ExplorerData ScienceMachine Learning
Research PaperResearchia:202605.06074

Exact ReLU realization of tensor-product refinement iterates

Tsogtgerel Gantumur

Abstract

We study scalar dyadic refinement operators on R^2 of the form (Vf)(x,y) = sum_{(j,k) in Z^2} c_{j,k} f(2x-j, 2y-k), where only finitely many mask coefficients c_{j,k} are nonzero. Under a fixed support-window hypothesis, we prove that for every compactly supported continuous piecewise linear seed g:R^2->R, the iterates V^n g admit exact ReLU realizations of fixed width and depth O(n). This gives a first genuinely two-dimensional extension of the exact realization theory for refinement cascade...

Submitted: May 6, 2026Subjects: Machine Learning; Data Science

Description / Details

We study scalar dyadic refinement operators on R^2 of the form (Vf)(x,y) = sum_{(j,k) in Z^2} c_{j,k} f(2x-j, 2y-k), where only finitely many mask coefficients c_{j,k} are nonzero. Under a fixed support-window hypothesis, we prove that for every compactly supported continuous piecewise linear seed g:R^2->R, the iterates V^n g admit exact ReLU realizations of fixed width and depth O(n). This gives a first genuinely two-dimensional extension of the exact realization theory for refinement cascades. Using the one-dimensional exact loop-controller framework, the proof transports the tensor-product residual dynamics exactly on the product of two polygonal loops and reduces the remaining seam ambiguity to a final readout and selector step. The matrix cascade is then handled by a fixed-depth recursive block, and general compactly supported continuous piecewise linear seeds are reduced to a finite decomposition together with exact clamped gluing on the support window. This identifies the tensor-product dyadic case as a natural first multivariate instance of the loop-controller method for refinement iterates.


Source: arXiv:2605.03917v1 - http://arxiv.org/abs/2605.03917v1 PDF: https://arxiv.org/pdf/2605.03917v1 Original Link: http://arxiv.org/abs/2605.03917v1

Please sign in to join the discussion.

No comments yet. Be the first to share your thoughts!

Access Paper
View Source PDF
Submission Info
Date:
May 6, 2026
Topic:
Data Science
Area:
Machine Learning
Comments:
0
Bookmark
Exact ReLU realization of tensor-product refinement iterates | Researchia