Alert button
Picture for Zhao Song

Zhao Song

Alert button

A Fast Optimization View: Reformulating Single Layer Attention in LLM Based on Tensor and SVM Trick, and Solving It in Matrix Multiplication Time

Sep 14, 2023
Yeqi Gao, Zhao Song, Weixin Wang, Junze Yin

Figure 1 for A Fast Optimization View: Reformulating Single Layer Attention in LLM Based on Tensor and SVM Trick, and Solving It in Matrix Multiplication Time
Figure 2 for A Fast Optimization View: Reformulating Single Layer Attention in LLM Based on Tensor and SVM Trick, and Solving It in Matrix Multiplication Time
Figure 3 for A Fast Optimization View: Reformulating Single Layer Attention in LLM Based on Tensor and SVM Trick, and Solving It in Matrix Multiplication Time
Figure 4 for A Fast Optimization View: Reformulating Single Layer Attention in LLM Based on Tensor and SVM Trick, and Solving It in Matrix Multiplication Time
Viaarxiv icon

Online Adaptive Mahalanobis Distance Estimation

Sep 02, 2023
Lianke Qin, Aravind Reddy, Zhao Song

Viaarxiv icon

Solving Attention Kernel Regression Problem via Pre-conditioner

Aug 28, 2023
Zhao Song, Junze Yin, Lichen Zhang

Figure 1 for Solving Attention Kernel Regression Problem via Pre-conditioner
Figure 2 for Solving Attention Kernel Regression Problem via Pre-conditioner
Figure 3 for Solving Attention Kernel Regression Problem via Pre-conditioner
Figure 4 for Solving Attention Kernel Regression Problem via Pre-conditioner
Viaarxiv icon

How to Protect Copyright Data in Optimization of Large Language Models?

Aug 23, 2023
Timothy Chu, Zhao Song, Chiwun Yang

Figure 1 for How to Protect Copyright Data in Optimization of Large Language Models?
Figure 2 for How to Protect Copyright Data in Optimization of Large Language Models?
Viaarxiv icon

Clustered Linear Contextual Bandits with Knapsacks

Aug 21, 2023
Yichuan Deng, Michalis Mamakos, Zhao Song

Viaarxiv icon

GradientCoin: A Peer-to-Peer Decentralized Large Language Models

Aug 21, 2023
Yeqi Gao, Zhao Song, Junze Yin

Figure 1 for GradientCoin: A Peer-to-Peer Decentralized Large Language Models
Figure 2 for GradientCoin: A Peer-to-Peer Decentralized Large Language Models
Figure 3 for GradientCoin: A Peer-to-Peer Decentralized Large Language Models
Figure 4 for GradientCoin: A Peer-to-Peer Decentralized Large Language Models
Viaarxiv icon

Convergence of Two-Layer Regression with Nonlinear Units

Aug 16, 2023
Yichuan Deng, Zhao Song, Shenghao Xie

Viaarxiv icon

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models

Jul 19, 2023
Zhenyu Zhang, Ying Sheng, Tianyi Zhou, Tianlong Chen, Lianmin Zheng, Ruisi Cai, Zhao Song, Yuandong Tian, Christopher Ré, Clark Barrett, Zhangyang Wang, Beidi Chen

Figure 1 for H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models
Figure 2 for H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models
Figure 3 for H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models
Figure 4 for H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models
Viaarxiv icon

Zero-th Order Algorithm for Softmax Attention Optimization

Jul 17, 2023
Yichuan Deng, Zhihang Li, Sridhar Mahadevan, Zhao Song

Viaarxiv icon

Fast Quantum Algorithm for Attention Computation

Jul 16, 2023
Yeqi Gao, Zhao Song, Xin Yang, Ruizhe Zhang

Viaarxiv icon