From post

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

, , , и . ICML, том 202 из Proceedings of Machine Learning Research, стр. 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.

 

Другие публикации лиц с тем же именем

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