Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,657 papers · 148 categories

Trend · papers per month

2975938901,186 · Jun 202019922001200920172026
48 results for Langevin methods

Paper analyzes and accelerates Langevin Monte Carlo methods using large deviations theory.

problem High-dimensional sampling problems in machine learning.
method Unified approach using large deviations theory to study and accelerate Langevin dynamics variants.
result Efficiency of Langevin dynamics variants demonstrated through numerical experiments.

SLMC improves sampling efficiency for high-dimensional distributions.

problem Sampling from high-dimensional distributions is computationally challenging.
method SLMC projects Langevin updates onto subsampled eigenblocks of a time-varying preconditioner.
result SLMC offers superior adaptability and computational efficiency compared to traditional methods.

New Langevin algorithms improve sampling efficiency in high dimensions.

problem Sampling from log-concave and smooth distributions in high dimensions.
method Combining splitting and accurate integration methods for PP-th order Langevin dynamics.
result LMC algorithms converge faster with better dimension dependence as PP increases.

A new method for sampling from complex distributions using Langevin samplers.

problem Sampling from unnormalized Boltzmann densities.
method Probability flow ODE derived from linear stochastic interpolants, employing Langevin samplers.
result Efficient simulation of the flow with non-asymptotic convergence rate.

New Langevin Monte Carlo algorithms for sampling from nonsmooth distributions.

problem Sampling from distributions with nonsmooth convex composite potentials.
method Leveraging Bregman--Moreau envelopes and proximal operators in mirror descent.
result Efficiency in sampling from nonsmooth distributions, extending existing methods.

Unified approach for sampling non-differentiable and heavy-tailed targets.

problem Sampling non-differentiable and heavy-tailed distributions using Langevin algorithms.
method Anchored Langevin dynamics, which modifies the Langevin diffusion with a smooth reference potential and multiplicative scaling.
result Non-asymptotic guarantees in the 2-Wasserstein distance to the target distribution.

New method uses higher-order Langevin dynamics for efficient parallel sampling.

problem Efficient parallel sampling from high-dimensional log-concave distributions.
method Combines higher-order Langevin dynamics with blockwise Lagrange polynomial interpolation.
result Reduces the number of parallel points required for a target accuracy.

New methods use transport maps to improve Langevin dynamics for sampling.

problem Sampling high-dimensional, non-Gaussian distributions efficiently.
method Apply transport maps to accelerate Langevin dynamics convergence.
result Discretized processes converge to target distribution with non-asymptotic bounds.

We study the underdamped Langevin diffusion when the log of the target distribution is smooth and strongly concave. We present a MCMC algorithm based on its discretization and show that it achieves ε\varepsilon error (in 2-Wasserstein distance) in O(d/ε)\mathcal{O}(\sqrt{d}/\varepsilon) steps. This is a significant improv…

2017-07-12abs ↗pdf ↗

Poisson Midpoint Method improves Langevin Dynamics for diffusion models.

problem Slow convergence of LMC in diffusion models requiring many small steps.
method Poisson Midpoint Method approximates LMC with larger steps, proving quadratic speed up.
result Poisson Midpoint Method maintains quality of DDPM with fewer calls.

A new method uses higher-order Langevin dynamics with critical damping for better generative modeling.

problem Improving generative models using Langevin dynamics with auxiliary variables.
method Introducing higher-order Langevin dynamics with critical damping, providing closed-form solutions.
result Improved generative models with better performance as measured by FID metric.

Langevin autoencoders improve deep latent variable models with efficient posterior sampling.

problem Efficient posterior sampling in deep latent variable models using MCMC.
method Amortized Langevin dynamics (ALD) replaces datapoint-wise sampling with encoder updates.
result ALD is valid as an MCMC algorithm with the target posterior as a stationary distribution.

First order discretizations of Langevin diffusion can achieve better generalization error with additional smoothness assumptions.

problem Analyzing generalization error for first order discretizations of Langevin diffusion.
method Providing a sufficient smoothness condition to show that first order methods can achieve arbitrarily runtime complexity for a given expected generalization error.
result First order methods can achieve arbitrarily runtime complexity with additional smoothness assumptions.

Paper tackles Bayesian image restoration in low-photon Poisson imaging problems.

problem Bayesian inference in challenging low-photon Poisson imaging problems.
method Plug-and-play (PnP) Langevin sampling strategies with accelerated methods and mirror sampling.
result Effective PnP Langevin sampling methods for low-photon Poisson imaging problems.

