Publication

Student Specialization in Deep Rectified Networks With Finite Width and Input Dimension

International Conference on Machine Learning (ICML)


Abstract

We consider a deep ReLU / Leaky ReLU student network trained from the output of a fixed teacher network of the same depth, with Stochastic Gradient Descent (SGD). The student network is \emph{over-realized}: at each layer l, the number nl of student nodes is more than that (ml) of teacher. Under mild conditions on dataset and teacher network, we prove that when the gradient is small at every data sample, each teacher node is \emph{specialized} by at least one student node \emph{at the lowest layer}. For two-layer network, such specialization can be achieved by training on any dataset of \emph{polynomial} size O(K^{5/2}d^3ϵ^{−1}). until the gradient magnitude drops to O(ϵ/K^{3/2}d^{1/2}). Here d is the input dimension, K=m_1+n_1 is the total number of neurons in the lowest layer of teacher and student. Note that we require a specific form of data augmentation and the sample complexity includes the additional data generated from augmentation. To our best knowledge, we are the first to give polynomial sample complexity for student specialization of training two-layer (Leaky) ReLU networks with finite depth and width in teacher-student setting, and finite complexity for the lowest layer specialization in multi-layer case, without parametric assumption of the input (like Gaussian). Our theory suggests that teacher nodes with large fan-out weights get specialized first when the gradient is still large, while others are specialized with small gradient, which suggests inductive bias in training. This shapes the stage of training as empirically observed in multiple previous works. Experiments on synthetic and CIFAR10 verify our findings. The code is released in https://github.com/facebookresearch/luckmatters

Related Publications

All Publications

Federated Learning for User Privacy and Data Confidentiality Workshop At ICML - July 24, 2021

Federated Learning with Buffered Asynchronous Aggregation

John Nguyen, Kshitiz Malik, Hongyuan Zhan, Ashkan Yousefpour, Michael Rabbat, Mani Malek, Dzmitry Huba

UAI - July 28, 2021

A Nonmyopic Approach to Cost-Constrained Bayesian Optimization

Eric Hans Lee, David Eriksson, Valerio Perrone, Matthias Seeger

ACM MM - October 20, 2021

EVRNet: Efficient Video Restoration on Edge Devices

Sachin Mehta, Amit Kumar, Fitsum Reda, Varun Nasery, Vikram Mulukutla, Rakesh Ranjan, Vikas Chandra

ICCV - October 11, 2021

Egocentric Pose Estimation from Human Vision Span

Hao Jiang, Vamsi Krishna Ithapu

To help personalize content, tailor and measure ads, and provide a safer experience, we use cookies. By clicking or navigating the site, you agree to allow our collection of information on and off Facebook through cookies. Learn more, including about available controls: Cookies Policy