Optimization Variance: Exploring Generalization Properties of DNNs

• URL: http://arxiv.org/abs/2106.01714v1
• Date: Thu, 3 Jun 2021 09:34:17 GMT
• Title: Optimization Variance: Exploring Generalization Properties of DNNs
• Authors: Xiao Zhang, Dongrui Wu, Haoyi Xiong, Bo Dai
• Abstract summary: The test error of a deep neural network (DNN) often demonstrates double descent. We propose a novel metric, optimization variance (OV), to measure the diversity of model updates.
• Score: 83.78477167211315
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Unlike the conventional wisdom in statistical learning theory, the test error of a deep neural network (DNN) often demonstrates double descent: as the model complexity increases, it first follows a classical U-shaped curve and then shows a second descent. Through bias-variance decomposition, recent studies revealed that the bell-shaped variance is the major cause of model-wise double descent (when the DNN is widened gradually). This paper investigates epoch-wise double descent, i.e., the test error of a DNN also shows double descent as the number of training epoches increases. By extending the bias-variance analysis to epoch-wise double descent of the zero-one loss, we surprisingly find that the variance itself, without the bias, varies consistently with the test error. Inspired by this result, we propose a novel metric, optimization variance (OV), to measure the diversity of model updates caused by the stochastic gradients of random training batches drawn in the same iteration. OV can be estimated using samples from the training set only but correlates well with the (unknown) \emph{test} error, and hence early stopping may be achieved without using a validation set.

Related papers

• A U-turn on Double Descent: Rethinking Parameter Counting in Statistical Learning [68.76846801719095]
  We show that double descent appears exactly when and where it occurs, and that its location is not inherently tied to the threshold p=n. This provides a resolution to tensions between double descent and statistical intuition.
  arXiv  Detail & Related papers  (2023-10-29T12:05:39Z)
• It's an Alignment, Not a Trade-off: Revisiting Bias and Variance in Deep Models [51.66015254740692]
  We show that for an ensemble of deep learning based classification models, bias and variance are emphaligned at a sample level. We study this phenomenon from two theoretical perspectives: calibration and neural collapse.
  arXiv  Detail & Related papers  (2023-10-13T17:06:34Z)
• Robust Modeling of Unknown Dynamical Systems via Ensemble Averaged Learning [2.523610673302386]
  Recent work has focused on data-driven learning of the evolution of unknown systems via deep neural networks (DNNs) This paper presents a computational technique which decreases the variance of the generalization error.
  arXiv  Detail & Related papers  (2022-03-07T15:17:53Z)
• Multi-scale Feature Learning Dynamics: Insights for Double Descent [71.91871020059857]
  We study the phenomenon of "double descent" of the generalization error. We find that double descent can be attributed to distinct features being learned at different scales.
  arXiv  Detail & Related papers  (2021-12-06T18:17:08Z)
• On the Double Descent of Random Features Models Trained with SGD [78.0918823643911]
  We study properties of random features (RF) regression in high dimensions optimized by gradient descent (SGD) We derive precise non-asymptotic error bounds of RF regression under both constant and adaptive step-size SGD setting. We observe the double descent phenomenon both theoretically and empirically.
  arXiv  Detail & Related papers  (2021-10-13T17:47:39Z)
• Towards an Understanding of Benign Overfitting in Neural Networks [104.2956323934544]
  Modern machine learning models often employ a huge number of parameters and are typically optimized to have zero training loss. We examine how these benign overfitting phenomena occur in a two-layer neural network setting. We show that it is possible for the two-layer ReLU network interpolator to achieve a near minimax-optimal learning rate.
  arXiv  Detail & Related papers  (2021-06-06T19:08:53Z)
• Memorizing without overfitting: Bias, variance, and interpolation in over-parameterized models [0.0]
  The bias-variance trade-off is a central concept in supervised learning. Modern Deep Learning methods flout this dogma, achieving state-of-the-art performance.
  arXiv  Detail & Related papers  (2020-10-26T22:31:04Z)
• Double Trouble in Double Descent : Bias and Variance(s) in the Lazy Regime [32.65347128465841]
  Deep neural networks can achieve remarkable performances while interpolating the training data perfectly. Rather than the U-curve of the bias-variance trade-off, their test error often follows a "double descent" We develop a quantitative theory for this phenomenon in the so-called lazy learning regime of neural networks.
  arXiv  Detail & Related papers  (2020-03-02T17:39:31Z)
• Rethinking Bias-Variance Trade-off for Generalization of Neural Networks [40.04927952870877]
  We provide a simple explanation for this by measuring the bias and variance of neural networks. We find that variance unimodality occurs robustly for all models we considered. Deeper models decrease bias and increase variance for both in-distribution and out-of-distribution data.
  arXiv  Detail & Related papers  (2020-02-26T07:21:54Z)

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.