Traversing the solution space of neural networks with Hessian Null Space Continuation
cs.LG, q-bio.NC, stat.ML
Submitted: 2026-09-29
Updated: 2026-09-29
Terminology
Sources
- Git Re-Basin: Merging Models modulo Permutation Symmetries
- Concrete Problems in AI Safety
- The loss landscape of overparameterized neural networks
- The Role of Permutation Invariance in Linear Mode Connectivity of Neural Networks
- All Models are Wrong, but Many are Useful: Learning a Variable's Importance by Studying an Entire Class of Prediction Models Simultaneously
- Neural Thickets: Diverse Task Experts Are Dense Around Pretrained Weights
- Studying Large Language Model Generalization with Influence Functions
- Gradient Descent Happens in a Tiny Subspace
- AI Safety Gridworlds
- The Blessing of Dimensionality in LLM Fine-tuning: A Variance-Curvature Perspective
- Characterizing Optimizer-Dependent Training Dynamics Through Hessian Eigenvector Displacement and Localization
- Phase codes emerge in recurrent neural networks optimized for modular arithmetic
- Discovering alternative solutions beyond the simplicity bias in recurrent neural networks
- Evolution Strategies at Scale: LLM Fine-Tuning Beyond Reinforcement Learning
- Estimating Implicit Regularization in Deep Learning
- Eigenvalues of the Hessian in Deep Learning: Singularity and Beyond
- Empirical Analysis of the Hessian of Over-Parametrized Neural Networks
- Proximal Policy Optimization Algorithms
- Contravariance Theory: Strong Alignment for Minimal Solutions to Hard Tasks
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