Xiyu Zhai

According to our database, Xiyu Zhai authored at least 10 papers between 2018 and 2024.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2024

Transformers are Efficient Compilers, Provably.

Xiyu Zhai, Runlong Zhou, Liao Zhang, Simon Shaolei Du

CoRR, 2024

2020

SceneGen: Generative Contextual Scene Augmentation using Scene Graph Priors.

Mohammad Keshavarzi, Aakash Parikh, Xiyu Zhai, Melody Mao, Luisa Caldas, Allen Y. Yang

CoRR, 2020

On the Multiple Descent of Minimum-Norm Interpolants and Restricted Lower Isometry of Kernels.

Tengyuan Liang, Alexander Rakhlin, Xiyu Zhai

Proceedings of the Conference on Learning Theory, 2020

2019

On the Risk of Minimum-Norm Interpolants and Restricted Lower Isometry of Kernels.

Tengyuan Liang, Alexander Rakhlin, Xiyu Zhai

CoRR, 2019

Gradient Descent Finds Global Minima of Deep Neural Networks.

Simon S. Du, Jason D. Lee, Haochuan Li, Liwei Wang, Xiyu Zhai

Proceedings of the 36th International Conference on Machine Learning, 2019

Gradient Descent Provably Optimizes Over-parameterized Neural Networks.

Simon S. Du, Xiyu Zhai, Barnabás Póczos, Aarti Singh

Proceedings of the 7th International Conference on Learning Representations, 2019

Consistency of Interpolation with Laplace Kernels is a High-Dimensional Phenomenon.

Alexander Rakhlin, Xiyu Zhai

Proceedings of the Conference on Learning Theory, 2019

2018

How Many Samples are Needed to Learn a Convolutional Neural Network?

Simon S. Du, Yining Wang, Xiyu Zhai, Sivaraman Balakrishnan, Ruslan Salakhutdinov, Aarti Singh

CoRR, 2018

How Many Samples are Needed to Estimate a Convolutional Neural Network?

Simon S. Du, Yining Wang, Xiyu Zhai, Sivaraman Balakrishnan, Ruslan Salakhutdinov, Aarti Singh

Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

Generalization Bounds of SGLD for Non-convex Learning: Two Theoretical Viewpoints.

Wenlong Mou, Liwei Wang, Xiyu Zhai, Kai Zheng

Proceedings of the Conference On Learning Theory, 2018