1 citations · 1 across the 12 of their papers we have counts for
12 papers
When Data Is Scarce: Scaling Sparse Language Models with Repeated Training
Boqian Wu, Qiao Xiao, Patrik Okanovic +6
Scaling laws for dense LLMs under infinite data are well explored, but how sparsity interacts with limited data is not. In this work, we study sparse training in data-constrained r…
Memory-Efficient LLM Training with Dynamic Sparsity: From Stability to Practical Scaling
Qiao Xiao, Boqian Wu, Patrik Okanovic +6
Dynamic Sparse Training (DST) offers a promising paradigm for improving the training and inference efficiency of deep neural networks; however, we find that in large language model…
Batch Matrix-form Equations and Implementation of Multilayer Perceptrons
Wieger Wesselink, Bram Grooten, Huub van de Wetering +2
Multilayer perceptrons (MLPs) remain fundamental to modern deep learning, yet their algorithmic details are rarely presented in complete, explicit \emph{batch matrix-form}. Rather,…
Addressing the Collaboration Dilemma in Low-Data Federated Learning via Transient Sparsity
Qiao Xiao, Boqian Wu, Andrey Poddubnyy +4
Federated learning (FL) enables collaborative model training across decentralized clients while preserving data privacy, leveraging aggregated updates to build robust global models…
NeuroTrails: Training with Dynamic Sparse Heads as the Key to Effective Ensembling
Bram Grooten, Farid Hasanov, Chenxiang Zhang +9
Model ensembles have long been a cornerstone for improving generalization and robustness in deep learning. However, their effectiveness often comes at the cost of substantial compu…
Leave it to the Specialist: Repair Sparse LLMs with Sparse Fine-Tuning via Sparsity Evolution
Qiao Xiao, Alan Ansell, Boqian Wu +4
Sparse large language models (LLMs) offer an attractive direction toward efficient deployment, but adapting them to downstream tasks remains challenging. The central difficulty is…
Dynamic Sparse Training versus Dense Training: The Unexpected Winner in Image Corruption Robustness
Boqian Wu, Qiao Xiao, Shunxin Wang +5
It is generally perceived that Dynamic Sparse Training opens the door to a new era of scalability and efficiency for artificial neural networks at, perhaps, some costs in accuracy…
Are Sparse Neural Networks Better Hard Sample Learners?
Qiao Xiao, Boqian Wu, Lu Yin +4
While deep learning has demonstrated impressive progress, it remains a daunting challenge to learn from hard samples as these samples are usually noisy and intricate. These hard sa…
Nerva: a Truly Sparse Implementation of Neural Networks
Wieger Wesselink, Bram Grooten, Qiao Xiao +2
We introduce Nerva, a fast neural network library under development in C++. It supports sparsity by using the sparse matrix operations of Intel's Math Kernel Library (MKL), which e…
Dynamic Data Pruning for Automatic Speech Recognition
Qiao Xiao, Pingchuan Ma, Adriana Fernandez-Lopez +7
The recent success of Automatic Speech Recognition (ASR) is largely attributed to the ever-growing amount of training data. However, this trend has made model training prohibitivel…
MSRS: Training Multimodal Speech Recognition Models from Scratch with Sparse Mask Optimization
Adriana Fernandez-Lopez, Honglie Chen, Pingchuan Ma +5
Pre-trained models have been a foundational approach in speech recognition, albeit with associated additional costs. In this study, we propose a regularization technique that facil…
E2ENet: Dynamic Sparse Feature Fusion for Accurate and Efficient 3D Medical Image Segmentation
Boqian Wu, Qiao Xiao, Shiwei Liu +5
Deep neural networks have evolved as the leading approach in 3D medical image segmentation due to their outstanding performance. However, the ever-increasing model size and computa…