Reliable predictive uncertainty in Laplace approximations depends critically on the prior precision, yet selecting it requires a posterior sweep that is prohibitively expensive for neural networks with billions of parameters. Under the Maximal Update Parametrization ($\mu\mathrm{P}$), we derive a rescaling of the prior...
Richard Bergna, Fernando Ruiz Mazo, Nicolò Felicioni et al.· 0 citations
It is shown that this loop can sustain a lower-return policy even when representation fitting is globally optimal on data selected by the agent, which then uses the resulting returns to guide its next choices.
SupportCal is introduced, a label-free post-hoc method that retains agreement examples at unit weight and assigns disagreement examples continuous weights based on the own-base PLM's relative support and corroboration from pretrained references selected from a size-compatible candidate pool.
Linhan Luo, Le-Quan Lin, Dai Shi et al.· 0 citations
This paper attempts to develop a formal account of the jump in four steps and measures the second, and hopes it paves the path for formalizing and measuring the full jump in the future.
Dai Shi, Xiao-Yu Li, José Miguel Hernández-Lobato· 0 citations
This survey reviews the geometry, learning, and computation of superposed representations, explaining how feature statistics and decoder choice affect the conclusions and compares practical methods for recovering and analyzing features.
The results show that PerturbPFN offers a complementary trade-off to specialized baselines, achieving competitive perturbation prediction with low inference cost while exposing interpretable intermediate estimates of targets, strengths, and system structure.
Yu-Che Gao, José Miguel Hernández-Lobato, Siyuan Guo· arXiv.org· 2 citations
A formal account of the jump is developed in four steps and measured, proving that jump instances are well-posed and establish a family theorem that certifies instances of unbounded difficulty without enumeration and further formalize when a jump is correct and how successive jumps compound.
Dai Shi, Xiao-Yu Li, José Miguel Hernández-Lobato· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
