Transformers Learn to Achieve Second-Order Convergence Rates for In-Context Linear Regression

Deqing Fu, Tian Qi Chen, Robin Jia, Vatsal Sharan. Transformers Learn to Achieve Second-Order Convergence Rates for In-Context Linear Regression. In Amir Globersons, Lester Mackey, Danielle Belgrave, Angela Fan, Ulrich Paquet, Jakub M. Tomczak, Cheng Zhang 0005, editors, Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, NeurIPS 2024, Vancouver, BC, Canada, December 10 - 15, 2024. 2024. [doi]

Authors

Deqing Fu

This author has not been identified. Look up 'Deqing Fu' in Google

Tian Qi Chen

This author has not been identified. Look up 'Tian Qi Chen' in Google

Robin Jia

This author has not been identified. Look up 'Robin Jia' in Google

Vatsal Sharan

This author has not been identified. Look up 'Vatsal Sharan' in Google