Lattice Field Theory
A discretization method in computational physics for studying quantum field theory. One of its central challenges is efficiently sampling field configurations from the equilibrium distribution.
Timeline (last 90 days)
A recent study proposes a "data-free training" scheme for diffusion models, allowing the model to complete training using only samples it generates itself, without sampling training data from the target distribution.
Denoising score matching (DSM) requires that the training data must come from the target distribution, otherwise the network learns the score of the wrong distribution, which is a fundamental obstacle to applying diffusion models to lattice field theory.
Hybrid Monte Carlo (HMC) is the standard algorithm for generating equilibrium configurations in lattice field theory, using Hamiltonian dynamics and a Metropolis accept-reject step to guarantee sampling correctness.
All Facts (3)
A recent study proposes a "data-free training" scheme for diffusion models, allowing the model to complete training using only samples it generates itself, without sampling training data from the target distribution.
50%UnverifiedDenoising score matching (DSM) requires that the training data must come from the target distribution, otherwise the network learns the score of the wrong distribution, which is a fundamental obstacle to applying diffusion models to lattice field theory.
50%UnverifiedHybrid Monte Carlo (HMC) is the standard algorithm for generating equilibrium configurations in lattice field theory, using Hamiltonian dynamics and a Metropolis accept-reject step to guarantee sampling correctness.
50%