paper-with-me

홈 › Papers

Preconditioners for the Stochastic Training of Implicit Neural Representations

2024-02-13 · Shin-Fang Chng, Hemanth Saratchandran, Simon Lucey

Implicit neural representations have emerged as a powerful technique for encoding complex continuous multidimensional signals as neural networks, enabling a wide range of applications in computer vision, robotics, and geometry. While Adam is commonly used for training due to its stochastic proficiency, it entails lengthy training durations. To address this, we explore alternative optimization techniques for accelerated training without sacrificing accuracy. Traditional second-order optimizers like L-BFGS are suboptimal in stochastic settings, making them unsuitable for large-scale data sets. Instead, we propose stochastic training using curvature-aware diagonal preconditioners, showcasing their effectiveness across various signal modalities such as images, shape reconstruction, and Neural Radiance Fields (NeRF).

📄 PDF Abstract BibTeX arXiv:2402.08784

Code (0)

등록된 구현이 없습니다.

Tasks

NeRF

Methods 이 논문이 사용한 방법론

Adam 설명 없음

Similar Papers 제목 키워드 기반

Preconditioners for the Stochastic Training of Neural Fields

2025-01-01 · CVPR 2025 1 · Shin-Fang Chng, Hemanth Saratchandran, Simon Lucey

Neural fields encode continuous multidimensional signals as neural networks, enabling diverse applications in computer vision, robotics, and geometry. While Adam is effective for stochastic optimization, it often req…

Image ReconstructionNeRFSecond-order methodsStochastic Optimization

Stochastic Preconditioning for Neural Field Optimization

2025-05-26 · Selena Ling, Merlin Nimier-David, Alec Jacobson, Nicholas Sharp

Neural fields are a highly effective representation across visual computing. This work observes that fitting these fields is greatly improved by incorporating spatial stochasticity during training, and that this simple t…

Surface Reconstruction

Online Second Order Methods for Non-Convex Stochastic Optimizations

2018-03-26 · Xi-Lin Li

This paper proposes a family of online second order methods for possibly non-convex stochastic optimizations based on the theory of preconditioned stochastic gradient descent (PSGD), which can be regarded as an enhance s…

Second-order methods

A General Family of Stochastic Proximal Gradient Methods for Deep Learning

2020-07-15 · Jihun Yun, Aurelie C. Lozano, Eunho Yang

We study the training of regularized neural networks where the regularizer can be non-smooth and non-convex. We propose a unified framework for stochastic proximal gradient descent, which we term ProxGen, that allows for…

Quantization

Curvature-Informed SGD via General Purpose Lie-Group Preconditioners

2024-02-07 · Omead Pooladzandi, Xi-Lin Li

We present a novel approach to accelerate stochastic gradient descent (SGD) by utilizing curvature information obtained from Hessian-vector products or finite differences of parameters and gradients, similar to the BFGS …