This paper introduces a new tamed stochastic gradient Hamiltonian Monte Carlo (tSGHMC) algorithm for sampling and optimization problems with large stochastic gradients, providing error bounds and perf…

This paper presents conditions for achieving optimal uniformity in Quasi-Monte Carlo estimators using Sobol' sequences and Artin-Schreier polynomials.

This paper introduces QuasiMoTTo, a method for generating correlated but exact samples in parallel to improve sample efficiency in scaling inference compute and reinforcement learning.

The paper proposes a novel probabilistic globally constrained decoding (P-GCD) method that efficiently constructs proposals for locally constrained decoding, significantly improving convergence speed…

This paper introduces survey sampling techniques to estimate or minimize empirical pairwise loss functions, showing that targeting informative pairs significantly reduces computational cost while main…

This paper presents a self-balancing sampler for sequential sampling that achieves faster convergence to a desired target law while maintaining unpredictability.

The paper introduces Entropy-Cut Metropolis-Hastings, an efficient sampling method that uses next-token entropy to identify and resample from critical decision points in a reasoning trace, significant…

This paper proves conditions for efficiently approximating expectations of certain functions with respect to standard Gaussian or symmetric exponential probability measures.

The paper introduces MINTS, a minimalist Bayesian framework that simplifies sequential decision-making by placing priors only on the optimum location, allowing for the incorporation of structural cons…

This paper proves space lower bounds for entropy-efficient random sampling using i.i.d. uniform bits.

This paper introduces CuBAS, an adaptive data selection method for supervised classification based on curvature estimation from a labeled dataset using the Potts MRF model.

This paper introduces a novel algorithm for generating k Hamming weight binary words in linear time while minimizing random bit consumption.

This paper introduces phase-to-primitive decomposition to enable Monte Carlo tree search (MCTS) on in-memory computing (IMC) systems, achieving significant energy efficiency and performance improvemen…

The paper presents a framework for model selection and parameter estimation using large language models and neural simulation-based inference.

The paper proposes sampling directly from approximations of an LLM posterior, conditioned on high-scoring regions, to generate more coherent and useful text compared to existing post-hoc hallucination…

The paper introduces Langevin Speculative Dynamics (LSD), a speculative sampling method that accelerates molecular dynamics simulations by using a fast draft model to propose steps, achieving signific…