Kronecker-Factored Approximate Curvature for Modern Neural Network Architectures

• URL: http://arxiv.org/abs/2311.00636v2
• Date: Thu, 11 Jan 2024 17:32:26 GMT
• Title: Kronecker-Factored Approximate Curvature for Modern Neural Network Architectures
• Authors: Runa Eschenhagen, Alexander Immer, Richard E. Turner, Frank Schneider, Philipp Hennig
• Abstract summary: Two different settings of linear weight-sharing layers motivate two flavours of Kronecker-Factored Approximate Curvature (K-FAC) We show they are exact for deep linear networks with weight-sharing in their respective setting. We observe little difference between these two K-FAC variations when using them to train both a graph neural network and a vision transformer.
• Score: 85.76673783330334
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The core components of many modern neural network architectures, such as transformers, convolutional, or graph neural networks, can be expressed as linear layers with $\textit{weight-sharing}$. Kronecker-Factored Approximate Curvature (K-FAC), a second-order optimisation method, has shown promise to speed up neural network training and thereby reduce computational costs. However, there is currently no framework to apply it to generic architectures, specifically ones with linear weight-sharing layers. In this work, we identify two different settings of linear weight-sharing layers which motivate two flavours of K-FAC -- $\textit{expand}$ and $\textit{reduce}$. We show that they are exact for deep linear networks with weight-sharing in their respective setting. Notably, K-FAC-reduce is generally faster than K-FAC-expand, which we leverage to speed up automatic hyperparameter selection via optimising the marginal likelihood for a Wide ResNet. Finally, we observe little difference between these two K-FAC variations when using them to train both a graph neural network and a vision transformer. However, both variations are able to reach a fixed validation metric target in $50$-$75\%$ of the number of steps of a first-order reference run, which translates into a comparable improvement in wall-clock time. This highlights the potential of applying K-FAC to modern neural network architectures.

Related papers

• Tiled Bit Networks: Sub-Bit Neural Network Compression Through Reuse of Learnable Binary Vectors [4.95475852994362]
  We propose a new form of quantization to tile neural network layers with sequences of bits to achieve sub-bit compression of binary-weighted neural networks. We employ the approach to both fully-connected and convolutional layers, which make up the breadth of space in most neural architectures.
  arXiv  Detail & Related papers  (2024-07-16T15:55:38Z)
• Kronecker-Factored Approximate Curvature for Physics-Informed Neural Networks [3.7308074617637588]
  We propose Kronecker-factored approximate curvature (KFAC) for PINN losses that greatly reduces the computational cost and allows scaling to much larger networks. We find that our KFAC-based gradients are competitive with expensive second-order methods on small problems, scale more favorably to higher-dimensional neural networks and PDEs, and consistently outperform first-order methods and LBFGS.
  arXiv  Detail & Related papers  (2024-05-24T14:36:02Z)
• Principled Architecture-aware Scaling of Hyperparameters [69.98414153320894]
  Training a high-quality deep neural network requires choosing suitable hyperparameters, which is a non-trivial and expensive process. In this work, we precisely characterize the dependence of initializations and maximal learning rates on the network architecture. We demonstrate that network rankings can be easily changed by better training networks in benchmarks.
  arXiv  Detail & Related papers  (2024-02-27T11:52:49Z)
• ReLU Neural Networks with Linear Layers are Biased Towards Single- and Multi-Index Models [9.96121040675476]
  This manuscript explores how properties of functions learned by neural networks of depth greater than two layers affect predictions. Our framework considers a family of networks of varying depths that all have the same capacity but different representation costs.
  arXiv  Detail & Related papers  (2023-05-24T22:10:12Z)
• Combinatorial optimization for low bit-width neural networks [23.466606660363016]
  Low-bit width neural networks have been extensively explored for deployment on edge devices to reduce computational resources. Existing approaches have focused on gradient-based optimization in a two-stage train-and-compress setting. We show that a combination of greedy coordinate descent and this novel approach can attain competitive accuracy on binary classification tasks.
  arXiv  Detail & Related papers  (2022-06-04T15:02:36Z)
• Instant Neural Graphics Primitives with a Multiresolution Hash Encoding [67.33850633281803]
  We present a versatile new input encoding that permits the use of a smaller network without sacrificing quality. A small neural network is augmented by a multiresolution hash table of trainable feature vectors whose values are optimized through a gradient descent. We achieve a combined speed of several orders of magnitude, enabling training of high-quality neural graphics primitives in a matter of seconds.
  arXiv  Detail & Related papers  (2022-01-16T07:22:47Z)
• Scalable Lipschitz Residual Networks with Convex Potential Flows [120.27516256281359]
  We show that using convex potentials in a residual network gradient flow provides a built-in $1$-Lipschitz transformation. A comprehensive set of experiments on CIFAR-10 demonstrates the scalability of our architecture and the benefit of our approach for $ell$ provable defenses.
  arXiv  Detail & Related papers  (2021-10-25T07:12:53Z)
• Learning N:M Fine-grained Structured Sparse Neural Networks From Scratch [75.69506249886622]
  Sparsity in Deep Neural Networks (DNNs) has been widely studied to compress and accelerate the models on resource-constrained environments. In this paper, we are the first to study training from scratch an N:M fine-grained structured sparse network.
  arXiv  Detail & Related papers  (2021-02-08T05:55:47Z)
• Convolutional Neural Network Training with Distributed K-FAC [14.2773046188145]
  Kronecker-factored Approximate Curvature (K-FAC) was recently proposed as an approximation of the Fisher Information Matrix. We investigate here a scalable K-FAC design and its applicability in convolutional neural network (CNN) training at scale.
  arXiv  Detail & Related papers  (2020-07-01T22:00:53Z)
• Network Adjustment: Channel Search Guided by FLOPs Utilization Ratio [101.84651388520584]
  This paper presents a new framework named network adjustment, which considers network accuracy as a function of FLOPs. Experiments on standard image classification datasets and a wide range of base networks demonstrate the effectiveness of our approach.
  arXiv  Detail & Related papers  (2020-04-06T15:51:00Z)

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.