Preconditioners for the Stochastic Training of Implicit Neural Representations

• URL: http://arxiv.org/abs/2402.08784v1
• Date: Tue, 13 Feb 2024 20:46:37 GMT
• Title: Preconditioners for the Stochastic Training of Implicit Neural Representations
• Authors: Shin-Fang Chng, Hemanth Saratchandran, Simon Lucey
• Abstract summary: Implicit neural representations have emerged as a powerful technique for encoding complex continuous multidimensional signals as neural networks. We propose training using diagonal preconditioners, showcasing their effectiveness across various signal modalities.
• Score: 30.92757082348805
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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).

Related papers

• Simmering: Sufficient is better than optimal for training neural networks [0.0]
  We introduce simmering, a physics-based method that trains neural networks to generate weights and biases that are merely good enough'' We show that simmering corrects neural networks that are overfit by Adam, and show that simmering avoids overfitting if deployed from the outset. Our results question optimization as a paradigm for neural network training, and leverage information-geometric arguments to point to the existence of classes of sufficient training algorithms.
  arXiv  Detail & Related papers  (2024-10-25T18:02:08Z)
• Self-STORM: Deep Unrolled Self-Supervised Learning for Super-Resolution Microscopy [55.2480439325792]
  We introduce deep unrolled self-supervised learning, which alleviates the need for such data by training a sequence-specific, model-based autoencoder. Our proposed method exceeds the performance of its supervised counterparts.
  arXiv  Detail & Related papers  (2024-03-25T17:40:32Z)
• Always-Sparse Training by Growing Connections with Guided Stochastic Exploration [46.4179239171213]
  We propose an efficient always-sparse training algorithm with excellent scaling to larger and sparser models. We evaluate our method on CIFAR-10/100 and ImageNet using VGG, and ViT models, and compare it against a range of sparsification methods.
  arXiv  Detail & Related papers  (2024-01-12T21:32:04Z)
• The Convex Landscape of Neural Networks: Characterizing Global Optima and Stationary Points via Lasso Models [75.33431791218302]
  Deep Neural Network Network (DNN) models are used for programming purposes. In this paper we examine the use of convex neural recovery models. We show that all the stationary non-dimensional objective objective can be characterized as the standard a global subsampled convex solvers program. We also show that all the stationary non-dimensional objective objective can be characterized as the standard a global subsampled convex solvers program.
  arXiv  Detail & Related papers  (2023-12-19T23:04:56Z)
• Implicit Stochastic Gradient Descent for Training Physics-informed Neural Networks [51.92362217307946]
  Physics-informed neural networks (PINNs) have effectively been demonstrated in solving forward and inverse differential equation problems. PINNs are trapped in training failures when the target functions to be approximated exhibit high-frequency or multi-scale features. In this paper, we propose to employ implicit gradient descent (ISGD) method to train PINNs for improving the stability of training process.
  arXiv  Detail & Related papers  (2023-03-03T08:17:47Z)
• Intelligence Processing Units Accelerate Neuromorphic Learning [52.952192990802345]
  Spiking neural networks (SNNs) have achieved orders of magnitude improvement in terms of energy consumption and latency. We present an IPU-optimized release of our custom SNN Python package, snnTorch.
  arXiv  Detail & Related papers  (2022-11-19T15:44:08Z)
• Random Weight Factorization Improves the Training of Continuous Neural Representations [1.911678487931003]
  Continuous neural representations have emerged as a powerful and flexible alternative to classical discretized representations of signals. We propose random weight factorization as a simple drop-in replacement for parameterizing and initializing conventional linear layers. We show how this factorization alters the underlying loss landscape and effectively enables each neuron in the network to learn using its own self-adaptive learning rate.
  arXiv  Detail & Related papers  (2022-10-03T23:48:48Z)
• Bayesian Optimisation-Assisted Neural Network Training Technique for Radio Localisation [3.0981875303080804]
  Radio signal-based (indoor) localisation technique is important for IoT applications such as smart factory and warehouse. Different radio protocols have different features in the transmitted signals that can be exploited for localisation. Neural networks methods often rely on carefully configured models and extensive training processes to obtain satisfactory performance.
  arXiv  Detail & Related papers  (2022-03-08T11:46:41Z)
• Learning Neural Network Subspaces [74.44457651546728]
  Recent observations have advanced our understanding of the neural network optimization landscape. With a similar computational cost as training one model, we learn lines, curves, and simplexes of high-accuracy neural networks. With a similar computational cost as training one model, we learn lines, curves, and simplexes of high-accuracy neural networks.
  arXiv  Detail & Related papers  (2021-02-20T23:26:58Z)
• Hyperparameter Optimization in Binary Communication Networks for Neuromorphic Deployment [4.280642750854163]
  Training neural networks for neuromorphic deployment is non-trivial. We introduce a Bayesian approach for optimizing the hyper parameters of an algorithm for training binary communication networks that can be deployed to neuromorphic hardware. We show that by optimizing the hyper parameters on this algorithm for each dataset, we can achieve improvements in accuracy over the previous state-of-the-art for this algorithm on each dataset.
  arXiv  Detail & Related papers  (2020-04-21T01:15:45Z)
• Large-Scale Gradient-Free Deep Learning with Recursive Local Representation Alignment [84.57874289554839]
  Training deep neural networks on large-scale datasets requires significant hardware resources. Backpropagation, the workhorse for training these networks, is an inherently sequential process that is difficult to parallelize. We propose a neuro-biologically-plausible alternative to backprop that can be used to train deep networks.
  arXiv  Detail & Related papers  (2020-02-10T16:20:02Z)

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.