Blueshift

Recent developments in large-scale machine learning have created a tempting picture suggesting that by scaling up data, model size and training time properly, one can obtain a model that can be used successfully in few-shot settings in all downstream tasks. In this work, we investigate this premise empirically and provide a strong case against it. In particular, we consider image recognition...

Inspired by human learning, researchers have proposed ordering examples during training based on their difficulty. Both curriculum learning, exposing a network to easier examples early in training, and anti-curriculum learning, showing the most difficult examples first, have been suggested as improvements to the standard i.i.d. training. In this work, we set out to investigate the relative...

In today's heavily overparameterized models, the value of the training loss provides few guarantees on model generalization ability. Indeed, optimizing only the training loss value, as is commonly done, can easily lead to suboptimal model quality. Motivated by prior work connecting the geometry of the loss landscape and generalization, we introduce a novel, effective procedure for instead...

We show theoretically and experimentally that both data whitening and second order optimization erase information about the training dataset, and can prevent any generalization for high dimensional datasets. First we show that if the input layer of a model is a dense linear layer, then the datapoint-datapoint second moment matrix contains all information which can be used to make predictions....

We study the role of L2 regularization in deep learning, and uncover simple relations between the performance of the model, the L2 coefficient, the learning rate, and the number of training steps. These empirical relations hold when the network is overparameterized. They can be used to predict the optimal regularization parameter of a given model. In addition, based on these observations we...

One desired capability for machines is the ability to transfer their understanding of one domain to another domain where data is (usually) scarce. Despite ample adaptation of transfer learning in many deep learning applications, we yet do not understand what enables a successful transfer and which part of the network is responsible for that. In this paper, we provide new tools and analysis to...

Understanding the asymptotic behavior of wide networks is of considerable interest. In this work, we present a general method for analyzing this large width behavior. The method is an adaptation of Feynman diagrams, a standard tool for computing multivariate Gaussian integrals. We apply our method to study training dynamics, improving existing bounds and deriving new results on wide network...

We study the phenomenon that some modules of deep neural networks (DNNs) are more critical than others. Meaning that rewinding their parameter values back to initialization, while keeping other modules fixed at the trained parameters, results in a large drop in the network's performance. Our analysis reveals interesting properties of the loss landscape which leads us to propose a complexity...