arXiv Machine Learning
Mode Connectivity Beyond Classifiers: Evidence from Generative and Contrastive Models
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Machine Learning
Jun 19
Linear Mode Connectivity under Data Shifts for Deep Ensembles of Image Classifiers
arXiv:2511. 04514v2 Announce Type: replace Abstract: The phenomenon of linear mode connectivity (LMC) links several aspects of deep learning, including training stability under noisy stochastic gradients, the smoothness and generalization of local minima (basins), the similarity and functional diversity of sampled models, and architectural effects on data processing.
arXiv Machine Learning
Jun 19
Compositionality Emerges in a Narrow Depth-Connectivity Regime: Architecture Constraints and Solution Manifolds
arXiv:2606. 19941v1 Announce Type: new Abstract: Compositionality is believed to be the foundation for generalization, enabling models to reuse meaningful primitives in novel combinations.
arXiv AI
Sep 1
From the Loss Landscape to Diverse Feature Learning in Neural Networks
arXiv:2608.28948v1 Announce Type: cross Abstract: Over the course of the last decade, neural networks have grown from an academic curiosity to moving the markets of nations. Despite this explosion in...
arXiv AI
Jul 28
Understanding Machine Unlearning Through the Lens of Mode Connectivity
arXiv:2607. 23970v1 Announce Type: cross Abstract: Machine Unlearning aims to remove undesired information from trained models without full retraining from scratch.
arXiv Machine Learning
Aug 4
Understanding Machine Unlearning Through the Lens of Mode Connectivity
arXiv:2504. 06407v2 Announce Type: replace Abstract: Machine Unlearning aims to remove undesired information from trained models without full retraining from scratch.
Hugging Face Trending Papers
Aug 3
Topological Simplification in Predictive Coding Networks
We study the topology of learned representations in predictive coding networks (PCNs), a neuro-inspired bidirectional architecture, using a quantitative layer-wise persistent homology analysis. We train well-performing PCNs on a synthetic classification dataset ($\geq 99.