Adapting Newton's Method to Neural Networks through a Summary of Higher-Order Derivatives

• URL: http://arxiv.org/abs/2312.03885v2
• Date: Sat, 3 Feb 2024 09:00:08 GMT
• Title: Adapting Newton's Method to Neural Networks through a Summary of Higher-Order Derivatives
• Authors: Pierre Wolinski
• Abstract summary: We consider a gradient-based optimization method applied to a function $boldsymboltheta$. This framework encompasses many common use-cases, such as training neural networks by gradient descent.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We consider a gradient-based optimization method applied to a function $\mathcal{L}$ of a vector of variables $\boldsymbol{\theta}$, in the case where $\boldsymbol{\theta}$ is represented as a tuple of tensors $(\mathbf{T}_1, \cdots, \mathbf{T}_S)$. This framework encompasses many common use-cases, such as training neural networks by gradient descent. First, we propose a computationally inexpensive technique providing higher-order information on $\mathcal{L}$, especially about the interactions between the tensors $\mathbf{T}_s$, based on automatic differentiation and computational tricks. Second, we use this technique at order 2 to build a second-order optimization method which is suitable, among other things, for training deep neural networks of various architectures. This second-order method leverages the partition structure of $\boldsymbol{\theta}$ into tensors $(\mathbf{T}_1, \cdots, \mathbf{T}_S)$, in such a way that it requires neither the computation of the Hessian of $\mathcal{L}$ according to $\boldsymbol{\theta}$, nor any approximation of it. The key part consists in computing a smaller matrix interpretable as a "Hessian according to the partition", which can be computed exactly and efficiently. In contrast to many existing practical second-order methods used in neural networks, which perform a diagonal or block-diagonal approximation of the Hessian or its inverse, the method we propose does not neglect interactions between layers. Finally, we can tune the coarseness of the partition to recover well-known optimization methods: the coarsest case corresponds to Cauchy's steepest descent method, the finest case corresponds to the usual Newton's method.

