RESEARCH

THEORY

Triple descent and the two kinds of overfitting: Where and why do they appear?

December 15, 2020

Abstract

A recent line of research has highlighted the existence of a “double descent” phenomenon in deep learning, whereby increasing the number of training examples N causes the generalization error of neural networks to peak when N is of the same order as the number of parameters P. In earlier works, a similar phenomenon was shown to exist in simpler models such as linear regression, where the peak instead occurs when N is equal to the input dimension D. Since both peaks coincide with the interpolation threshold, they are often conflated in the litterature. In this paper, we show that despite their apparent similarity, these two scenarios are inherently different. In fact, both peaks can co-exist when neural networks are applied to noisy regression tasks. The relative size of the peaks is then governed by the degree of nonlinearity of the activation function. Building on recent developments in the analysis of random feature models, we provide a theoretical ground for this sample-wise triple descent. As shown previously, the nonlinear peak at N =P is a true divergence caused by the extreme sensitivity of the output function to both the noise corrupting the labels and the initialization of the random features (or the weights in neural networks). This peak survives in the absence of noise, but can be suppressed by regularization. In contrast, the linear peak at N =D is solely due to overfitting the noise in the labels, and forms earlier during training. We show that this peak is implicitly regularized by the nonlinearity, which is why it only becomes salient at high noise and is weakly affected by explicit regularization. Throughout the paper, we compare analytical results obtained in the random feature model with the outcomes of numerical experiments involving deep neural networks.

Download the Paper

AUTHORS

Written by

Stéphane d’Ascoli

Levent Sagun

Giulio Biroli

Research Topics

Theory

Related Publications

May 17, 2019

COMPUTER VISION

SPEECH & AUDIO

GLoMo: Unsupervised Learning of Transferable Relational Graphs | Facebook AI Research

Modern deep transfer learning approaches have mainly focused on learning generic feature vectors from one task that are transferable to other tasks, such as word embeddings in language and pretrained convolutional features in vision. However,…

Zhilin Yang, Jake (Junbo) Zhao, Bhuwan Dhingra, Kaiming He, William W. Cohen, Ruslan Salakhutdinov, Yann LeCun

May 17, 2019

May 06, 2019

COMPUTER VISION

NLP

No Training Required: Exploring Random Encoders for Sentence Classification | Facebook AI Research

We explore various methods for computing sentence representations from pre-trained word embeddings without any training, i.e., using nothing but random parameterizations. Our aim is to put sentence embeddings on more solid footing by 1) looking…

John Wieting, Douwe Kiela

May 06, 2019

May 06, 2019

NLP

COMPUTER VISION

Efficient Lifelong Learning with A-GEM | Facebook AI Research

In lifelong learning, the learner is presented with a sequence of tasks, incrementally building a data-driven prior which may be leveraged to speed up learning of a new task. In this work, we investigate the efficiency of current lifelong…

Arslan Chaudhry, Marc'Aurelio Ranzato, Marcus Rohrbach, Mohamed Elhoseiny

May 06, 2019

May 06, 2019

COMPUTER VISION

Learning Exploration Policies for Navigation | Facebook AI Research

Numerous past works have tackled the problem of task-driven navigation. But, how to effectively explore a new environment to enable a variety of down-stream tasks has received much less attention. In this work, we study how agents can…

Tao Chen, Saurabh Gupta, Abhinav Gupta

May 06, 2019

Help Us Pioneer The Future of AI

We share our open source frameworks, tools, libraries, and models for everything from research exploration to large-scale production deployment.