Representation Measurements Under Function-Preserving Reparameterizations
Hidden coordinates are not uniquely determined by a language model's input--output function, so representation-derived measurements should be invariant to function-preserving changes of basis. This study shows that column-permutation parallel analysis violates function-preserving reparameterization invariance because its reference distribution and selected component count can change while the model function and observed covariance spectrum remain fixed. More generally, a data-internal reference procedure cannot simultaneously preserve every coordinate marginal, remain orthogonally equivariant, and remove cross-coordinate covariance. Empirically, across five models, three retrieval domains, and 75 transformations, median component-count disagreement is 0.79 and median fixed-threshold decision disagreement is 0.26. A centering-only control isolates the reference-driven effect, with 1,141 of 1,200 component counts changing despite an unchanged observed spectrum, whereas independent parallel analysis seeds change none of the corresponding decisions. By contrast, orthogonally invariant comparator scores remain numerically stable with similar held-out discrimination. Together, these results show that parallel analysis-derived component counts and decisions can reflect hidden-coordinate choice rather than a well-defined property of the model.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Perception Learning: A Formal Separation of Sensory Representation Learning from Decision Learning
We introduce Perception Learning (PeL), a paradigm that optimizes an agent's sensory interface $f_φ:\mathcal{X}\to\mathcal{Z}$ using task-agnostic signals, decoupled from downstream decision learning $g_θ:\mathcal{Z}\to\…
Representation LearningThe Concrete Distribution: A Continuous Relaxation of Discrete Random Variables
The reparameterization trick enables optimizing large scale stochastic computation graphs via gradient descent. The essence of the trick is to refactor each stochastic node into a differentiable function of its parameter…
Density EstimationStructured PredictionLikelihood Training of Cascaded Diffusion Models via Hierarchical Volume-preserving Maps
Cascaded models are multi-scale generative models with a marked capacity for producing perceptually impressive samples at high resolutions. In this work, we show that they can also be excellent likelihood models, so long…
Density EstimationOut-of-Distribution DetectionOn the Geometric Structure of Layer Updates in Deep Language Models
We study the geometric structure of layer updates in deep language models. Rather than analyzing what information is encoded in intermediate representations, we ask how representations change from one layer to the next. …
Unnatural Algorithms in Machine Learning
Natural gradient descent has a remarkable property that in the small learning rate limit, it displays an invariance with respect to network reparameterizations, leading to robust training behavior even for highly covaria…