paper-with-me

Papers

From Tempered to Benign Overfitting in ReLU Neural Networks

2023-05-24 · NeurIPS 2023 11 · Guy Kornowski, Gilad Yehudai, Ohad Shamir

Overparameterized neural networks (NNs) are observed to generalize well even when trained to perfectly fit noisy data. This phenomenon motivated a large body of work on "benign overfitting", where interpolating predictors achieve near-optimal performance. Recently, it was conjectured and empirically observed that the behavior of NNs is often better described as "tempered overfitting", where the performance is non-optimal yet also non-trivial, and degrades as a function of the noise level. However, a theoretical justification of this claim for non-linear NNs has been lacking so far. In this work, we provide several results that aim at bridging these complementing views. We study a simple classification setting with 2-layer ReLU NNs, and prove that under various assumptions, the type of overfitting transitions from tempered in the extreme case of one-dimensional data, to benign in high dimensions. Thus, we show that the input dimension has a crucial role on the type of overfitting in this setting, which we also validate empirically for intermediate dimensions. Overall, our results shed light on the intricate connections between the dimension, sample size, architecture and training algorithm on the one hand, and the type of resulting overfitting on the other hand.

📄 PDF Abstract BibTeX arXiv:2305.15141

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Benign, Tempered, or Catastrophic: A Taxonomy of Overfitting

2022-07-14 · Neil Mallinar, James B. Simon, Amirhesam Abedsoltan, Parthe Pandit 외

The practical success of overparameterized neural networks has motivated the recent scientific study of interpolating methods, which perfectly fit their training data. Certain interpolating methods, including neural netw…

Learning Theory

Provable Tempered Overfitting of Minimal Nets and Typical Nets

2024-10-24 · Itamar Harel, William M. Hoza, Gal Vardi, Itay Evron 외

We study the overfitting behavior of fully connected deep Neural Networks (NNs) with binary weights fitted to perfectly classify a noisy training set. We consider interpolation using both the smallest NN (having the mini…

Noisy Interpolation Learning with Shallow Univariate ReLU Networks

2023-07-28 · Nirmit Joshi, Gal Vardi, Nathan Srebro

Understanding how overparameterized neural networks generalize despite perfect interpolation of noisy training data is a fundamental question. Mallinar et. al. 2022 noted that neural networks seem to often exhibit ``temp…

regression

Benign overfitting in leaky ReLU networks with moderate input dimension

2024-03-11 · Kedar Karhadkar, Erin George, Michael Murray, Guido Montúfar 외

The problem of benign overfitting asks whether it is possible for a model to perfectly fit noisy training data and still generalize well. We study benign overfitting in two-layer leaky ReLU networks trained with the hing…

AttributeBinary Classification

Benign Overfitting for Two-layer ReLU Convolutional Neural Networks

2023-03-07 · Yiwen Kou, Zixiang Chen, Yuanzhou Chen, Quanquan Gu

Modern deep learning models with great expressive power can be trained to overfit the training data but still generalize well. This phenomenon is referred to as \textit{benign overfitting}. Recently, a few studies have a…

Vocal Bursts Valence Prediction