GRAIN: Group Aggregation via Min-Norm Objective
Nghia Bui, Jiarui Yao, Lijing Wang
cs.LG, stat.ML
Submitted: 2026-06-22
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Regularized Learning for Domain Adaptation under Label Shifts
- We need to talk about random seeds
- Training Verifiers to Solve Math Word Problems
- Fine-Tuning Pretrained Language Models: Weight Initializations, Data Orders, and Early Stopping
- Sharpness-Aware Minimization for Efficiently Improving Generalization
- Revisiting Checkpoint Averaging for Neural Machine Translation
- Coverage-based Example Selection for In-Context Learning
- Does Prompt Formatting Have Any Impact on LLM Performance?
- Averaging Weights Leads to Wider Optima and Better Generalization
- Tilted Sharpness-Aware Minimization
- RoBERTa: A Robustly Optimized BERT Pretraining Approach
- Decoupled Weight Decay Regularization
- Torch.manual_seed(3407) is all you need: On the influence of random seeds in deep learning architectures for computer vision
- LLaMA: Open and Efficient Foundation Language Models
- Qwen2 Technical Report
- Qwen2.5 Technical Report
- Revisiting Few-sample BERT Fine-tuning
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks