The Geometry of Neural Nets' Parameter Spaces Under Reparametrization

• URL: http://arxiv.org/abs/2302.07384v3
• Date: Mon, 23 Oct 2023 17:04:14 GMT
• Title: The Geometry of Neural Nets' Parameter Spaces Under Reparametrization
• Authors: Agustinus Kristiadi and Felix Dangel and Philipp Hennig
• Abstract summary: We study the invariance of neural nets under reparametrization from the perspective of Riemannian geometry. We discuss implications for measuring the flatness of minima, optimization, and for probability-density.
• Score: 35.5848464226014
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Model reparametrization, which follows the change-of-variable rule of calculus, is a popular way to improve the training of neural nets. But it can also be problematic since it can induce inconsistencies in, e.g., Hessian-based flatness measures, optimization trajectories, and modes of probability densities. This complicates downstream analyses: e.g. one cannot definitively relate flatness with generalization since arbitrary reparametrization changes their relationship. In this work, we study the invariance of neural nets under reparametrization from the perspective of Riemannian geometry. From this point of view, invariance is an inherent property of any neural net if one explicitly represents the metric and uses the correct associated transformation rules. This is important since although the metric is always present, it is often implicitly assumed as identity, and thus dropped from the notation, then lost under reparametrization. We discuss implications for measuring the flatness of minima, optimization, and for probability-density maximization. Finally, we explore some interesting directions where invariance is useful.

Related papers

• Benign overfitting in Fixed Dimension via Physics-Informed Learning with Smooth Inductive Bias [8.668428992331808]
  We develop an Sobolev norm learning curve for kernel ridge(less) regression when addressing (elliptical) linear inverse problems. Our results show that the PDE operators in the inverse problem can stabilize the variance and even behave benign overfitting for fixed-dimensional problems.
  arXiv  Detail & Related papers  (2024-06-13T14:54:30Z)
• Reparameterization invariance in approximate Bayesian inference [32.88960624085645]
  We develop a new geometric view of reparametrizations from which we explain the success of linearization. We demonstrate that these re parameterization invariance properties can be extended to the original neural network predictive.
  arXiv  Detail & Related papers  (2024-06-05T14:49:15Z)
• The Inductive Bias of Flatness Regularization for Deep Matrix Factorization [58.851514333119255]
  This work takes the first step toward understanding the inductive bias of the minimum trace of the Hessian solutions in deep linear networks. We show that for all depth greater than one, with the standard Isometry Property (RIP) on the measurements, minimizing the trace of Hessian is approximately equivalent to minimizing the Schatten 1-norm of the corresponding end-to-end matrix parameters.
  arXiv  Detail & Related papers  (2023-06-22T23:14:57Z)
• Instance-Dependent Generalization Bounds via Optimal Transport [51.71650746285469]
  Existing generalization bounds fail to explain crucial factors that drive the generalization of modern neural networks. We derive instance-dependent generalization bounds that depend on the local Lipschitz regularity of the learned prediction function in the data space. We empirically analyze our generalization bounds for neural networks, showing that the bound values are meaningful and capture the effect of popular regularization methods during training.
  arXiv  Detail & Related papers  (2022-11-02T16:39:42Z)
• Scale-invariant Bayesian Neural Networks with Connectivity Tangent Kernel [30.088226334627375]
  We show that flatness and generalization bounds can be changed arbitrarily according to the scale of a parameter. We propose new prior and posterior distributions invariant to scaling transformations by textitdecomposing the scale and connectivity of parameters. We empirically demonstrate our posterior provides effective flatness and calibration measures with low complexity.
  arXiv  Detail & Related papers  (2022-09-30T03:31:13Z)
• Equivariance Discovery by Learned Parameter-Sharing [153.41877129746223]
  We study how to discover interpretable equivariances from data. Specifically, we formulate this discovery process as an optimization problem over a model's parameter-sharing schemes. Also, we theoretically analyze the method for Gaussian data and provide a bound on the mean squared gap between the studied discovery scheme and the oracle scheme.
  arXiv  Detail & Related papers  (2022-04-07T17:59:19Z)
• Revisiting Transformation Invariant Geometric Deep Learning: Are Initial Representations All You Need? [80.86819657126041]
  We show that transformation-invariant and distance-preserving initial representations are sufficient to achieve transformation invariance. Specifically, we realize transformation-invariant and distance-preserving initial point representations by modifying multi-dimensional scaling. We prove that TinvNN can strictly guarantee transformation invariance, being general and flexible enough to be combined with the existing neural networks.
  arXiv  Detail & Related papers  (2021-12-23T03:52:33Z)
• Depth Without the Magic: Inductive Bias of Natural Gradient Descent [1.020554144865699]
  In gradient descent, changing how we parametrize the model can lead to drastically different optimization trajectories. We characterize the behaviour of natural gradient flow in deep linear networks for separable classification under logistic loss and deep matrix factorization. We demonstrate that there exist learning problems where natural gradient descent fails to generalize, while gradient descent with the right architecture performs well.
  arXiv  Detail & Related papers  (2021-11-22T21:20:10Z)
• Fundamental Limits and Tradeoffs in Invariant Representation Learning [99.2368462915979]
  Many machine learning applications involve learning representations that achieve two competing goals. Minimax game-theoretic formulation represents a fundamental tradeoff between accuracy and invariance. We provide an information-theoretic analysis of this general and important problem under both classification and regression settings.
  arXiv  Detail & Related papers  (2020-12-19T15:24:04Z)
• Learning Invariances in Neural Networks [51.20867785006147]
  We show how to parameterize a distribution over augmentations and optimize the training loss simultaneously with respect to the network parameters and augmentation parameters. We can recover the correct set and extent of invariances on image classification, regression, segmentation, and molecular property prediction from a large space of augmentations.
  arXiv  Detail & Related papers  (2020-10-22T17:18:48Z)

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.