Certification Frontiers for Gaussian LoRA: Independent Priors, Posterior Risk, and Prediction-Preserving Balancing
cs.LG
Submitted: 2026-09-26
Updated: 2026-09-26
Terminology
Sources
- Fisher-Geometric Sharpness and the Implicit Bias of SGD toward Flat Minima
- PAC--Bayes Bounds on Quotient Parameter Spaces: Geometry-induced Implicit-Bias Priors
- Tight Sample Complexity for Low-Rank Adaptation: Matching Bounds and Rank Selection
- Improving LoRA with Variational Learning
- BaLoRA: Bayesian Low-Rank Adaptation of Large Scale Models
- Some theoretical improvements on the tightness of PAC-Bayes risk certificates for neural networks
- PAC-Bayes Beyond Parameter Space: Behavioral Equivalence, Z-Information, and Exact Complexity Decomposition
- Sharp Generalization Bounds for Foundation Models with Asymmetric Randomized Low-Rank Adapters
- Tuning without Peeking: Provable Generalization Bounds and Robust LLM Post-Training
- Smoothness-Based Derandomization of PAC-Bayes Bounds
- FragileFlow: Spectral Control of Correct-but-Fragile Predictions for Foundation Model Robustness
- Bayesian-LoRA: Probabilistic Low-Rank Adaptation of Large Language Models
- RoBERTa: A Robustly Optimized BERT Pretraining Approach
- Minimal Ranks, Maximum Confidence: Parameter-efficient Uncertainty Quantification for LoRA
- A Note on the PAC Bayesian Theorem
- Gaussian Stochastic Weight Averaging for Bayesian Low-Rank Adaptation of Large Language Models
- How good is PAC-Bayes at explaining generalisation?
- Non-Vacuous Generalization Bounds: Can Rescaling Invariances Help?
- Convergent Stochastic Training of Multi-Headed Attention and Understanding LoRA
- Non-vacuous Generalization Bounds for Deep Neural Networks without any modification to the trained models
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: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks