What Does Goodness Measure? A Likelihood-Ratio Account of Forward-Forward Learning
Computer Science
Sponsored
AI Networking Cookbook: Practical recipes for AI-assisted network automation and development
AI Networking Cookbook: Practical recipes for AI-assisted network automation and development
Similar papers
Open access
Aug 2026
Restricted Boltzmann Machines, Bernoulli Mixtures and Sum-Product Networks: A Matched-Capacity Comparison on Binarized Image Data
Generative probabilistic models differ in a fundamental way that is rarely measured directly: some permit exact inference, while others are more expressive but require their likelihood to be estimated. This study compares three model families on binarized Fashion-MNIST and MNIST under identical preprocessing, identical...
Monther Ahmad, Syed Ejaz Ahmed
· Stats · 0 citations
Understanding and Exploiting Anisotropy in Post-Training
LLM post-training combines supervised fine-tuning (SFT), a mode-covering forward-KL objective, with reinforcement learning (RL), a mode-seeking reverse-KL objective. Frequency-weighted likelihood training leaves a well-known signature: \emph{anisotropy}, in which a few residual channels carry disproportionately large a...
Samyak Jha, Harshvardhan Saini, Yi-Zhen Liao et al.
· 0 citations
Whitening Inverts the Hierarchy: What the Norm of a Whitened Embedding Measures
Whitening a foundation-model embedding and using its squared norm as a training-free likelihood surrogate is motivated by the observation that whitened coordinates often appear approximately standard normal. We show that this observation follows from the projection central limit theorem and therefore does not imply a G...
Mohammed Ahnouch, Lotfi Elaachak
· 0 citations
Beyond Affine Transformations: A Soft Dominance Layer for Coordinate-Wise Neural Computation
This paper presents a preliminary study of an alternative to the affine transformation underlying conventional neural-network layers. In the proposed Soft Dominance Layer, each output unit compares input coordinates with a learnable reference vector and aggregates smooth inequality responses. A sigmoid relaxation makes...
Mariano Rivera
· 0 citations
Does a Shared Temperature Imply a Shared Angular Scale in Probabilistic Contrastive Learning?
In probabilistic contrastive learning, a shared temperature is commonly interpreted as a shared similarity scale, but this interpretation does not hold for high-dimensional distributional class representations. We study the exact von Mises-Fisher (vMF) probabilistic score used by ProCo when representation dimension and...
Ning-Kang Peng, Qian-Feng Yu, Jing Mao et al.
· 0 citations
Marginal Log-Likelihood Increments under Dirichlet-Smoothed Markov Estimation
For a Dirichlet-smoothed transition model, the effect of adding one workflow trace to the training archive is an exact change in reference-weighted log likelihood. We derive that change and show that it is a weighted reduction of Kullback--Leibler divergence between the reference conditionals and the model. From this f...
Levin David Schwab
· 0 citations