In-context Learning for Mixture of Linear Regressions: Existence, Generalization and Training Dynamicsby Yanhao Jin, Krishnakumar…
Montessori-Instruct: Generate Influential Training Data Tailored for Student Learningby Xiaochuan Li, Zichun Yu, Chenyan XiongFirst…
Tensor Decomposition with Unaligned Observationsby Runshi Tang, Tamara Kolda, Anru R. ZhangFirst submitted to arxiv…
Gradual Domain Adaptation via Manifold-Constrained Distributionally Robust Optimizationby Amir Hossein Saberi, Amir Najafi, Ala Emrani,…
Reward-free World Models for Online Imitation Learningby Shangzhe Li, Zhiao Huang, Hao SuFirst submitted to…
A Common Pitfall of Margin-based Language Model Alignment: Gradient Entanglementby Hui Yuan, Yifan Zeng, Yue…
ORSO: Accelerating Reward Design via Online Reward Selection and Policy Optimizationby Chen Bo Calvin Zhang,…
AutoAL: Automated Active Learning with Differentiable Query Strategy Searchby Yifeng Wang, Xueying Zhan, Siyu HuangFirst…
Single-Timescale Multi-Sequence Stochastic Approximation Without Fixed Point Smoothness: Theories and Applicationsby Yue Huang, Zhaoxian Wu,…
Truncating Trajectories in Monte Carlo Policy Evaluation: an Adaptive Approachby Riccardo Poiani, Nicole Nobili, Alberto…