Stochastic Gradient Descent-like relaxation is equivalent to Metropolis dynamics in discrete optimization and inference problems

• URL: http://arxiv.org/abs/2309.05337v2
• Date: Thu, 30 May 2024 09:11:51 GMT
• Title: Stochastic Gradient Descent-like relaxation is equivalent to Metropolis dynamics in discrete optimization and inference problems
• Authors: Maria Chiara Angelini, Angelo Giorgio Cavaliere, Raffaele Marino, Federico Ricci-Tersenghi,
• Abstract summary: We show that the dynamics of an SGD-like algorithm resemble very closely that of Metropolis Monte Carlo with a properly chosen temperature. This equivalence allows us to use results about performances and limits of Monte Carlo algorithms to optimize the mini-batch size in the SGD-like algorithm.
• Score: 0.7499722271664147
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Is Stochastic Gradient Descent (SGD) substantially different from Metropolis Monte Carlo dynamics? This is a fundamental question at the time of understanding the most used training algorithm in the field of Machine Learning, but it received no answer until now. Here we show that in discrete optimization and inference problems, the dynamics of an SGD-like algorithm resemble very closely that of Metropolis Monte Carlo with a properly chosen temperature, which depends on the mini-batch size. This quantitative matching holds both at equilibrium and in the out-of-equilibrium regime, despite the two algorithms having fundamental differences (e.g.\ SGD does not satisfy detailed balance). Such equivalence allows us to use results about performances and limits of Monte Carlo algorithms to optimize the mini-batch size in the SGD-like algorithm and make it efficient at recovering the signal in hard inference problems.

Related papers

• A Stochastic Approach to Bi-Level Optimization for Hyperparameter Optimization and Meta Learning [74.80956524812714]
  We tackle the general differentiable meta learning problem that is ubiquitous in modern deep learning. These problems are often formalized as Bi-Level optimizations (BLO) We introduce a novel perspective by turning a given BLO problem into a ii optimization, where the inner loss function becomes a smooth distribution, and the outer loss becomes an expected loss over the inner distribution.
  arXiv  Detail & Related papers  (2024-10-14T12:10:06Z)
• Greedy versus Map-based Optimized Adaptive Algorithms for random-telegraph-noise mitigation by spectator qubits [6.305016513788048]
  In a scenario where data-storage qubits are kept in isolation as far as possible, noise mitigation can still be done using additional noise probes. We construct a theoretical model assuming projective measurements on the qubits, and derive the performance of different measurement and control strategies. We show, analytically and numerically, that MOAAAR outperforms the Greedy algorithm, especially in the regime of high noise sensitivity of SQ.
  arXiv  Detail & Related papers  (2022-05-25T08:25:10Z)
• Improved Convergence Rate of Stochastic Gradient Langevin Dynamics with Variance Reduction and its Application to Optimization [50.83356836818667]
  gradient Langevin Dynamics is one of the most fundamental algorithms to solve non-eps optimization problems. In this paper, we show two variants of this kind, namely the Variance Reduced Langevin Dynamics and the Recursive Gradient Langevin Dynamics.
  arXiv  Detail & Related papers  (2022-03-30T11:39:00Z)
• The effective noise of Stochastic Gradient Descent [9.645196221785694]
  Gradient Descent (SGD) is the workhorse algorithm of deep learning technology. We characterize the parameters of SGD and a recently-introduced variant, persistent SGD, in a neural network model. We find that noisier algorithms lead to wider decision boundaries of the corresponding constraint satisfaction problem.
  arXiv  Detail & Related papers  (2021-12-20T20:46:19Z)
• Non Asymptotic Bounds for Optimization via Online Multiplicative Stochastic Gradient Descent [0.0]
  The gradient noise of Gradient Descent (SGD) is considered to play a key role in its properties. We show that noise classes that have the same mean and covariance structure of SGD via minibatching have similar properties. We also establish bounds for the convergence of the M-SGD algorithm in the strongly convex regime.
  arXiv  Detail & Related papers  (2021-12-14T02:25:43Z)
• Quantum algorithm for stochastic optimal stopping problems with applications in finance [60.54699116238087]
  The famous least squares Monte Carlo (LSM) algorithm combines linear least square regression with Monte Carlo simulation to approximately solve problems in optimal stopping theory. We propose a quantum LSM based on quantum access to a process, on quantum circuits for computing the optimal stopping times, and on quantum techniques for Monte Carlo.
  arXiv  Detail & Related papers  (2021-11-30T12:21:41Z)
• Differentiable Annealed Importance Sampling and the Perils of Gradient Noise [68.44523807580438]
  Annealed importance sampling (AIS) and related algorithms are highly effective tools for marginal likelihood estimation. Differentiability is a desirable property as it would admit the possibility of optimizing marginal likelihood as an objective. We propose a differentiable algorithm by abandoning Metropolis-Hastings steps, which further unlocks mini-batch computation.
  arXiv  Detail & Related papers  (2021-07-21T17:10:14Z)
• Plug-And-Play Learned Gaussian-mixture Approximate Message Passing [71.74028918819046]
  We propose a plug-and-play compressed sensing (CS) recovery algorithm suitable for any i.i.d. source prior. Our algorithm builds upon Borgerding's learned AMP (LAMP), yet significantly improves it by adopting a universal denoising function within the algorithm. Numerical evaluation shows that the L-GM-AMP algorithm achieves state-of-the-art performance without any knowledge of the source prior.
  arXiv  Detail & Related papers  (2020-11-18T16:40:45Z)
• Stochastic Gradient Langevin Dynamics Algorithms with Adaptive Drifts [8.36840154574354]
  We propose a class of adaptive gradient Markov chain Monte Carlo (SGMCMC) algorithms, where the drift function is biased to enhance escape from saddle points and the bias is adaptively adjusted according to the gradient of past samples. We demonstrate via numerical examples that the proposed algorithms can significantly outperform the existing SGMCMC algorithms.
  arXiv  Detail & Related papers  (2020-09-20T22:03:39Z)
• Single-Timescale Stochastic Nonconvex-Concave Optimization for Smooth Nonlinear TD Learning [145.54544979467872]
  We propose two single-timescale single-loop algorithms that require only one data point each step. Our results are expressed in a form of simultaneous primal and dual side convergence.
  arXiv  Detail & Related papers  (2020-08-23T20:36:49Z)
• Multi-index Antithetic Stochastic Gradient Algorithm [0.0]
  Gradient algorithms (SGAs) are ubiquitous in computational statistics, machine learning and optimisation. Recent years have brought an influx of interest in SGAs, and the non-asymptotic analysis of their bias is now well-developed. We show that MASGA is an optimal estimator from the mean square error-computational cost perspective within the class of Monte Carlo estimators.
  arXiv  Detail & Related papers  (2020-06-10T22:59:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.