paper-with-me

Papers

Most Activation Functions Can Win the Lottery Without Excessive Depth

2022-05-04 · Rebekka Burkholz

The strong lottery ticket hypothesis has highlighted the potential for training deep neural networks by pruning, which has inspired interesting practical and theoretical insights into how neural networks can represent functions. For networks with ReLU activation functions, it has been proven that a target network with depth $L$ can be approximated by the subnetwork of a randomly initialized neural network that has double the target's depth $2L$ and is wider by a logarithmic factor. We show that a depth $L+1$ network is sufficient. This result indicates that we can expect to find lottery tickets at realistic, commonly used depths while only requiring logarithmic overparametrization. Our novel construction approach applies to a large class of activation functions and is not limited to ReLUs.

📄 PDF Abstract BibTeX arXiv:2205.02321

Code (1)

relationalml/lt-existence 공식 구현 pytorch

Similar Papers 제목 키워드 기반

Convolutional and Residual Networks Provably Contain Lottery Tickets

2022-05-04 · Rebekka Burkholz

The Lottery Ticket Hypothesis continues to have a profound practical impact on the quest for small scale deep neural networks that solve modern deep learning tasks at competitive performance. These lottery tickets are id…

Can We Find Strong Lottery Tickets in Generative Models?

2022-12-16 · Sangyeop Yeo, Yoojin Jang, Jy-yong Sohn, Dongyoon Han 외

Yes. In this paper, we investigate strong lottery tickets in generative models, the subnetworks that achieve good generative performance without any weight update. Neural network pruning is considered the main cornerston…

Model CompressionNetwork Pruning

Lottery Tickets with Nonzero Biases

2021-10-21 · Jonas Fischer, Advait Gadhikar, Rebekka Burkholz

The strong lottery ticket hypothesis holds the promise that pruning randomly initialized deep neural networks could offer a computationally efficient alternative to deep learning with stochastic gradient descent. Common …

Trainable Activations for Image Classification

2023-01-26 · Preprints 2023 1 · Evgenii Pishchik

Non-linear activation functions are one of the main parts of deep neural network architectures. The choice of the activation function can affect model speed, performance and convergence. Most popular activation functions…

image-classificationImage Classification

Dissecting Lottery Ticket Transformers: Structural and Behavioral Study of Sparse Neural Machine Translation

2020-09-17 · EMNLP (BlackboxNLP) 2020 11 · Rajiv Movva, Jason Y. Zhao

Recent work on the lottery ticket hypothesis has produced highly sparse Transformers for NMT while maintaining BLEU. However, it is unclear how such pruning techniques affect a model's learned representations. By probing…

Machine TranslationNMTTranslation