Paper

Automatically Differentiable Nonlinear Tensor Networks (ADNTNs) for Exponential Compression of Deep Neural Networks

Unreadunread

AI summary

arXiv:2606. 00130v1 Announce Type: new Abstract: We study Automatically Differentiable Nonlinear Tensor Networks (ADNTNs), a family of structured weight generators whose compact core tensors are trained end-to-end by reverse-mode automatic differentiation (AD).

Reading status

Priority

About this paper

Authors: Andrzej Cichocki, Michal Wietczak
Released: 2026-06-02 (1mo ago)
Topic: Related to current project
Relation to my work: Read next because Automatically Differentiable Nonlinear Tensor Networks (ADNTNs) for Exponential Compression of Deep Neural Networks overlaps with clean result "The marker is a representational handle, not a behavioural one — sharing it between a villain persona and the assistant transfers no misalignment (HIGH confidence)", experiment "Follow-up to #354: cascading chunk-binding — does A→B, B→C, C→D propagate the full chain on a recipient trained only to emit A?", experiment "Factor screen for marker implantation + leakage (2^5: system-prompt length, answer-format length, persona-presence, on-policy, marker-only-loss)". Matching terms: line, does, trained, factor. Source: arxiv cs.LG (Machine Learning).
arXiv: 2606.00130

Ask Claude about this paper

Posts a comment with @claude so the runner spins up a Claude Code session scoped to Automatically Differentiable Nonlinear Tensor Networks (ADNTNs) for Exponential Compression of Deep Neural Networks. Replies appear in the conversation below.

Comments

No comments yet.

Related records

No links yet.