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

139278417556 · Jun 202019922001200920172026
48 results for Stochastic Gradient Langevin Diffusion

Error estimates found between SGD with momentum and Langevin diffusion.

problem Quantifying the difference between SGD with momentum and Langevin diffusion.
method Established error estimates using 1-Wasserstein and total variation distances.
result Quantitative error estimates between SGD with momentum and underdamped Langevin diffusion.

NSGLD improves SGLD for non-convex optimization problems.

problem Optimizing non-convex objectives efficiently.
method Introducing non-reversible SGLD by adding an anti-symmetric matrix to the drift term of the Langevin diffusion.
result NSGLD converges faster to the same stationary distribution with non-asymptotic guarantees.

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.

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.

Improved error estimate for SGLD sampling algorithm.

problem Establishing a precise error bound for SGLD.
method Sharp uniform-in-time error estimate for SGLD under mild assumptions.
result Uniform-in-time O(η2)O(η^2) bound for KL-divergence between SGLD and Langevin diffusion.

Paper analyzes PSGLD for adaptive IRL with finite-sample bounds.

problem Estimating cost function of a forward learner using noisy gradients.
method Passive stochastic gradient Langevin dynamics (PSGLD) algorithm.
result Explicit bounds on 2-Wasserstein distance between PSGLD sample measure and stationary measure.

This paper introduces Stochastic Gradient Langevin Boosting (SGLB) - a powerful and efficient machine learning framework that may deal with a wide range of loss functions and has provable generalization guarantees. The method is based on a special form of the Langevin diffusion equation specifically designed for gradie…

2020-01-20abs ↗pdf ↗

Improved privacy analysis for stochastic gradient descent.

problem Analyzing privacy leakage in noisy stochastic gradient descent.
method Modeling Rényi divergence dynamics with Langevin diffusions, proving exponential privacy loss convergence for smooth and strongly convex objectives.
result Privacy loss converges exponentially fast for smooth and strongly convex objectives under constant step size.

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 variance reduction in stochastic gradient Langevin dynamics.

problem Reducing the variance of stochastic gradient estimators in Langevin dynamics.
method Central limit theorem and Poisson equation analysis for variance characterization.
result Anti-symmetric perturbations can reduce the variance of non-reversible Langevin dynamics.

New method improves sampling from high-dimensional target densities.

problem Sampling from high-dimensional target densities using Monte Carlo algorithms.
method Extends Metropolis-Adjusted Langevin Diffusion algorithm with random precondition matrix modeling.
result Significantly improves performance and computational efficiency over standard MCMC methods.

New algorithm TUSLA improves learning of non-convex neural networks.

problem Optimizing non-convex loss functions in neural networks with superlinear gradient growth.
method Tamed Unadjusted Stochastic Langevin Algorithm (TUSLA) based on SGLD with taming technology.
result Finite-time guarantees for TUSLA to find approximate minimizers of empirical and population risks.

Sampling with Markov chain Monte Carlo methods often amounts to discretizing some continuous-time dynamics with numerical integration. In this paper, we establish the convergence rate of sampling algorithms obtained by discretizing smooth Itô diffusions exhibiting fast Wasserstein-22 contraction, based on local deviat…

2019-06-19abs ↗pdf ↗

Proposes a new method for constrained generative modeling using Langevin dynamics.

problem Challenges in satisfying underlying constraints with score-based generative models.
method Uses kinetic Langevin dynamics with specular reflection to model constraints.
result Demonstrates efficient numerical samplers with optimal convergence rates.

This paper resolves the Langevin Algorithm's mixing time for log-concave distributions.

problem Resolving the mixing time of the Langevin Algorithm for log-concave sampling.
method Introducing Privacy Amplification by Iteration to analyze Rényi divergence and Optimal Transport smoothing.
result Optimal mixing bounds for the Langevin Algorithm in log-concave sampling settings.

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.

