Neural network training under semidefinite constraints

• URL: http://arxiv.org/abs/2201.00632v1
• Date: Mon, 3 Jan 2022 13:10:49 GMT
• Title: Neural network training under semidefinite constraints
• Authors: Patricia Pauli, Niklas Funcke, Dennis Gramlich, Mohamed Amine Msalmi and Frank Allg\"ower
• Abstract summary: This paper is concerned with the training of neural networks (NNs) under semidefinite constraints. Semidefinite constraints can be used to verify interesting properties for NNs. In experiments, we demonstrate the superior efficiency of our training method over previous approaches.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper is concerned with the training of neural networks (NNs) under semidefinite constraints. This type of training problems has recently gained popularity since semidefinite constraints can be used to verify interesting properties for NNs that include, e.g., the estimation of an upper bound on the Lipschitz constant, which relates to the robustness of an NN, or the stability of dynamic systems with NN controllers. The utilized semidefinite constraints are based on sector constraints satisfied by the underlying activation functions. Unfortunately, one of the biggest bottlenecks of these new results is the required computational effort for incorporating the semidefinite constraints into the training of NNs which is limiting their scalability to large NNs. We address this challenge by developing interior point methods for NN training that we implement using barrier functions for semidefinite constraints. In order to efficiently compute the gradients of the barrier terms, we exploit the structure of the semidefinite constraints. In experiments, we demonstrate the superior efficiency of our training method over previous approaches, which allows us, e.g., to use semidefinite constraints in the training of Wasserstein generative adversarial networks, where the discriminator must satisfy a Lipschitz condition.

Related papers

• N-Adaptive Ritz Method: A Neural Network Enriched Partition of Unity for Boundary Value Problems [1.2200609701777907]
  This work introduces a novel neural network-enriched Partition of Unity (NN-PU) approach for solving boundary value problems via artificial neural networks. The NN enrichment is constructed by combining pre-trained feature-encoded NN blocks with an untrained NN block. The proposed method offers accurate solutions while notably reducing the computational cost compared to the conventional adaptive refinement in the mesh-based methods.
  arXiv  Detail & Related papers  (2024-01-16T18:11:14Z)
• Neural Fields with Hard Constraints of Arbitrary Differential Order [61.49418682745144]
  We develop a series of approaches for enforcing hard constraints on neural fields. The constraints can be specified as a linear operator applied to the neural field and its derivatives. Our approaches are demonstrated in a wide range of real-world applications.
  arXiv  Detail & Related papers  (2023-06-15T08:33:52Z)
• Benign Overfitting in Deep Neural Networks under Lazy Training [72.28294823115502]
  We show that when the data distribution is well-separated, DNNs can achieve Bayes-optimal test error for classification. Our results indicate that interpolating with smoother functions leads to better generalization.
  arXiv  Detail & Related papers  (2023-05-30T19:37:44Z)
• Globally Optimal Training of Neural Networks with Threshold Activation Functions [63.03759813952481]
  We study weight decay regularized training problems of deep neural networks with threshold activations. We derive a simplified convex optimization formulation when the dataset can be shattered at a certain layer of the network.
  arXiv  Detail & Related papers  (2023-03-06T18:59:13Z)
• DeepSaDe: Learning Neural Networks that Guarantee Domain Constraint Satisfaction [8.29487992932196]
  We present an approach to train neural networks which can enforce a wide variety of constraints and guarantee that the constraint is satisfied by all possible predictions. Our approach is flexible enough to enforce a wide variety of domain constraints and is able to guarantee them in neural networks.
  arXiv  Detail & Related papers  (2023-03-02T10:40:50Z)
• Constrained Empirical Risk Minimization: Theory and Practice [2.4934936799100034]
  We present a framework that allows the exact enforcement of constraints on parameterized sets of functions such as Deep Neural Networks (DNNs) We focus on constraints that are outside the scope of equivariant networks used in Geometric Deep Learning. As a major example of the framework, we restrict filters of a Convolutional Neural Network (CNN) to be wavelets, and apply these wavelet networks to the task of contour prediction in the medical domain.
  arXiv  Detail & Related papers  (2023-02-09T16:11:58Z)
• Lipschitz Continuity Retained Binary Neural Network [52.17734681659175]
  We introduce the Lipschitz continuity as the rigorous criteria to define the model robustness for BNN. We then propose to retain the Lipschitz continuity as a regularization term to improve the model robustness. Our experiments prove that our BNN-specific regularization method can effectively strengthen the robustness of BNN.
  arXiv  Detail & Related papers  (2022-07-13T22:55:04Z)
• Comparative Analysis of Interval Reachability for Robust Implicit and Feedforward Neural Networks [64.23331120621118]
  We use interval reachability analysis to obtain robustness guarantees for implicit neural networks (INNs) INNs are a class of implicit learning models that use implicit equations as layers. We show that our approach performs at least as well as, and generally better than, applying state-of-the-art interval bound propagation methods to INNs.
  arXiv  Detail & Related papers  (2022-04-01T03:31:27Z)
• Robustness Analysis of Neural Networks via Efficient Partitioning with Applications in Control Systems [45.35808135708894]
  Neural networks (NNs) are now routinely implemented on systems that must operate in uncertain environments. This paper unifies propagation and partition approaches to provide a family of robustness analysis algorithms. New partitioning techniques are aware of their current bound estimates and desired boundary shape.
  arXiv  Detail & Related papers  (2020-10-01T16:51:36Z)
• Training robust neural networks using Lipschitz bounds [0.0]
  neural networks (NNs) are hardly used in safety-critical applications. One measure of robustness to adversarial perturbations is the Lipschitz constant of the input-output map defined by an NN. We propose a framework to train multi-layer NNs while at the same time encouraging robustness by keeping their Lipschitz constant small.
  arXiv  Detail & Related papers  (2020-05-06T16:07:46Z)
• Robust Pruning at Initialization [61.30574156442608]
  A growing need for smaller, energy-efficient, neural networks to be able to use machine learning applications on devices with limited computational resources. For Deep NNs, such procedures remain unsatisfactory as the resulting pruned networks can be difficult to train and, for instance, they do not prevent one layer from being fully pruned.
  arXiv  Detail & Related papers  (2020-02-19T17:09:50Z)

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.