paper-with-me

Papers

Representing Piecewise-Linear Functions by Functions with Minimal Arity

2024-06-04 · Christoph Koutschan, Anton Ponomarchuk, Josef Schicho

Any continuous piecewise-linear function $F\colon \mathbb{R}^{n}\to \mathbb{R}$ can be represented as a linear combination of $\max$ functions of at most $n+1$ affine-linear functions. In our previous paper [``Representing piecewise linear functions by functions with small arity'', AAECC, 2023], we showed that this upper bound of $n+1$ arguments is tight. In the present paper, we extend this result by establishing a correspondence between the function $F$ and the minimal number of arguments that are needed in any such decomposition. We show that the tessellation of the input space $\mathbb{R}^{n}$ induced by the function $F$ has a direct connection to the number of arguments in the $\max$ functions.

📄 PDF Abstract BibTeX arXiv:2406.02421

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Representing Piecewise Linear Functions by Functions with Small Arity

2023-05-26 · Christoph Koutschan, Bernhard Moser, Anton Ponomarchuk, Josef Schicho

A piecewise linear function can be described in different forms: as an arbitrarily nested expression of $\min$- and $\max$-functions, as a difference of two convex piecewise linear functions, or as a linear combination o…

On minimal representations of shallow ReLU networks

2021-08-12 · S. Dereich, S. Kassing

The realization function of a shallow ReLU network is a continuous and piecewise affine function $f:\mathbb R^d\to \mathbb R$, where the domain $\mathbb R^{d}$ is partitioned by a set of $n$ hyperplanes into cells on whi…

Decomposition Polyhedra of Piecewise Linear Functions

2024-10-07 · Marie-Charlotte Brandenburg, Moritz Grillo, Christoph Hertrich

In this paper we contribute to the frequently studied question of how to decompose a continuous piecewise linear (CPWL) function into a difference of two convex CPWL functions. