Pith. sign in

Simon, Maksis Knutins, Liu Ziyin, Daniel Geisz, Abraham J

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

citation-role summary

background 1

citation-polarity summary

fields

cs.LG 2

years

2026 2

verdicts

UNVERDICTED 2

roles

background 1

polarities

background 1

representative citing papers

A Theory of Saddle Escape in Deep Nonlinear Networks

cs.LG · 2026-05-02 · unverdicted · novelty 8.0 · 3 refs

Derives exact Frobenius norm imbalance identity for deep nonlinear networks, classifies activations into four classes, and obtains critical-depth escape time law τ★ = Θ(ε^{-(r-2)}) from reduction to scalar ODE on permutation-symmetric submanifold.

Unsupervised Causal Abstractions Discovery

cs.LG · 2026-06-17 · unverdicted · novelty 6.0

Low-rank graphs induce latents that form causal abstractions, with identifiability results and a practical objective enabling unsupervised learning of high-level SCMs from low-level measurements.

citing papers explorer

Showing 2 of 2 citing papers.

  • A Theory of Saddle Escape in Deep Nonlinear Networks cs.LG · 2026-05-02 · unverdicted · none · ref 38 · 3 links

    Derives exact Frobenius norm imbalance identity for deep nonlinear networks, classifies activations into four classes, and obtains critical-depth escape time law τ★ = Θ(ε^{-(r-2)}) from reduction to scalar ODE on permutation-symmetric submanifold.

  • Unsupervised Causal Abstractions Discovery cs.LG · 2026-06-17 · unverdicted · none · ref 66

    Low-rank graphs induce latents that form causal abstractions, with identifiability results and a practical objective enabling unsupervised learning of high-level SCMs from low-level measurements.