Recommender systems play a significant role in information filtering and have been utilized in different scenarios, such as e-commerce and social media. With the prosperity of deep …
As their size increases, Large Languages Models (LLMs) are natural candidates for network pruning methods: approaches that drop a subset of network weights while striving to …
The growing energy and performance costs of deep learning have driven the community to reduce the size of neural networks by selectively pruning components. Similarly to their …
U Evci, T Gale, J Menick, PS Castro… - … on machine learning, 2020 - proceedings.mlr.press
Many applications require sparse neural networks due to space or inference time restrictions. There is a large body of work on training dense networks to yield sparse …
X Zhou, Y Lin, W Zhang… - … Conference on Machine …, 2022 - proceedings.mlr.press
Abstract Invariant Risk Minimization (IRM) is an emerging invariant feature extracting technique to help generalization with distributional shift. However, we find that there exists a …
Since hardware resources are limited, the objective of training deep learning models is typically to maximize accuracy subject to the time and memory constraints of training and …
Works on lottery ticket hypothesis (LTH) and single-shot network pruning (SNIP) have raised a lot of attention currently on post-training pruning (iterative magnitude pruning), and before …
S Liu, L Yin, DC Mocanu… - … on Machine Learning, 2021 - proceedings.mlr.press
In this paper, we introduce a new perspective on training deep neural networks capable of state-of-the-art performance without the need for the expensive over-parameterization by …
Recent discoveries on neural network pruning reveal that, with a carefully chosen layerwise sparsity, a simple magnitude-based pruning achieves state-of-the-art tradeoff between …