MAFLA improves sampling from heavy-tailed distributions using MH-inspired corrections.

problem Sampling from heavy-tailed and multimodal distributions when neither target nor proposal densities can be evaluated.
method Metropolis-Adjusted Fractional Langevin Algorithm (MAFLA) with Score Balance Matching.
result MAFLA significantly improves finite-time sampling accuracy over unadjusted fractional Langevin dynamics.

Langevin algorithms improve training of very deep neural networks, especially for image classification.

problem Training very deep neural networks is challenging due to increased non-linearity and the risk of getting stuck in local minima.
method Comparison of Langevin and non-Langevin algorithms for training deep neural networks, introduction of Layer Langevin algorithm.
result Langevin algorithms, especially Layer Langevin, lead to significant improvements in training deep neural networks, particularly for image classification tasks.

Paper analyzes and compares ELF algorithms for federated learning.

problem Improving efficiency and privacy in federated learning.
method Proposes P-ELF, D-ELF, and B-ELF algorithms with primal, dual, and bidirectional compression.
result Provides non-asymptotic convergence guarantees under Log-Sobolev inequality.

Novel method learns memory kernels in Langevin equations.

problem Estimating memory kernels in Langevin equations.
method Regularized Prony method for correlation functions, followed by regression over Sobolev norm-based loss function with RKHS regularization.
result Method outperforms other regression estimators in exponentially weighted L^2 space.

In this paper, we provide new insights on the Unadjusted Langevin Algorithm. We show that this method can be formulated as a first order optimization algorithm of an objective functional defined on the Wasserstein space of order 22. Using this interpretation and techniques borrowed from convex optimization, we give a …

2018-02-26abs ↗pdf ↗

New method controls bias in unadjusted Hamiltonian Monte Carlo and underdamped Langevin.

problem Bias in unadjusted Hamiltonian Monte Carlo and underdamped Langevin samplers.
method Delocalization of bias technique applied to these samplers.
result Control W2W_2 bias with O(K)O(\sqrt{K}) integration steps for high-dimensional distributions.

We provide convergence guarantees in Wasserstein distance for a variety of variance-reduction methods: SAGA Langevin diffusion, SVRG Langevin diffusion and control-variate underdamped Langevin diffusion. We analyze these methods under a uniform set of assumptions on the log-posterior distribution, assuming it to be smo…

2018-02-15abs ↗pdf ↗

The paper analyzes the randomized midpoint method for Langevin diffusions, revealing biases and asymptotic properties.

problem Analyzing biases and asymptotic properties of the randomized midpoint method for Langevin diffusions.
method Characterization of stationary distribution and asymptotic normality for numerical integration.
result The step-size needs to go to zero for the method to be asymptotically unbiased.

Langevin algorithms enhance training of deep neural networks for stochastic control problems.

problem Training acceleration for deep neural networks in stochastic control problems.
method Application of Langevin algorithms to minimize the loss of deep neural networks in stochastic control problems.
result Langevin algorithms improve training on various stochastic control problems.

SGLDiff approximates Bayesian posterior distributions with subsampling error.

problem Approximating Bayesian posterior distributions in large-scale data settings.
method Stochastic Gradient Langevin Diffusion (SGLDiff) with subsampling.
result The Wasserstein distance between the posterior and SGLDiff's limiting distribution is bounded by a fractional power of the mean waiting time.

Estimates generalization gap for overparameterized models using Langevin approximation.

problem Estimating the difference between training and generalization performance in overparameterized models.
method Functional variance and Langevin approximation of functional variance.
result Demonstrates efficient estimation of generalization gaps for overparameterized models.

Adaptive Langevin dynamics reduces bias in Bayesian inference with mini-batching.

problem Bias in posterior sampling due to mini-batching in Bayesian inference.
method Adaptive Langevin dynamics with dynamical friction to correct noise.
result Quantified bias in posterior distribution due to mini-batching.

New methods improve efficiency of sampling algorithms for complex systems.

problem Efficiently sampling from complex, high-dimensional probability distributions.
method Randomized Runge-Kutta-Nyström methods tailored for Hamiltonian flows.
result Quantitative 5/25/2-order L2L^2-accuracy in approximating Hamiltonian flows.

A fundamental problem in Bayesian inference and statistical machine learning is to efficiently sample from multimodal distributions. Due to metastability, multimodal distributions are difficult to sample using standard Markov chain Monte Carlo methods. We propose a new sampling algorithm based on a birth-death mechanis…

2019-05-23abs ↗pdf ↗