity Testing for Restricted Boltzmann Machines and Potts models

no code implementations22 Apr 2020 Antonio Blanca, Zongchen Chen, Daniel Štefankovič, Eric Vigoda

Daskalakis et al. (2018) presented a polynomial-time algorithm for identity testing for the ferromagnetic (attractive) Ising model.

Lower bounds for testing graphical models: colorings and antiferromagnetic Ising models

no code implementations22 Jan 2019 Ivona Bezakova, Antonio Blanca, Zongchen Chen, Daniel Štefankovič, Eric Vigoda

In particular, we prove hardness results in two prototypical cases, the Ising model and proper colorings, and explore whether identity testing is any easier than structure learning.

Structure Learning of $H$-colorings

no code implementations17 Aug 2017 Antonio Blanca, Zongchen Chen, Daniel Štefankovič, Eric Vigoda

We prove that in the tree uniqueness region (when $q>d$) the problem is identifiable and we can learn $G$ in ${\rm poly}(d, q) \times O(n^2\log{n})$ time.

Cannot find the paper you are looking for? You can Submit a new open access paper.