Related papers

• A Quasilinear Algorithm for Computing Higher-Order Derivatives of Deep Feed-Forward Neural Networks [0.0]
  $n$-TangentProp computes the exact derivative $dn/dxn f(x)$ in quasilinear, instead of exponential time. We demonstrate that our method is particularly beneficial in the context of physics-informed neural networks.
  arXiv  Detail & Related papers  (2024-12-12T22:57:28Z)
• Inverting the Leverage Score Gradient: An Efficient Approximate Newton Method [10.742859956268655]
  This paper aims to recover the intrinsic model parameters given the leverage scores gradient. We specifically scrutinize the inversion of the leverage score gradient, denoted as $g(x)$.
  arXiv  Detail & Related papers  (2024-08-21T01:39:42Z)
• Neural network learns low-dimensional polynomials with SGD near the information-theoretic limit [75.4661041626338]
  We study the problem of gradient descent learning of a single-index target function $f_*(boldsymbolx) = textstylesigma_*left(langleboldsymbolx,boldsymbolthetarangleright)$ under isotropic Gaussian data. We prove that a two-layer neural network optimized by an SGD-based algorithm learns $f_*$ of arbitrary link function with a sample and runtime complexity of $n asymp T asymp C(q) cdot d
  arXiv  Detail & Related papers  (2024-06-03T17:56:58Z)
• FORML: A Riemannian Hessian-free Method for Meta-learning on Stiefel Manifolds [4.757859522106933]
  This paper introduces a Hessian-free approach that uses a first-order approximation of derivatives on the Stiefel manifold. Our method significantly reduces the computational load and memory footprint.
  arXiv  Detail & Related papers  (2024-02-28T10:57:30Z)
• Self-concordant Smoothing for Large-Scale Convex Composite Optimization [0.0]
  We introduce a notion of self-concordant smoothing for minimizing the sum of two convex functions, one of which is smooth and the other may be nonsmooth. We prove the convergence of two resulting algorithms: Prox-N-SCORE, a proximal Newton algorithm and Prox-GGN-SCORE, a proximal generalized Gauss-Newton algorithm.
  arXiv  Detail & Related papers  (2023-09-04T19:47:04Z)
• 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)
• Optimization using Parallel Gradient Evaluations on Multiple Parameters [51.64614793990665]
  We propose a first-order method for convex optimization, where gradients from multiple parameters can be used during each step of gradient descent. Our method uses gradients from multiple parameters in synergy to update these parameters together towards the optima.
  arXiv  Detail & Related papers  (2023-02-06T23:39:13Z)
• Randomized Block-Coordinate Optimistic Gradient Algorithms for Root-Finding Problems [8.0153031008486]
  We develop two new algorithms to approximate a solution of nonlinear equations in large-scale settings. We apply our methods to a class of large-scale finite-sum inclusions, which covers prominent applications in machine learning.
  arXiv  Detail & Related papers  (2023-01-08T21:46:27Z)
• 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)
• Optimal Gradient Sliding and its Application to Distributed Optimization Under Similarity [121.83085611327654]
  We structured convex optimization problems with additive objective $r:=p + q$, where $r$ is $mu$-strong convex similarity. We proposed a method to solve problems master to agents' communication and local calls. The proposed method is much sharper than the $mathcalO(sqrtL_q/mu)$ method.
  arXiv  Detail & Related papers  (2022-05-30T14:28:02Z)
• High-dimensional Asymptotics of Feature Learning: How One Gradient Step Improves the Representation [89.21686761957383]
  We study the first gradient descent step on the first-layer parameters $boldsymbolW$ in a two-layer network. Our results demonstrate that even one step can lead to a considerable advantage over random features.
  arXiv  Detail & Related papers  (2022-05-03T12:09:59Z)
• Reducing the Variance of Gaussian Process Hyperparameter Optimization with Preconditioning [54.01682318834995]
  Preconditioning is a highly effective step for any iterative method involving matrix-vector multiplication. We prove that preconditioning has an additional benefit that has been previously unexplored. It simultaneously can reduce variance at essentially negligible cost.
  arXiv  Detail & Related papers  (2021-07-01T06:43:11Z)
• SHINE: SHaring the INverse Estimate from the forward pass for bi-level optimization and implicit models [15.541264326378366]
  In recent years, implicit deep learning has emerged as a method to increase the depth of deep neural networks. The training is performed as a bi-level problem, and its computational complexity is partially driven by the iterative inversion of a huge Jacobian matrix. We propose a novel strategy to tackle this computational bottleneck from which many bi-level problems suffer.
  arXiv  Detail & Related papers  (2021-06-01T15:07:34Z)
• Implicit differentiation for fast hyperparameter selection in non-smooth convex learning [87.60600646105696]
  We study first-order methods when the inner optimization problem is convex but non-smooth. We show that the forward-mode differentiation of proximal gradient descent and proximal coordinate descent yield sequences of Jacobians converging toward the exact Jacobian.
  arXiv  Detail & Related papers  (2021-05-04T17:31:28Z)
• DyCo3D: Robust Instance Segmentation of 3D Point Clouds through Dynamic Convolution [136.7261709896713]
  We propose a data-driven approach that generates the appropriate convolution kernels to apply in response to the nature of the instances. The proposed method achieves promising results on both ScanetNetV2 and S3DIS. It also improves inference speed by more than 25% over the current state-of-the-art.
  arXiv  Detail & Related papers  (2020-11-26T14:56:57Z)
• Beyond Lazy Training for Over-parameterized Tensor Decomposition [69.4699995828506]
  We show that gradient descent on over-parametrized objective could go beyond the lazy training regime and utilize certain low-rank structure in the data. Our results show that gradient descent on over-parametrized objective could go beyond the lazy training regime and utilize certain low-rank structure in the data.
  arXiv  Detail & Related papers  (2020-10-22T00:32:12Z)
• Training (Overparametrized) Neural Networks in Near-Linear Time [21.616949485102342]
  We show how to speed up the algorithm of [CGH+1] for training (mildly overetrized) ReparamLU networks. The centerpiece of our algorithm is to reformulate the Gauss-Newton as an $ell$-recondition.
  arXiv  Detail & Related papers  (2020-06-20T20:26:14Z)
• Linear Time Sinkhorn Divergences using Positive Features [51.50788603386766]
  Solving optimal transport with an entropic regularization requires computing a $ntimes n$ kernel matrix that is repeatedly applied to a vector. We propose to use instead ground costs of the form $c(x,y)=-logdotpvarphi(x)varphi(y)$ where $varphi$ is a map from the ground space onto the positive orthant $RRr_+$, with $rll n$.
  arXiv  Detail & Related papers  (2020-06-12T10:21:40Z)
• On the Modularity of Hypernetworks [103.1147622394852]
  We show that for a structured target function, the overall number of trainable parameters in a hypernetwork is smaller by orders of magnitude than the number of trainable parameters of a standard neural network and an embedding method.
  arXiv  Detail & Related papers  (2020-02-23T22:51:52Z)
• A Corrective View of Neural Networks: Representation, Memorization and Learning [26.87238691716307]
  We develop a corrective mechanism for neural network approximation. We show that two-layer neural networks in the random features regime (RF) can memorize arbitrary labels. We also consider three-layer neural networks and show that the corrective mechanism yields faster representation rates for smooth radial functions.
  arXiv  Detail & Related papers  (2020-02-01T20:51:09Z)
• Supervised Learning for Non-Sequential Data: A Canonical Polyadic Decomposition Approach [85.12934750565971]
  Efficient modelling of feature interactions underpins supervised learning for non-sequential tasks. To alleviate this issue, it has been proposed to implicitly represent the model parameters as a tensor. For enhanced expressiveness, we generalize the framework to allow feature mapping to arbitrarily high-dimensional feature vectors.
  arXiv  Detail & Related papers  (2020-01-27T22:38:40Z)

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.