An accurate flatness measure to estimate the generalization performance of CNN models

• URL: http://arxiv.org/abs/2603.09016v1
• Date: Mon, 09 Mar 2026 23:17:49 GMT
• Title: An accurate flatness measure to estimate the generalization performance of CNN models
• Abstract summary: We develop a flatness measure that is both exact and architecturally faithful for a broad and practically relevant class of CNNs.<n>The results suggest that the proposed measure can serve as a tool to assess and compare the generalization of CNN models.
• Score: 2.867517731896504
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Flatness measures based on the spectrum or the trace of the Hessian of the loss are widely used as proxies for the generalization ability of deep networks. However, most existing definitions are either tailored to fully connected architectures, relying on stochastic estimators of the Hessian trace, or ignore the specific geometric structure of modern Convolutional Neural Networks (CNNs). In this work, we develop a flatness measure that is both exact and architecturally faithful for a broad and practically relevant class of CNNs. We first derive a closed-form expression for the trace of the Hessian of the cross-entropy loss with respect to convolutional kernels in networks that use global average pooling followed by a linear classifier. Building on this result, we then specialize the notion of relative flatness to convolutional layers and obtain a parameterization-aware flatness measure that properly accounts for the scaling symmetries and filter interactions induced by convolution and pooling. Finally, we empirically investigate the proposed measure on families of CNNs trained on standard image-classification benchmarks. The results obtained suggest that the proposed measure can serve as a robust tool to assess and compare the generalization performance of CNN models, and to guide the design of architecture and training choices in practice.

Related papers

• Convergence of Gradient Descent for General Neural Network Architectures Beyond the NTK Regime [24.053364183688874]
  Training dynamics is central to understanding neural networks.<n>We propose a convergence framework for analyzing gradient descent dynamics under a broad family of neural network architectures.
  arXiv  Detail & Related papers  (2026-06-22T14:00:26Z)
• VIKING: Deep variational inference with stochastic projections [48.946143517489496]
  Variational mean field approximations tend to struggle with contemporary overparametrized deep neural networks.<n>We propose a simple variational family that considers two independent linear subspaces of the parameter space.<n>This allows us to build a fully-correlated approximate posterior reflecting the overparametrization.
  arXiv  Detail & Related papers  (2025-10-27T15:38:35Z)
• AMBER: Adaptive Mesh Generation by Iterative Mesh Resolution Prediction [48.72179728638418]
  We propose Adaptive Meshing By Expert Reconstruction (AMBER), a supervised learning approach to mesh adaptation.<n>AMBER iteratively predicts the sizing field, and uses this prediction to produce a new intermediate mesh using an out-of-the-box mesh generator.<n>We evaluate AMBER on 2D and 3D geometries, datasets including classical physics problems, mechanical components, and real-world industrial designs with human expert meshes.
  arXiv  Detail & Related papers  (2025-05-29T17:10:44Z)
• Random Sparse Lifts: Construction, Analysis and Convergence of finite sparse networks [17.487761710665968]
  We present a framework to define a large class of neural networks for which, by construction, training by gradient flow provably reaches arbitrarily low loss when the number of parameters grows.
  arXiv  Detail & Related papers  (2025-01-10T12:52:00Z)
• Chasing Fairness in Graphs: A GNN Architecture Perspective [73.43111851492593]
  We propose textsfFair textsfMessage textsfPassing (FMP) designed within a unified optimization framework for graph neural networks (GNNs) In FMP, the aggregation is first adopted to utilize neighbors' information and then the bias mitigation step explicitly pushes demographic group node presentation centers together. Experiments on node classification tasks demonstrate that the proposed FMP outperforms several baselines in terms of fairness and accuracy on three real-world datasets.
  arXiv  Detail & Related papers  (2023-12-19T18:00:15Z)
• Interpretable A-posteriori Error Indication for Graph Neural Network Surrogate Models [0.0]
  This work introduces an interpretability enhancement procedure for graph neural networks (GNNs) The end result is an interpretable GNN model that isolates regions in physical space, corresponding to sub-graphs, that are intrinsically linked to the forecasting task. The interpretable GNNs can also be used to identify, during inference, graph nodes that correspond to a majority of the anticipated forecasting error.
  arXiv  Detail & Related papers  (2023-11-13T18:37:07Z)
• Post-mortem on a deep learning contest: a Simpson's paradox and the complementary roles of scale metrics versus shape metrics [61.49826776409194]
  We analyze a corpus of models made publicly-available for a contest to predict the generalization accuracy of neural network (NN) models. We identify what amounts to a Simpson's paradox: where "scale" metrics perform well overall but perform poorly on sub partitions of the data. We present two novel shape metrics, one data-independent, and the other data-dependent, which can predict trends in the test accuracy of a series of NNs.
  arXiv  Detail & Related papers  (2021-06-01T19:19:49Z)
• Reframing Neural Networks: Deep Structure in Overcomplete Representations [41.84502123663809]
  We introduce deep frame approximation, a unifying framework for representation learning with structured overcomplete frames. We quantify structural differences with the deep frame potential, a data-independent measure of coherence linked to representation uniqueness and stability. This connection to the established theory of overcomplete representations suggests promising new directions for principled deep network architecture design.
  arXiv  Detail & Related papers  (2021-03-10T01:15:14Z)
• Anomaly Detection on Attributed Networks via Contrastive Self-Supervised Learning [50.24174211654775]
  We present a novel contrastive self-supervised learning framework for anomaly detection on attributed networks. Our framework fully exploits the local information from network data by sampling a novel type of contrastive instance pair. A graph neural network-based contrastive learning model is proposed to learn informative embedding from high-dimensional attributes and local structure.
  arXiv  Detail & Related papers  (2021-02-27T03:17:20Z)
• Deep Manifold Prior [37.725563645899584]
  We present a prior for manifold structured data, such as surfaces of 3D shapes, where deep neural networks are adopted to reconstruct a target shape using gradient descent. We show that surfaces generated this way are smooth, with limiting behavior characterized by Gaussian processes, and we mathematically derive such properties for fully-connected as well as convolutional networks.
  arXiv  Detail & Related papers  (2020-04-08T20:47:56Z)
• An Optimization and Generalization Analysis for Max-Pooling Networks [34.58092926599547]
  Max-Pooling operations are a core component of deep learning architectures. We perform a theoretical analysis of a convolutional max-pooling architecture. We empirically validate that CNNs significantly outperform fully connected networks in our setting.
  arXiv  Detail & Related papers  (2020-02-22T22:26:26Z)
• Understanding Generalization in Deep Learning via Tensor Methods [53.808840694241]
  We advance the understanding of the relations between the network's architecture and its generalizability from the compression perspective. We propose a series of intuitive, data-dependent and easily-measurable properties that tightly characterize the compressibility and generalizability of neural networks.
  arXiv  Detail & Related papers  (2020-01-14T22:26:57Z)
• Understanding Graph Neural Networks with Generalized Geometric Scattering Transforms [67.88675386638043]
  The scattering transform is a multilayered wavelet-based deep learning architecture that acts as a model of convolutional neural networks. We introduce windowed and non-windowed geometric scattering transforms for graphs based upon a very general class of asymmetric wavelets. We show that these asymmetric graph scattering transforms have many of the same theoretical guarantees as their symmetric counterparts.
  arXiv  Detail & Related papers  (2019-11-14T17:23:06Z)

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.