Convergence of energy-based learning in linear resistive networks

• URL: http://arxiv.org/abs/2503.00349v1
• Date: Sat, 01 Mar 2025 04:47:02 GMT
• Title: Convergence of energy-based learning in linear resistive networks
• Authors: Anne-Men Huijzer, Thomas Chaffey, Bart Besselink, Henk J. van Waarde,
• Abstract summary: Energy-based learning algorithms are well-suited to distributed implementations in analog electronic devices.<n>We make a first step in this direction by analysing a particular energy-based learning algorithm, Contrastive Learning, applied to a network of linear adjustable resistors.
• Score: 2.9248916859490173
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Energy-based learning algorithms are alternatives to backpropagation and are well-suited to distributed implementations in analog electronic devices. However, a rigorous theory of convergence is lacking. We make a first step in this direction by analysing a particular energy-based learning algorithm, Contrastive Learning, applied to a network of linear adjustable resistors. It is shown that, in this setup, Contrastive Learning is equivalent to projected gradient descent on a convex function, for any step size, giving a guarantee of convergence for the algorithm.

Related papers

• Stochastic Unrolled Federated Learning [85.6993263983062]
  We introduce UnRolled Federated learning (SURF), a method that expands algorithm unrolling to federated learning. Our proposed method tackles two challenges of this expansion, namely the need to feed whole datasets to the unrolleds and the decentralized nature of federated learning.
  arXiv  Detail & Related papers  (2023-05-24T17:26:22Z)
• Iterative regularization in classification via hinge loss diagonal descent [12.684351703991965]
  Iterative regularization is a classic idea in regularization theory, that has recently become popular in machine learning. In this paper, we focus on iterative regularization in the context of classification.
  arXiv  Detail & Related papers  (2022-12-24T07:15:26Z)
• Stabilizing Q-learning with Linear Architectures for Provably Efficient Learning [53.17258888552998]
  This work proposes an exploration variant of the basic $Q$-learning protocol with linear function approximation. We show that the performance of the algorithm degrades very gracefully under a novel and more permissive notion of approximation error.
  arXiv  Detail & Related papers  (2022-06-01T23:26:51Z)
• An Adaptive Gradient Method with Energy and Momentum [0.0]
  We introduce a novel algorithm for gradient-based optimization of objective functions. The method is simple to implement, computationally efficient, and well suited for large-scale machine learning problems.
  arXiv  Detail & Related papers  (2022-03-23T04:48:38Z)
• Neural Network Training with Asymmetric Crosspoint Elements [1.0773924713784704]
  asymmetric conductance modulation of practical resistive devices critically degrades the classification of networks trained with conventional algorithms. Here, we describe and experimentally demonstrate an alternative fully-parallel training algorithm: Hamiltonian Descent. We provide critical intuition on why device asymmetry is fundamentally incompatible with conventional training algorithms and how the new approach exploits it as a useful feature instead.
  arXiv  Detail & Related papers  (2022-01-31T17:41:36Z)
• Optimization schemes for unitary tensor-network circuit [0.0]
  We discuss the variational optimization of a unitary tensor-network circuit with different network structures. The ansatz is performed based on a generalization of well-developed multi-scale entanglement renormalization algorithm. We present the benchmarking calculations for different network structures.
  arXiv  Detail & Related papers  (2020-09-05T21:57:28Z)
• MetaSDF: Meta-learning Signed Distance Functions [85.81290552559817]
  Generalizing across shapes with neural implicit representations amounts to learning priors over the respective function space. We formalize learning of a shape space as a meta-learning problem and leverage gradient-based meta-learning algorithms to solve this task.
  arXiv  Detail & Related papers  (2020-06-17T05:14:53Z)
• Training End-to-End Analog Neural Networks with Equilibrium Propagation [64.0476282000118]
  We introduce a principled method to train end-to-end analog neural networks by gradient descent. We show mathematically that a class of analog neural networks (called nonlinear resistive networks) are energy-based models. Our work can guide the development of a new generation of ultra-fast, compact and low-power neural networks supporting on-chip learning.
  arXiv  Detail & Related papers  (2020-06-02T23:38:35Z)
• Controllable Orthogonalization in Training DNNs [96.1365404059924]
  Orthogonality is widely used for training deep neural networks (DNNs) due to its ability to maintain all singular values of the Jacobian close to 1. This paper proposes a computationally efficient and numerically stable orthogonalization method using Newton's iteration (ONI) We show that our method improves the performance of image classification networks by effectively controlling the orthogonality to provide an optimal tradeoff between optimization benefits and representational capacity reduction. We also show that ONI stabilizes the training of generative adversarial networks (GANs) by maintaining the Lipschitz continuity of a network, similar to spectral normalization (
  arXiv  Detail & Related papers  (2020-04-02T10:14:27Z)
• Optimization of Graph Total Variation via Active-Set-based Combinatorial Reconditioning [48.42916680063503]
  We propose a novel adaptive preconditioning strategy for proximal algorithms on this problem class. We show that nested-forest decomposition of the inactive edges yields a guaranteed local linear convergence rate. Our results suggest that local convergence analysis can serve as a guideline for selecting variable metrics in proximal algorithms.
  arXiv  Detail & Related papers  (2020-02-27T16:33:09Z)

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.