Author of the publication

Same Pre-training Loss, Better Downstream: Implicit Bias Matters for Language Models.

, , , and . ICML, volume 202 of Proceedings of Machine Learning Research, page 22188-22214. PMLR, (2023)

Please choose a person to relate this publication to

To differ between persons with the same name, the academic degree and the title of an important publication will be displayed. You can also use the button next to the name to display some publications already assigned to the person.

 

Other publications of authors with the same name

Improved Sample Complexities for Deep Networks and Robust Classification via an All-Layer Margin, and . (2019)cite arxiv:1910.04284.Safe Reinforcement Learning by Imagining the Near Future, , and . (2022)cite arxiv:2202.07789Comment: Accepted at NeurIPS 2021.In-N-Out: Pre-Training and Self-Training using Auxiliary Information for Out-of-Distribution Robustness., , , , , and . CoRR, (2020)Self-training Avoids Using Spurious Features Under Domain Shift., , , and . NeurIPS, (2020)Fine-Grained Gap-Dependent Bounds for Tabular MDPs via Adaptive Multi-Step Bootstrap., , and . COLT, volume 134 of Proceedings of Machine Learning Research, page 4438-4472. PMLR, (2021)In-N-Out: Pre-Training and Self-Training using Auxiliary Information for Out-of-Distribution Robustness., , , , , and . ICLR, OpenReview.net, (2021)Optimal Regularization can Mitigate Double Descent., , , and . ICLR, OpenReview.net, (2021)Plan Better Amid Conservatism: Offline Multi-Agent Reinforcement Learning with Actor Rectification., , , and . ICML, volume 162 of Proceedings of Machine Learning Research, page 17221-17237. PMLR, (2022)Robust and On-the-Fly Dataset Denoising for Image Classification., , , and . ECCV (29), volume 12374 of Lecture Notes in Computer Science, page 556-572. Springer, (2020)Algorithmic Regularization in Over-parameterized Matrix Sensing and Neural Networks with Quadratic Activations., , and . COLT, volume 75 of Proceedings of Machine Learning Research, page 2-47. PMLR, (2018)