Zobrazeno 1 - 10
of 159
pro vyhledávání: '"GHOSH, SOUMYADIP"'
This paper presents an extension of the classical Ulan-von Neumann Markov chain Monte-Carlo algorithm for the computation of the matrix inverse. The algorithm presented in this paper, termed as \emph{regenerative Ulam-von Neumann algorithm}, utilizes
Externí odkaz:
http://arxiv.org/abs/2407.16661
We study convergence rates of Hamiltonian Monte Carlo (HMC) algorithms with leapfrog integration under mild conditions on stochastic gradient oracle for the target distribution (SGHMC). Our method extends standard HMC by allowing the use of general a
Externí odkaz:
http://arxiv.org/abs/2405.13140
Model explainability is crucial for human users to be able to interpret how a proposed classifier assigns labels to data based on its feature values. We study generalized linear models constructed using sets of feature value rules, which can capture
Externí odkaz:
http://arxiv.org/abs/2311.01994
The mean field variational inference (MFVI) formulation restricts the general Bayesian inference problem to the subspace of product measures. We present a framework to analyze MFVI algorithms, which is inspired by a similar development for general va
Externí odkaz:
http://arxiv.org/abs/2210.11385
We study the problem of transfer learning, observing that previous efforts to understand its information-theoretic limits do not fully exploit the geometric structure of the source and target domains. In contrast, our study first illustrates the bene
Externí odkaz:
http://arxiv.org/abs/2202.11685
Numerical solution of partial differential equations on parallel computers using domain decomposition usually requires synchronization and communication among the processors. These operations often have a significant overhead in terms of time and ene
Externí odkaz:
http://arxiv.org/abs/2202.10548
We study the convergence of a random iterative sequence of a family of operators on infinite dimensional Hilbert spaces, inspired by the Stochastic Gradient Descent (SGD) algorithm in the case of the noiseless regression, as studied in [1]. We identi
Externí odkaz:
http://arxiv.org/abs/2202.02266
Existing rigorous convergence guarantees for the Hamiltonian Monte Carlo (HMC) algorithm use Gaussian auxiliary momentum variables, which are crucially symmetrically distributed. We present a novel convergence analysis for HMC utilizing new analytic
Externí odkaz:
http://arxiv.org/abs/2110.12907
Communication in parallel systems imposes significant overhead which often turns out to be a bottleneck in parallel machine learning. To relieve some of this overhead, in this paper, we present EventGraD - an algorithm with event-triggered communicat
Externí odkaz:
http://arxiv.org/abs/2103.07454
The main purpose of this paper is to facilitate the communication between the Analytic, Probabilistic and Algorithmic communities. We present a proof of convergence of the Hamiltonian (Hybrid) Monte Carlo algorithm from the point of view of the Dynam
Externí odkaz:
http://arxiv.org/abs/2102.02691