Diffusion models simulate molecular dynamics with adjustable accuracy.

problem Simulating molecular dynamics with high accuracy and efficiency.
method Diffusion models as Euler-Maruyama integrators for Langevin dynamics, learning forces from static snapshots.
result Diffusion models generate molecular trajectories with temporal correlations similar to MD simulations.

We analyze a new Markov chain model for better sampling and optimization.

problem Developing a new Markov chain model for improved sampling and optimization.
method We introduce a new class of Ito chains with arbitrary noise and inexact drift/diffusion coefficients, proving a bound in W2W_{2}-distance.
result Our analysis provides improved or first results for various applications like SGLD, sampling, and boosting.

New method improves sampling efficiency in complex stochastic systems.

problem Sampling efficiency in nonconvex stochastic gradient cases.
method Reflection coupling for unadjusted generalized Hamiltonian Monte Carlo.
result Quantitative Gaussian concentration bounds and convergence rates established.

Enhances SGLD for log-concave posteriors with asynchronous computation.

problem Sampling log-concave posterior distributions efficiently.
method Integrates asynchronous computation into SGLD with delayed gradients.
result Convergence in measure is not significantly affected by delayed gradient information.

Langevin MCMC samples efficiently from Riemannian manifolds with geometric Euler-Murayama analysis.

problem Efficient sampling from Gibbs distributions on Riemannian manifolds.
method Geometric Langevin MCMC, discretization error bound, contraction guarantee for Langevin Diffusion.
result Langevin MCMC iterates converge to the target distribution after a number of steps proportional to the inverse square of the desired accuracy.

Paper improves convergence rate of Langevin Dynamics algorithms.

problem Sampling problems and non-convex optimization in machine learning.
method Stochastic Variance Reduced Gradient Langevin Dynamics and Stochastic Recursive Gradient Langevin Dynamics with improved convergence rates.
result Proves convergence to objective distribution under weaker conditions.

Markov chains and diffusion processes are indispensable tools in machine learning and statistics that are used for inference, sampling, and modeling. With the growth of large-scale datasets, the computational cost associated with simulating these stochastic processes can be considerable, and many algorithms have been p…

2016-05-20abs ↗pdf ↗

Unified bounds for random subset generalization error and improved SGD Langevin dynamics.

problem Generalization error bounds for random subsets and stochastic gradient Langevin dynamics.
method Unified framework based on Hellström and Durisi's work, extending bounds for Langevin dynamics.
result Unified and refined bounds for generalization error in stochastic gradient Langevin dynamics.

Langevin diffusion is a commonly used tool for sampling from a given distribution. In this work, we establish that when the target density pp^* is such that logp\log p^* is LL smooth and mm strongly convex, discrete Langevin diffusion produces a distribution pp with KL(pp)εKL(p||p^*)\leq ε in O~(dε)\tilde{O}(\frac{d}ε) steps,…

2017-05-25abs ↗pdf ↗

SGD in DLNs reveals feature learning dynamics.

problem Understanding SGD dynamics in DLNs during saddle-to-saddle training.
method Stochastic Langevin dynamics with anisotropic, state-dependent noise; one-dimensional per-mode SDEs; Boltzmann distribution approximation.
result SGD noise encodes feature learning progression but does not alter saddle-to-saddle dynamics.

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.

In this paper, we propose a novel technique to implement stochastic gradient methods, which are beneficial for learning from large datasets, through accelerated stochastic dynamics. A stochastic gradient method is based on mini-batch learning for reducing the computational cost when the amount of data is large. The sto…

2015-11-19abs ↗pdf ↗

Paper proposes Langevin dynamics for adaptive IRL of stochastic gradient algorithms.

problem Estimating reward functions from noisy gradient estimates of stochastic gradient agents.
method Generalized Langevin dynamics algorithm for IRL.
result Proposed algorithms asymptotically generate samples proportional to exp(R(θ)).