Reusing Historical Trajectories in Natural Policy Gradient via Importance Sampling: Convergence and Convergence Rateby Yifan…
Adaptive Learning Rate for Follow-the-Regularized-Leader: Competitive Analysis and Best-of-Both-Worldsby Shinji Ito, Taira Tsuchiya, Junya HondaFirst…
Snapshot Reinforcement Learning: Leveraging Prior Trajectories for Efficiencyby Yanxiao Zhao, Yangge Qian, Tianyi Wang, Jingyang…
Subhomogeneous Deep Equilibrium Modelsby Pietro Sittoni, Francesco TudiscoFirst submitted to arxiv on: 1 Mar 2024CategoriesMain:…
Misconduct in Post-Selections and Deep Learningby Juyang WengFirst submitted to arxiv on: 13 Feb 2024CategoriesMain:…
Mitigating Reversal Curse in Large Language Models via Semantic-aware Permutation Trainingby Qingyan Guo, Rui Wang,…
Empirical and Experimental Insights into Data Mining Techniques for Crime Prediction: A Comprehensive Surveyby Kamal…
PRECISE Framework: GPT-based Text For Improved Readability, Reliability, and Understandability of Radiology Reports For Patient-Centered…
An Empirical Study of Data Ability Boundary in LLMs’ Math Reasoningby Zui Chen, Yezeng Chen,…
Getting Serious about Humor: Crafting Humor Datasets with Unfunny Large Language Modelsby Zachary Horvitz, Jingru…