carboniferous_umbraculum

[Linkpost] Re­marks on the Con­ver­gence in Distri­bu­tion of Ran­dom Neu­ral Net­works to Gaus­sian Pro­cesses in the In­finite Width Limit

Short Re­mark on the (sub­jec­tive) math­e­mat­i­cal ‘nat­u­ral­ness’ of the Nanda—Lie­berum ad­di­tion mod­ulo 113 algorithm

A Neu­ral Net­work un­der­go­ing Gra­di­ent-based Train­ing as a Com­plex System

Notes on the Math­e­mat­ics of LLM Architectures

On Devel­op­ing a Math­e­mat­i­cal The­ory of In­ter­pretabil­ity

Some Notes on the math­e­mat­ics of Toy Au­toen­cod­ing Problems

Be­havi­our Man­i­folds and the Hes­sian of the To­tal Loss—Notes and Criticism

A brief note on Sim­plic­ity Bias

Notes on Learn­ing the Prior

An ob­ser­va­tion about Hub­inger et al.’s frame­work for learned optimization