English
Related papers

Related papers: Simplicity Bias of Two-Layer Networks beyond Linea…

200 papers

Recent works have cast some light on the mystery of why deep nets fit any data and generalize despite being very overparametrized. This paper analyzes training and generalization for a simple 2-layer ReLU net with random initialization, and…

Machine Learning · Computer Science 2019-05-28 Sanjeev Arora , Simon S. Du , Wei Hu , Zhiyuan Li , Ruosong Wang

Training neural networks with first order optimisation methods is at the core of the empirical success of deep learning. The scale of initialisation is a crucial factor, as small initialisations are generally associated to a feature…

Machine Learning · Computer Science 2025-09-16 Etienne Boursier , Nicolas Flammarion

Can we modify the training data distribution to encourage the underlying optimization method toward finding solutions with superior generalization performance on in-distribution data? In this work, we approach this question for the first…

Machine Learning · Computer Science 2026-03-03 Dang Nguyen , Paymon Haddad , Eric Gan , Baharan Mirzasoleiman

People use rich prior knowledge about the world in order to efficiently learn new concepts. These priors - also known as "inductive biases" - pertain to the space of internal models considered by a learner, and they help the learner make…

Computation and Language · Computer Science 2018-06-20 Reuben Feinman , Brenden M. Lake

Neural networks often learn to make predictions that overly rely on spurious correlation existing in the dataset, which causes the model to be biased. While previous work tackles this issue by using explicit labeling on the spuriously…

Machine Learning · Computer Science 2020-11-24 Junhyun Nam , Hyuntak Cha , Sungsoo Ahn , Jaeho Lee , Jinwoo Shin

Dataset bias and spurious correlations can significantly impair generalization in deep neural networks. Many prior efforts have addressed this problem using either alternative loss functions or sampling strategies that focus on rare…

Machine Learning · Computer Science 2024-04-16 Robik Shrestha , Kushal Kafle , Christopher Kanan

The practice of deep learning has shown that neural networks generalize remarkably well even with an extreme number of learned parameters. This appears to contradict traditional statistical wisdom, in which a trade-off between model…

Machine Learning · Computer Science 2023-02-21 Yifei Wang , Yixuan Hua , Emmanuel Candés , Mert Pilanci

Many deep neural networks trained on natural images exhibit a curious phenomenon in common: on the first layer they learn features similar to Gabor filters and color blobs. Such first-layer features appear not to be specific to a particular…

Machine Learning · Computer Science 2014-12-09 Jason Yosinski , Jeff Clune , Yoshua Bengio , Hod Lipson

The distributional simplicity bias (DSB) posits that neural networks learn low-order moments of the data distribution first, before moving on to higher-order correlations. In this work, we present compelling new evidence for the DSB by…

Machine Learning · Computer Science 2024-10-10 Nora Belrose , Quintin Pope , Lucia Quirke , Alex Mallen , Xiaoli Fern

Which parts of a dataset will a given model find difficult? Recent work has shown that SGD-trained models have a bias towards simplicity, leading them to prioritize learning a majority class, or to rely upon harmful spurious correlations.…

Machine Learning · Computer Science 2023-06-09 Samuel J. Bell , Levent Sagun

Neural networks trained with gradient descent often learn solutions of increasing complexity over time, a phenomenon known as simplicity bias. Despite being widely observed across architectures, existing theoretical treatments lack a…

Machine Learning · Computer Science 2026-03-12 Yedi Zhang , Andrew Saxe , Peter E. Latham

In this work, we investigate a particular implicit bias in gradient descent training, which we term "Feature Averaging," and argue that it is one of the principal factors contributing to the non-robustness of deep neural networks. We show…

Machine Learning · Computer Science 2025-03-04 Binghui Li , Zhixuan Pan , Kaifeng Lyu , Jian Li

Deep Neural Networks (DNNs) generalize well despite their massive size and capability of memorizing all examples. There is a hypothesis that DNNs start learning from simple patterns and the hypothesis is based on the existence of examples…

Computer Vision and Pattern Recognition · Computer Science 2022-06-14 Ikki Kishida , Hideki Nakayama

Learning representations that generalize under distribution shifts is critical for building robust machine learning models. However, despite significant efforts in recent years, algorithmic advances in this direction have been limited. In…

Machine Learning · Computer Science 2025-02-14 Tianren Zhang , Chujie Zhao , Guanyu Chen , Yizhou Jiang , Feng Chen

Previous research has shown that fully-connected networks with small initialization and gradient-based training methods exhibit a phenomenon known as condensation during training. This phenomenon refers to the input weights of hidden…

Machine Learning · Computer Science 2023-05-18 Zhangchen Zhou , Hanxu Zhou , Yuqing Li , Zhi-Qin John Xu

Empirical studies suggest that machine learning models often rely on features, such as the background, that may be spuriously correlated with the label only during training time, resulting in poor accuracy during test-time. In this work, we…

Machine Learning · Computer Science 2024-09-10 Vaishnavh Nagarajan , Anders Andreassen , Behnam Neyshabur

In supervised learning, it is known that overparameterized neural networks with one hidden layer provably and efficiently learn and generalize, when trained using stochastic gradient descent with a sufficiently small learning rate and…

Machine Learning · Computer Science 2022-03-24 Kulin Shah , Amit Deshpande , Navin Goyal

Latent variable models for network data extract a summary of the relational structure underlying an observed network. The simplest possible models subdivide nodes of the network into clusters; the probability of a link between any two nodes…

Machine Learning · Computer Science 2012-07-03 Konstantina Palla , David Knowles , Zoubin Ghahramani

Existing generalization measures that aim to capture a model's simplicity based on parameter counts or norms fail to explain generalization in overparameterized deep neural networks. In this paper, we introduce a new, theoretically…

Machine Learning · Computer Science 2021-03-11 Lorenz Kuhn , Clare Lyle , Aidan N. Gomez , Jonas Rothfuss , Yarin Gal

It is widely observed that deep learning models with learned parameters generalize well, even with much more model parameters than the number of training samples. We systematically investigate the underlying reasons why deep neural networks…

Machine Learning · Computer Science 2017-11-29 Lei Wu , Zhanxing Zhu , Weinan E