Online Laplace Model Selection Revisited

• URL: http://arxiv.org/abs/2307.06093v2
• Date: Tue, 9 Jan 2024 15:49:14 GMT
• Title: Online Laplace Model Selection Revisited
• Authors: Jihao Andreas Lin, Javier Antor\'an, Jos\'e Miguel Hern\'andez-Lobato
• Abstract summary: Online variants of the Laplace approximation have seen renewed interest in the Bayesian deep learning community. This work re-derives online Laplace methods, showing them to target a variational bound on a mode-corrected variant of the Laplace evidence. We demonstrate that these optima are roughly attained in practise by online algorithms using full-batch gradient descent on UCI regression datasets.
• Score: 0.6355355626203273
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The Laplace approximation provides a closed-form model selection objective for neural networks (NN). Online variants, which optimise NN parameters jointly with hyperparameters, like weight decay strength, have seen renewed interest in the Bayesian deep learning community. However, these methods violate Laplace's method's critical assumption that the approximation is performed around a mode of the loss, calling into question their soundness. This work re-derives online Laplace methods, showing them to target a variational bound on a mode-corrected variant of the Laplace evidence which does not make stationarity assumptions. Online Laplace and its mode-corrected counterpart share stationary points where 1. the NN parameters are a maximum a posteriori, satisfying the Laplace method's assumption, and 2. the hyperparameters maximise the Laplace evidence, motivating online methods. We demonstrate that these optima are roughly attained in practise by online algorithms using full-batch gradient descent on UCI regression datasets. The optimised hyperparameters prevent overfitting and outperform validation-based early stopping.

Related papers

• Training Deep Learning Models with Norm-Constrained LMOs [56.00317694850397]
  We study optimization methods that leverage the linear minimization oracle (LMO) over a norm-ball. We propose a new family of algorithms that uses the LMO to adapt to the geometry of the problem and, perhaps surprisingly, show that they can be applied to unconstrained problems.
  arXiv  Detail & Related papers  (2025-02-11T13:10:34Z)
• PACMANN: Point Adaptive Collocation Method for Artificial Neural Networks [44.99833362998488]
  PINNs minimize a loss function which includes the PDE residual determined for a set of collocation points. Previous work has shown that the number and distribution of these collocation points have a significant influence on the accuracy of the PINN solution. We present the Point Adaptive Collocation Method for Artificial Neural Networks (PACMANN)
  arXiv  Detail & Related papers  (2024-11-29T11:31:11Z)
• Trust-Region Sequential Quadratic Programming for Stochastic Optimization with Random Models [57.52124921268249]
  We propose a Trust Sequential Quadratic Programming method to find both first and second-order stationary points. To converge to first-order stationary points, our method computes a gradient step in each iteration defined by minimizing a approximation of the objective subject. To converge to second-order stationary points, our method additionally computes an eigen step to explore the negative curvature the reduced Hessian matrix.
  arXiv  Detail & Related papers  (2024-09-24T04:39:47Z)
• G-Adaptivity: optimised graph-based mesh relocation for finite element methods [20.169049222190853]
  Mesh relocation (r-adaptivity) seeks to optimise the mesh geometry to obtain the best solution accuracy at given computational budget. Recent machine learning approaches have focused on the construction of fast surrogates for such classical methods. We present a novel, and effective, approach to achieve optimal mesh relocation in finite element methods (FEMs)
  arXiv  Detail & Related papers  (2024-07-05T13:57:35Z)
• Stochastic Marginal Likelihood Gradients using Neural Tangent Kernels [78.6096486885658]
  We introduce lower bounds to the linearized Laplace approximation of the marginal likelihood. These bounds are amenable togradient-based optimization and allow to trade off estimation accuracy against computational complexity.
  arXiv  Detail & Related papers  (2023-06-06T19:02:57Z)
• Distributed Sketching for Randomized Optimization: Exact Characterization, Concentration and Lower Bounds [54.51566432934556]
  We consider distributed optimization methods for problems where forming the Hessian is computationally challenging. We leverage randomized sketches for reducing the problem dimensions as well as preserving privacy and improving straggler resilience in asynchronous distributed systems.
  arXiv  Detail & Related papers  (2022-03-18T05:49:13Z)
• Low-rank variational Bayes correction to the Laplace method [0.0]
  We propose a hybrid approximate method called Low-Rank Variational Bayes correction (VBC) The cost is essentially that of the Laplace method which ensures scalability of the method, in both model complexity and data size.
  arXiv  Detail & Related papers  (2021-11-25T07:01:06Z)
• Online Hyperparameter Meta-Learning with Hypergradient Distillation [59.973770725729636]
  gradient-based meta-learning methods assume a set of parameters that do not participate in inner-optimization. We propose a novel HO method that can overcome these limitations, by approximating the second-order term with knowledge distillation.
  arXiv  Detail & Related papers  (2021-10-06T05:14:53Z)
• Bayesian Sparse learning with preconditioned stochastic gradient MCMC and its applications [5.660384137948734]
  The proposed algorithm converges to the correct distribution with a controllable bias under mild conditions. We show that the proposed algorithm canally converge to the correct distribution with a controllable bias under mild conditions.
  arXiv  Detail & Related papers  (2020-06-29T20:57:20Z)
• Implicit differentiation of Lasso-type models for hyperparameter optimization [82.73138686390514]
  We introduce an efficient implicit differentiation algorithm, without matrix inversion, tailored for Lasso-type problems. Our approach scales to high-dimensional data by leveraging the sparsity of the solutions.
  arXiv  Detail & Related papers  (2020-02-20T18:43:42Z)

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.