HOLE: Homological Observation of Latent Embeddings for Neural Network Interpretability
cs.LG, cs.GR, cs.HC
Submitted: 2025-12-08
Updated: 2026-11-03
Code: https://github.com/FoxHound0x00/hole
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Intraclass clustering: an implicit learning ability that regularizes DNNs
- A Survey of Quantization Methods for Efficient Neural Network Inference
- Persistent Homology Captures the Generalization of Neural Networks Without A Validation Set
- Auto-Encoding Variational Bayes
- Intriguing properties of neural networks
- Integer Quantization for Deep Learning Inference: Principles and Empirical Evaluation
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis