Mind the spikes: Benign overfitting of kernels and neural networks in fixed dimension

• URL: http://arxiv.org/abs/2305.14077v3
• Date: Wed, 06 Nov 2024 09:13:37 GMT
• Title: Mind the spikes: Benign overfitting of kernels and neural networks in fixed dimension
• Authors: Moritz Haas, David Holzmüller, Ulrike von Luxburg, Ingo Steinwart,
• Abstract summary: We show that the smoothness of the estimators, and not the dimension, is the key to benign overfitting. We translate our results to wide neural networks. Our experiments verify that such neural networks, while overfitting, can indeed generalize well even on low-dimensional data sets.
• Score: 17.96183484063563
• License:
• Abstract: The success of over-parameterized neural networks trained to near-zero training error has caused great interest in the phenomenon of benign overfitting, where estimators are statistically consistent even though they interpolate noisy training data. While benign overfitting in fixed dimension has been established for some learning methods, current literature suggests that for regression with typical kernel methods and wide neural networks, benign overfitting requires a high-dimensional setting where the dimension grows with the sample size. In this paper, we show that the smoothness of the estimators, and not the dimension, is the key: benign overfitting is possible if and only if the estimator's derivatives are large enough. We generalize existing inconsistency results to non-interpolating models and more kernels to show that benign overfitting with moderate derivatives is impossible in fixed dimension. Conversely, we show that rate-optimal benign overfitting is possible for regression with a sequence of spiky-smooth kernels with large derivatives. Using neural tangent kernels, we translate our results to wide neural networks. We prove that while infinite-width networks do not overfit benignly with the ReLU activation, this can be fixed by adding small high-frequency fluctuations to the activation function. Our experiments verify that such neural networks, while overfitting, can indeed generalize well even on low-dimensional data sets.

Related papers

• Scalable Bayesian Inference in the Era of Deep Learning: From Gaussian Processes to Deep Neural Networks [0.5827521884806072]
  Large neural networks trained on large datasets have become the dominant paradigm in machine learning. This thesis develops scalable methods to equip neural networks with model uncertainty.
  arXiv  Detail & Related papers  (2024-04-29T23:38:58Z)
• Nonparametric regression using over-parameterized shallow ReLU neural networks [10.339057554827392]
  We show that neural networks can achieve minimax optimal rates of convergence (up to logarithmic factors) for learning functions from certain smooth function classes. It is assumed that the regression function is from the H"older space with smoothness $alpha(d+3)/2$ or a variation space corresponding to shallow neural networks. As a byproduct, we derive a new size-independent bound for the local Rademacher complexity of shallow ReLU neural networks.
  arXiv  Detail & Related papers  (2023-06-14T07:42:37Z)
• 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)
• Promises and Pitfalls of the Linearized Laplace in Bayesian Optimization [73.80101701431103]
  The linearized-Laplace approximation (LLA) has been shown to be effective and efficient in constructing Bayesian neural networks. We study the usefulness of the LLA in Bayesian optimization and highlight its strong performance and flexibility.
  arXiv  Detail & Related papers  (2023-04-17T14:23:43Z)
• Benign Overfitting for Two-layer ReLU Convolutional Neural Networks [60.19739010031304]
  We establish algorithm-dependent risk bounds for learning two-layer ReLU convolutional neural networks with label-flipping noise. We show that, under mild conditions, the neural network trained by gradient descent can achieve near-zero training loss and Bayes optimal test risk.
  arXiv  Detail & Related papers  (2023-03-07T18:59:38Z)
• 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)
• Benign, Tempered, or Catastrophic: A Taxonomy of Overfitting [19.08269066145619]
  Some interpolating methods, including neural networks, can fit noisy training data without catastrophically bad test performance. We argue that real interpolating methods like neural networks do not fit benignly.
  arXiv  Detail & Related papers  (2022-07-14T00:23:01Z)
• Benign Overfitting in Two-layer Convolutional Neural Networks [90.75603889605043]
  We study the benign overfitting phenomenon in training a two-layer convolutional neural network (CNN) We show that when the signal-to-noise ratio satisfies a certain condition, a two-layer CNN trained by gradient descent can achieve arbitrarily small training and test loss. On the other hand, when this condition does not hold, overfitting becomes harmful and the obtained CNN can only achieve constant level test loss.
  arXiv  Detail & Related papers  (2022-02-14T07:45:51Z)
• Robust Implicit Networks via Non-Euclidean Contractions [63.91638306025768]
  Implicit neural networks show improved accuracy and significant reduction in memory consumption. They can suffer from ill-posedness and convergence instability. This paper provides a new framework to design well-posed and robust implicit neural networks.
  arXiv  Detail & Related papers  (2021-06-06T18:05:02Z)
• The Neural Tangent Kernel in High Dimensions: Triple Descent and a Multi-Scale Theory of Generalization [34.235007566913396]
  Modern deep learning models employ considerably more parameters than required to fit the training data. Whereas conventional statistical wisdom suggests such models should drastically overfit, in practice these models generalize remarkably well. An emerging paradigm for describing this unexpected behavior is in terms of a emphdouble descent curve. We provide a precise high-dimensional analysis of generalization with the Neural Tangent Kernel, which characterizes the behavior of wide neural networks with gradient descent.
  arXiv  Detail & Related papers  (2020-08-15T20:55:40Z)
• Nonconvex regularization for sparse neural networks [0.0]
  We show that a non regularization method is investigated in the context of shallow ReLU networks. We show that the network approximation guarantees existing bounds on the size for finite data are maintained.
  arXiv  Detail & Related papers  (2020-04-24T03:03:21Z)

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.