gradient-based proposals 1hamiltonian monte carlo 1high-dimensional sampling 1mcmc scaling 1metropolis-hastings 1
From the 1 of 3 linked papers with an AI index.
Showing math.OCShow all
2 papers · 1 filter
math.OC2026
Accelerated optimization algorithms and ordinary differential equations: the convex non Euclidean case
Paul Dobson, Jesus MarÃa Sanz-Serna, Konstantinos C. Zygalakis
We study the connections between ordinary differential equations and optimization algorithms in a non-Euclidean setting. We propose a novel accelerated algorithm for minimising con…
math.OC2024
On the connections between optimization algorithms, Lyapunov functions, and differential equations: theory and insights
Paul Dobson, Jesus Maria Sanz-Serna, Konstantinos Zygalakis
We revisit the general framework introduced by Fazylab et al. (SIAM J. Optim. 28, 2018) to construct Lyapunov functions for optimization algorithms in discrete and continuous time.…