cs.LG（2023-10-08）

📊 共 11 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

#	题目	一句话要点	标签	🔗
1	Deep Reinforcement Learning Based Cross-Layer Design in Terahertz Mesh Backhaul Networks	提出基于深度强化学习的跨层设计以解决太赫兹网回程网络问题	reinforcement learning deep reinforcement learning DRL
2	DRL-ORA: Distributional Reinforcement Learning with Online Risk Adaption	提出DRL-ORA框架以解决强化学习中的风险适应问题	reinforcement learning DRL
3	Understanding the Robustness of Multi-modal Contrastive Learning to Distribution Shift	提出多模态对比学习机制以提升对分布偏移的鲁棒性	contrastive learning multimodal
4	Global Convergence of Policy Gradient Methods in Reinforcement Learning, Games and Control	提出全局收敛的策略梯度方法以解决强化学习中的优化问题	reinforcement learning
5	GEAR: A GPU-Centric Experience Replay System for Large Reinforcement Learning Models	提出GEAR以解决大规模强化学习模型的经验回放问题	reinforcement learning	✅
6	FedFed: Feature Distillation against Data Heterogeneity in Federated Learning	提出FedFed以解决联邦学习中的数据异质性问题	distillation
7	FP3O: Enabling Proximal Policy Optimization in Multi-Agent Cooperation with Parameter-Sharing Versatility	提出FP3O以解决多智能体合作中的参数共享问题	reinforcement learning PPO

#	题目	一句话要点	标签	🔗
8	Towards Optimizing with Large Language Models	评估大型语言模型在优化任务中的能力	large language model
9	Federated Learning: A Cutting-Edge Survey of the Latest Advancements and Applications	综述联邦学习的最新进展与应用以应对隐私与通信成本问题	large language model
10	Outlier Weighed Layerwise Sparsity (OWL): A Missing Secret Sauce for Pruning LLMs to High Sparsity	提出OWL方法以解决LLMs高稀疏性修剪问题	large language model	✅
11	Revisiting Block-based Quantisation: What is Important for Sub-8-bit LLM Inference?	提出块状量化方法以解决LLM推理中的数值缩放问题	large language model