Behavioral Capacity Certificates for Quantized Language Models
cs.LG
Submitted: 2026-09-29
Updated: 2026-09-29
Code: https://github.com/eamaz/bcc
Sources
- Symmetries in PAC-Bayesian Learning
- Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks with Many More Parameters than Training Data
- GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers
- Breaking the 1.58-bit Barrier for Ternary LLMs
- Mixtral of Experts
- PAC-Bayes Compression Bounds So Tight That They Can Explain Generalization
- A Note on the PAC Bayesian Theorem
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