Is Weight Tying Still Beneficial for Decoder-Only LLMs in Private Settings Under DP-SGD?
cs.LG
Submitted: 2026-09-30
Updated: 2026-09-30
Sources
- GPT-4 Technical Report
- LLaMA: Open and Efficient Foundation Language Models
- Let Your Graph Do the Talking: Encoding Structured Data for LLMs
- Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agents
- Efficient Per-Example Gradient Computations
- Large Language Models Can Be Strong Differentially Private Learners
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