Robust Offline Reinforcement Learning with Linearly Structured f-Divergence Regularization
"正则化" 相关文章
AMStraMGRAM: Adaptive Multi-cutoff Strategy Modification for ANaGRAM
Feature Selection and Regularization in Multi-Class Classification: An Empirical Study of One-vs-Rest Logistic Regression with Gradient Descent Optimization and L1 Sparsity Constraints
A Function Centric Perspective On Flat and Sharp Minima
A Function Centric Perspective On Flat and Sharp Minima
Early Detection and Reduction of Memorisation for Domain Adaptation and Instruction Tuning
Low Rank Gradients and Where to Find Them
NeurIPS 2025 | 清华大学与华为等提出全新正则化方法，破解稀疏视图3DGS“协同适应”难题
Learning Distinguishable Representations in Deep Q-Networks for Linear Transfer
Dynamic Orthogonal Continual Fine-tuning for Mitigating Catastrophic Forgettings
Spectral Collapse Drives Loss of Plasticity in Deep Continual Learning
Promoting Shape Bias in CNNs: Frequency-Based and Contrastive Regularization for Corruption Robustness
大模型“记性差一点”反而更聪明！金鱼损失随机剔除token，让AI不再死记硬背
大模型“记性差一点”反而更聪明：金鱼损失随机剔除 token，让 AI 不再死记硬背
VISP: Volatility Informed Stochastic Projection for Adaptive Regularization
Crisp Attention: Regularizing Transformers via Structured Sparsity
D2PPO: Diffusion Policy Policy Optimization with Dispersive Loss
Teaching the Teacher: Improving Neural Network Distillability for Symbolic Regression via Jacobian Regularization
机器学习入门基础：机器学习实践
【机器学习】通透！L1和L2核心区别 ！！
