GIST: distributed training for large-scale graph convolutional networks von Wolfe, Cameron R., Yang, Jingkang, Liao, Fangshuo, Chowdhury, Arindam, Dun, Chen, Bayer, Artun, Segarra, Santiago, Kyrillidis, Anastasios

Volltext

Provable Accelerated Convergence of Nesterov's Momentum for Deep ReLU Neural Networks von Liao, Fangshuo, Kyrillidis, Anastasios

Volltext bestellen

On the Convergence of Shallow Neural Network Training with Randomly Masked Neurons von Liao, Fangshuo, Kyrillidis, Anastasios

Volltext bestellen

Strong Lottery Ticket Hypothesis with $\varepsilon$--perturbation von Xiong, Zheyang, Liao, Fangshuo, Kyrillidis, Anastasios

Volltext bestellen

Accelerated Convergence of Nesterov's Momentum for Deep Neural Networks under Partial Strong Convexity von Liao, Fangshuo, Kyrillidis, Anastasios

Volltext

On the Error-Propagation of Inexact Hotelling's Deflation for Principal Component Analysis von Liao, Fangshuo, Kim, Junhyung Lyle, Barnum, Cruz, Kyrillidis, Anastasios

Volltext bestellen

On the Convergence of Shallow Neural Network Training with Randomly Masked Neurons von Liao, Fangshuo, Kyrillidis, Anastasios

Volltext

LOFT: Finding Lottery Tickets through Filter-wise Training von Wang, Qihan, Dun, Chen, Liao, Fangshuo, Jermaine, Chris, Kyrillidis, Anastasios

Volltext bestellen

Scissorhands: Exploiting the Persistence of Importance Hypothesis for LLM KV Cache Compression at Test Time von Liu, Zichang, Desai, Aditya, Liao, Fangshuo, Wang, Weitao, Xie, Victor, Xu, Zhaozhuo, Kyrillidis, Anastasios, Shrivastava, Anshumali

Volltext bestellen

Strong Lottery Ticket Hypothesis with \(\varepsilon\)--perturbation von Xiong, Zheyang, Liao, Fangshuo, Kyrillidis, Anastasios

Volltext

How much pre-training is enough to discover a good subnetwork? von Wolfe, Cameron R, Liao, Fangshuo, Wang, Qihan, Kim, Junhyung Lyle, Kyrillidis, Anastasios

Volltext bestellen

LOFT: Finding Lottery Tickets through Filter-wise Training von Wang, Qihan, Chen, Dun, Liao, Fangshuo, Jermaine, Chris, Kyrillidis, Anastasios

Volltext

Scissorhands: Exploiting the Persistence of Importance Hypothesis for LLM KV Cache Compression at Test Time von Liu, Zichang, Desai, Aditya, Liao, Fangshuo, Wang, Weitao, Xie, Victor, Xu, Zhaozhuo, Kyrillidis, Anastasios, Shrivastava, Anshumali

Volltext

How much pre-training is enough to discover a good subnetwork? von Wolfe, Cameron R, Liao, Fangshuo, Wang, Qihan, Kim, Junhyung Lyle, Kyrillidis, Anastasios

Volltext

Rapid drawing method for regular building facade based on laser point cloud von LIU RUI, YANG FAN, PAN YITING, WU YILE, ZHANG FANGSHUO, LIAO MINGRUI

Volltext bestellen