Predicting Training Time Without Training

by   Luca Zancato, et al.

We tackle the problem of predicting the number of optimization steps that a pre-trained deep network needs to converge to a given value of the loss function. To do so, we leverage the fact that the training dynamics of a deep network during fine-tuning are well approximated by those of a linearized model. This allows us to approximate the training loss and accuracy at any point during training by solving a low-dimensional Stochastic Differential Equation (SDE) in function space. Using this result, we are able to predict the time it takes for Stochastic Gradient Descent (SGD) to fine-tune a model to a given loss without having to perform any training. In our experiments, we are able to predict training time of a ResNet within a 20 variety of datasets and hyper-parameters, at a 30 to 45-fold reduction in cost compared to actual training. We also discuss how to further reduce the computational and memory cost of our method, and in particular we show that by exploiting the spectral properties of the gradients' matrix it is possible predict training time on a large dataset while processing only a subset of the samples.


page 1

page 2

page 3

page 4


Overparameterized Nonlinear Learning: Gradient Descent Takes the Shortest Path?

Many modern learning tasks involve fitting nonlinear models to data whic...

On uniform-in-time diffusion approximation for stochastic gradient descent

The diffusion approximation of stochastic gradient descent (SGD) in curr...

Exploring Low-Cost Transformer Model Compression for Large-Scale Commercial Reply Suggestions

Fine-tuning pre-trained language models improves the quality of commerci...

Overparameterization of deep ResNet: zero loss and mean-field analysis

Finding parameters in a deep neural network (NN) that fit training data ...

Extrapolation for Large-batch Training in Deep Learning

Deep learning networks are typically trained by Stochastic Gradient Desc...

Predicting Grokking Long Before it Happens: A look into the loss landscape of models which grok

This paper focuses on predicting the occurrence of grokking in neural ne...

Please sign up or login with your details

Forgot password? Click here to reset