Search Results for author:
Found 6 papers, 1 papers with code
SparseOptimizer: Sparsify Language Models through Moreau-Yosida Regularization and Accelerate via Compiler Co-design
This paper introduces SparseOptimizer, a novel deep learning optimizer that exploits Moreau-Yosida regularization to naturally induce sparsity in large language models such as BERT, ALBERT and GPT.
Zero-Shot and Few-Shot Learning for Lung Cancer Multi-Label Classification using Vision Transformer
Histology is an essential tool for lung cancer diagnosis.
Sim2Real Docs: Domain Randomization for Documents in Natural Scenes using Ray-traced Rendering
In the past, computer vision systems for digitized documents could rely on systematically captured, high-quality scans.
Algorithm to Compilation Co-design: An Integrated View of Neural Network Sparsity
Integration of BSR operations enables the TVM runtime execution to leverage structured pattern sparsity induced by model regularization.
Reweighted Proximal Pruning for Large-Scale Language Representation
Is it possible to compress these large-scale language representation models?
PCONV: The Missing but Desirable Sparsity in DNN Weight Pruning for Real-time Execution on Mobile Devices
Model compression techniques on Deep Neural Network (DNN) have been widely acknowledged as an effective way to achieve acceleration on a variety of platforms, and DNN weight pruning is a straightforward and effective method.
