We describe a framework to reduce the computational effort to evaluate large deviation functions of time integrated observables within nonequilibrium steady states. We do this by incorporating an auxiliary dynamics into trajectory based Monte Carlo calculations, through a transformation of the system's propagator using an approximate guiding function. This procedure importance samples the trajectories that most contribute to the large deviation function, mitigating the exponential complexity of such calculations. We illustrate the method by studying driven diffusion and interacting lattice models in one and two spatial dimensions. Our work offers an avenue to calculate large deviation functions for high dimensional systems driven far from equilibrium. DOI: 10.1103/PhysRevLett.120.210602 Much like their equilibrium counterparts, fluctuations about nonequilibrium steady states encode physical information about a system. This is illustrated by the discovery of the fluctuation theorems [1][2][3][4], thermodynamic uncertainty relations [5,6], and extensions of the fluctuationdissipation theorem to systems far from equilibrium [7][8][9][10]. Large deviation functions provide a general mathematical framework within which to characterize and understand nonequilibrium fluctuations [11], and their evaluation has underpinned much recent progress in understanding driven systems [12][13][14][15]. However, the current Monte Carlo methods, such as the cloning algorithm [16][17][18][19][20][21] or transition path sampling [22], exhibit low statistical efficiency when accessing rare fluctuations that are needed to compute them [21,23]. This has limited the numerical application of large deviation theory to idealized model systems with relatively few degrees of freedom.In principle, these difficulties can be eliminated through the use of importance sampling. A formally exact importance sampling can be derived through Doob's h transform, although this requires the exact eigenvector of the tilted operator that generates the biased path ensemble [24][25][26]. As this is not practical, approximate importance sampling schemes have been introduced [21,27,28], including a sophisticated iterative algorithm to improve sampling based on feedback and control [21,28].In this Letter, we will show that guiding distribution functions (GDF), used to implement importance sampling in diffusion Monte Carlo (DMC) calculations of quantum ground states, can be extended to provide an approximate, but improvable, importance sampling for the simulation of nonequilibrium steady states. We show the potential of the GDF method by computing the large deviation functions of time integrated currents at large bias values that capture very rare fluctuations within two widely studied models: a driven diffusion model and an interacting lattice model. As examples of GDFs, we use analytical expressions as well as GDFs determined from a generalized variational approximation [29]. The variational approach provides a procedure to generate guiding functions for arbit...