arXiv Machine Learning
When Parameter Gradient Flows Close in Representation Space
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
Jul 29
Quotient Dynamics, Effective Curvature, and Implicit Bias in Positive Quadratic Networks
arXiv:2607. 25624v1 Announce Type: new Abstract: Positive quadratic networks admit the low-rank representation f_U(x)=x^top UU^top x, where Uinmathbb{R}^{dtimes r} is identifiable only up to right orthogonal multiplication, representing a rank-r PSD matrix Q=UU^top.
arXiv Machine Learning
Aug 12
Iterative Erasure Count Is Not an Affine-Invariant Concept Dimension
arXiv:2608. 10566v1 Announce Type: cross Abstract: How many directions does a neural representation use to encode a concept?
Hugging Face Trending Papers
Aug 11
Iterative Erasure Count Is Not an Affine-Invariant Concept Dimension
How many directions does a neural representation use to encode a concept? A common answer repeatedly erases probe directions and reports the stopping count or cumulative removed rank.
arXiv Machine Learning
Oct 19
Is a Linear Probe Evidence of a Linear Representation?
arXiv:2610.22655v1 Announce Type: cross Abstract: The linear representation hypothesis holds that pretrained vision models encode generative factors as linearly decodable directions in feature space,...
arXiv Machine Learning
Jul 15
The Geometry of Memorization: Finite-Time Spectral Sensitivity as a Diagnostic for Flow Matching Models
arXiv:2607. 12616v1 Announce Type: new Abstract: Continuous-time generative frameworks construct probability paths between base and target domains by optimizing time-dependent velocity fields.
arXiv Machine Learning
Aug 10
Understanding Differentiable Embeddings Through Differential and Integral Geometry
arXiv:2608. 06809v1 Announce Type: new Abstract: How can an analyst decide whether a nonlinear dimensionality reduction embedding can be trusted?