paper-with-me

홈 › Papers

Stochastic Gradient Langevin Dynamics Based on Quantization with Increasing Resolution

2023-05-30 · Jinwuk Seok, Changsik Cho

Stochastic learning dynamics based on Langevin or Levy stochastic differential equations (SDEs) in deep neural networks control the variance of noise by varying the size of the mini-batch or directly those of injecting noise. Since the noise variance affects the approximation performance, the design of the additive noise is significant in SDE-based learning and practical implementation. In this paper, we propose an alternative stochastic descent learning equation based on quantized optimization for non-convex objective functions, adopting a stochastic analysis perspective. The proposed method employs a quantized optimization approach that utilizes Langevin SDE dynamics, allowing for controllable noise with an identical distribution without the need for additive noise or adjusting the mini-batch size. Numerical experiments demonstrate the effectiveness of the proposed algorithm on vanilla convolution neural network(CNN) models and the ResNet-50 architecture across various data sets. Furthermore, we provide a simple PyTorch implementation of the proposed algorithm.

📄 PDF Abstract BibTeX arXiv:2305.18864

Code (0)

등록된 구현이 없습니다.

Tasks

Quantization

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Similar Papers 제목 키워드 기반

Adaptive Stochastic Gradient Langevin Dynamics: Taming Convergence and Saddle Point Escape Time

2018-05-23 · Hejian Sang, Jia Liu

In this paper, we propose a new adaptive stochastic gradient Langevin dynamics (ASGLD) algorithmic framework and its two specialized versions, namely adaptive stochastic gradient (ASG) and adaptive gradient Langevin dyna…

Low-Precision Stochastic Gradient Langevin Dynamics

2022-06-20 · Ruqi Zhang, Andrew Gordon Wilson, Christopher De Sa

While low-precision optimization has been widely used to accelerate deep learning, low-precision sampling remains largely unexplored. As a consequence, sampling is simply infeasible in many large-scale scenarios, despite…

Deep LearningQuantization

Graph Energy-based Model for Molecular Graph Generation

2021-02-26 · ICLR Workshop EBM 2021 5 · Ryuichiro Hataya, Hideki Nakayama, Kazuki Yoshizoe

We present Graph Energy-based Model (GEM), an energy-based model for molecular graph generation. GEM uses dequantization and gradient symmetrization to incorporate generation by stochastic gradient Langevin dynamics for …

Graph GenerationmodelMolecular Graph Generation

Global Convergence of Langevin Dynamics Based Algorithms for Nonconvex Optimization

2017-07-20 · NeurIPS 2018 12 · Pan Xu, Jinghui Chen, Difan Zou, Quanquan Gu

We present a unified framework to analyze the global convergence of Langevin dynamics based algorithms for nonconvex finite-sum optimization with $n$ component functions. At the core of our analysis is a direct analysis …

Variance Reduction in Stochastic Gradient Langevin Dynamics

2016-12-01 · NeurIPS 2016 12 · Kumar Avinava Dubey, Sashank J. Reddi, Sinead A. Williamson, Barnabas Poczos 외

Stochastic gradient-based Monte Carlo methods such as stochastic gradient Langevin dynamics are useful tools for posterior inference on large scale datasets in many machine learning applications. These methods scale to l…

BIG-bench Machine Learning