English
Related papers

Related papers: A Langevin sampling algorithm inspired by the Adam…

200 papers

Gradient methods are widely used in optimization problems. In practice, while the smoothness parameter can be estimated utilizing techniques such as backtracking, estimating the strong convexity parameter remains a challenge; moreover, even…

Optimization and Control · Mathematics 2026-02-17 Xiaozhe Hu , Sara Pollock , Zhongqin Xue , Yunrong Zhu

Most existing approximate Thompson Sampling (TS) algorithms for multi-armed bandits use Stochastic Gradient Langevin Dynamics (SGLD) or its variants in each round to sample from the posterior, relaxing the need for conjugacy assumptions…

Machine Learning · Computer Science 2025-10-07 Weixin Wang , Haoyang Zheng , Guang Lin , Wei Deng , Pan Xu

Recent studies on diffusion-based sampling methods have shown that Langevin Monte Carlo (LMC) algorithms can be beneficial for non-convex optimization, and rigorous theoretical guarantees have been proven for both asymptotic and finite-time…

Optimization and Control · Mathematics 2019-01-23 Thanh Huy Nguyen , Umut Şimşekli , Gaël Richard

This paper discusses the adaptive sampling problem in a nonholonomic mobile robotic sensor network for efficiently monitoring a spatial field. It is proposed to employ Gaussian process to model a spatial phenomenon and predict it at…

Robotics · Computer Science 2021-03-23 Viet-Anh Le , Linh Nguyen , Truong X. Nghiem

There has been a surge of works bridging MCMC sampling and optimization, with a specific focus on translating non-asymptotic convergence guarantees for optimization problems into the analysis of Langevin algorithms in MCMC sampling. A…

Machine Learning · Computer Science 2021-10-06 Yoav Freund , Yi-An Ma , Tong Zhang

Stochastic quantization offers the opportunity to simulate field theories with a complex action. In some theories unstable trajectories are prevalent when a constant stepsize is employed. We construct algorithms for generating an adaptive…

High Energy Physics - Lattice · Physics 2014-11-20 Gert Aarts , Frank A. James , Erhard Seiler , Ion-Olimpiu Stamatescu

Gradient descent (GD) based optimization methods are these days the standard tools to train deep neural networks in artificial intelligence systems. In optimization procedures in deep learning the employed optimizer is often not the…

Optimization and Control · Mathematics 2025-09-24 Steffen Dereich , Robin Graeber , Arnulf Jentzen , Adrian Riekert

In continual learning, a learner has to keep learning from the data over its whole life time. A key issue is to decide what knowledge to keep and what knowledge to let go. In a neural network, this can be implemented by using a step-size…

Machine Learning · Computer Science 2024-02-01 Thomas Degris , Khurram Javed , Arsalan Sharifnassab , Yuxin Liu , Richard Sutton

We introduce a novel and efficient algorithm called the stochastic approximate gradient descent (SAGD), as an alternative to the stochastic gradient descent for cases where unbiased stochastic gradients cannot be trivially obtained.…

Machine Learning · Computer Science 2020-02-14 Yixuan Qiu , Xiao Wang

Solving the optimal symbol detection problem in multiple-input multiple-output (MIMO) systems is known to be NP-hard. Hence, the objective of any detector of practical relevance is to get reasonably close to the optimal solution while…

Signal Processing · Electrical Eng. & Systems 2023-03-20 Nicolas Zilberstein , Chris Dick , Rahman Doost-Mohammady , Ashutosh Sabharwal , Santiago Segarra

Training instability in modern deep learning systems is frequently triggered by rare but extreme gradient-norm spikes, which can induce oversized parameter updates, corrupt optimizer state, and lead to slow recovery or divergence. Widely…

Although ADAM is a very popular algorithm for optimizing the weights of neural networks, it has been recently shown that it can diverge even in simple convex optimization examples. Several variants of ADAM have been proposed to circumvent…

Optimization and Control · Mathematics 2020-09-25 Anas Barakat , Pascal Bianchi

This paper provides the first tight convergence analyses for RMSProp and Adam in non-convex optimization under the most relaxed assumptions of coordinate-wise generalized smoothness and affine noise variance. We first analyze RMSProp, which…

Machine Learning · Statistics 2025-03-11 Qi Zhang , Yi Zhou , Shaofeng Zou

We present an unbiased method for Bayesian posterior means based on kinetic Langevin dynamics that combines advanced splitting methods with enhanced gradient approximations. Our approach avoids Metropolis correction by coupling Markov…

Computation · Statistics 2025-12-04 Neil K. Chada , Benedict Leimkuhler , Daniel Paulin , Peter A. Whalley

The classical Langevin Monte Carlo method looks for samples from a target distribution by descending the samples along the gradient of the target distribution. The method enjoys a fast convergence rate. However, the numerical cost is…

Machine Learning · Statistics 2025-03-07 Zhiyan Ding , Qin Li

The performance of Metropolis-Hastings algorithms is highly sensitive to the choice of step size, and miss-specification can lead to severe loss of efficiency. We study algorithms with randomized step sizes, considering both…

Computation · Statistics 2026-01-28 Sebastiano Grazzi , Samuel Livingstone , Lionel Riou-Durand

In a Hilbert setting, for convex differentiable optimization, we develop a general framework for adaptive accelerated gradient methods. They are based on damped inertial dynamics where the coefficients are designed in a closed-loop way.…

Optimization and Control · Mathematics 2025-01-28 Hedy Attouch , Radu Ioan Bot , Dang-Khoa Nguyen

The paper studies decentralized optimization over networks, where agents minimize a sum of {\it locally} smooth (strongly) convex losses and plus a nonsmooth convex extended value term. We propose decentralized methods wherein agents {\it…

Optimization and Control · Mathematics 2026-02-20 Xiaokai Chen , Ilya Kuruzov , Gesualdo Scutari

The choice of the stepsize in first-order convex optimization is typically based on the smoothness constant and plays a crucial role in the performance of algorithms. Recently, there has been a resurgent interest in introducing adaptive…

Optimization and Control · Mathematics 2025-12-04 Reza Rahimi Baghbadorani , Sergio Grammatico , Peyman Mohajerin Esfahani

We provide a new convergence analysis of stochastic gradient Langevin dynamics (SGLD) for sampling from a class of distributions that can be non-log-concave. At the core of our approach is a novel conductance analysis of SGLD using an…

Machine Learning · Computer Science 2021-02-24 Difan Zou , Pan Xu , Quanquan Gu