View publication

We propose adaptive weight decay, which automatically tunes the hyper-parameter for weight decay during each training iteration. For classification problems, we propose changing the value of the weight decay hyper-parameter on the fly based on the strength of updates from the classification loss (i.e., gradient of cross-entropy), and the regularization loss (i.e., -norm of the weights). We show that this simple modification can result in large improvements in adversarial robustness — an area which suffers from robust overfitting — without requiring extra data across various datasets and architecture choices. For example, our reformulation results in 20% relative robustness improvement for CIFAR-100, and 10% relative robustness improvement on CIFAR-10 comparing to the best tuned hyper-parameters of traditional weight decay resulting in models that have comparable performance to SOTA robustness methods. In addition, this method has other desirable properties, such as less sensitivity to learning rate, and smaller weight norms, which the latter contributes to robustness to overfitting to label noise, and pruning.

Related readings and updates.

Multi-objective Hyper-parameter Optimization of Behavioral Song Embeddings

Song embeddings are a key component of most music recommendation engines. In this work, we study the hyper-parameter optimization of behavioral song embeddings based on Word2Vec on a selection of downstream tasks, namely next-song recommendation, false neighbor rejection, and artist and genre clustering. We present new optimization objectives and metrics to monitor the effects of hyper-parameter optimization. We show that single-objective…
See paper details

Improving Neural Network Subspaces

In spite of the success of deep learning, we know relatively little about the many possible solutions to which a trained network can converge. Networks generally converge to some local minima—a region in space where the loss function increases in every direction—of their loss function during training. Our research explores why local minima outperforms others when a trained network is evaluated on a held-out test set.

See highlight details