Zobrazeno 1 - 10
of 168
pro vyhledávání: '"Pillai, Natesh S."'
Autor:
Badrinarayanan, Saikrishna, Osoba, Osonde, Cheng, Miao, Rogers, Ryan, Jain, Sakshi, Tandra, Rahul, Pillai, Natesh S.
AI fairness measurements, including tests for equal treatment, often take the form of disaggregated evaluations of AI systems. Such measurements are an important part of Responsible AI operations. These measurements compare system performance across
Externí odkaz:
http://arxiv.org/abs/2409.04652
Autor:
Zhao, Daniel, Pillai, Natesh S.
Parallel tempering is meta-algorithm for Markov Chain Monte Carlo that uses multiple chains to sample from tempered versions of the target distribution, enhancing mixing in multi-modal distributions that are challenging for traditional methods. The e
Externí odkaz:
http://arxiv.org/abs/2409.01574
Stein Variational Gradient Descent (SVGD) is a nonparametric particle-based deterministic sampling algorithm. Despite its wide usage, understanding the theoretical properties of SVGD has remained a challenging problem. For sampling from a Gaussian ta
Externí odkaz:
http://arxiv.org/abs/2305.14076
Autor:
Pillai, Natesh S.
The Metropolis-adjusted Langevin (MALA) algorithm is a sampling algorithm that incorporates the gradient of the logarithm of the target density in its proposal distribution. In an earlier joint work \cite{pill:stu:12}, the author had extended the sem
Externí odkaz:
http://arxiv.org/abs/2204.10793
It is widely known that the performance of Markov chain Monte Carlo (MCMC) can degrade quickly when targeting computationally expensive posterior distributions, such as when the sample size is large. This has motivated the search for MCMC variants th
Externí odkaz:
http://arxiv.org/abs/2010.12514
In this note, we show how to provide sharp control on the least singular value of a certain translated linearization matrix arising in the study of the local universality of products of independent random matrices. This problem was first considered i
Externí odkaz:
http://arxiv.org/abs/2007.03595
In this work, we analyze dimension reduction algorithms based on the Kac walk and discrete variants. (1) For $n$ points in $\mathbb{R}^{d}$, we design an optimal Johnson-Lindenstrauss (JL) transform based on the Kac walk which can be applied to any v
Externí odkaz:
http://arxiv.org/abs/2003.10069
Publikováno v:
J. Appl. Probab. 58 (2021) 83-105
A family $\{Q_{\beta}\}_{\beta \geq 0}$ of Markov chains is said to exhibit $\textit{metastable mixing}$ with $\textit{modes}$ $S_{\beta}^{(1)},\ldots,S_{\beta}^{(k)}$ if its spectral gap (or some other mixing property) is very close to the worst con
Externí odkaz:
http://arxiv.org/abs/1808.03239
Hamiltonian Monte Carlo (HMC) is a very popular and generic collection of Markov chain Monte Carlo (MCMC) algorithms. One explanation for the popularity of HMC algorithms is their excellent performance as the dimension $d$ of the target becomes large
Externí odkaz:
http://arxiv.org/abs/1808.03230
Autor:
Pillai, Natesh S, Smith, Aaron
We study a kinetically constrained Ising process (KCIP) associated with a graph $G$ and density parameter $p$; this process is an interacting particle system with state space $\{ 0, 1 \}^{G}$, the location of the particles. The `constraint' in the na
Externí odkaz:
http://arxiv.org/abs/1708.03838