Pith. sign in

The gradient is given for allx∈R d by ∇xEλ(θ,x) =∇ xg1(x) + 1 λ(x−prox λ g2(θ,x)), 27 where we treatθ as fixed in the minimisation overRdx

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

stat.ML 1

years

2026 1

verdicts

CONDITIONAL 1

representative citing papers

Particle-based Generalised Stochastic Optimisation

stat.ML · 2026-08-03 · conditional · novelty 6.0

A unified diffusion-based particle framework for stochastic optimisation with intractable gradients, with exponential contraction and finite-particle error bounds, instantiated as new momentum and higher-order Langevin algorithms.

citing papers explorer

Showing 1 of 1 citing paper.

  • Particle-based Generalised Stochastic Optimisation stat.ML · 2026-08-03 · conditional · none · ref 8

    A unified diffusion-based particle framework for stochastic optimisation with intractable gradients, with exponential contraction and finite-particle error bounds, instantiated as new momentum and higher-order Langevin algorithms.