近期论文9
- Understanding Transformers for Time Series Forecasting: A Case Study on MOIRAI第 4 位,共 5 位作者ICLR 2026
- Benign Overfitting in Out-of-Distribution Generalization of Linear Models第 3 位,共 4 位作者ICLR 2025
- One-Layer Transformer Provably Learns One-Nearest Neighbor In Context第 7 位,共 8 位作者NeurIPS 2024 · 25 次引用
- On the Provable Advantage of Unsupervised Pretraining第 3 位,共 4 位作者ICLR 2024 · 23 次引用
- Maximum Likelihood Estimation is All You Need for Well-Specified Covariate Shift第 3 位,共 5 位作者ICLR 2024 · 16 次引用
- Global Convergence in Training Large-Scale Transformers第 8 位,共 8 位作者NeurIPS 2024 · 10 次引用
- Optimal Aggregation of Prediction Intervals under Unsupervised Domain Shift第 3 位,共 3 位作者NeurIPS 2024 · 6 次引用
- Curriculum Learning for Vision-and-Language Navigation第 3 位,共 4 位作者NeurIPS 2021 · 33 次引用
- Sample-Efficient Reinforcement Learning for Linearly-Parameterized MDPs with a Generative Model第 3 位,共 3 位作者NeurIPS 2021 · 26 次引用
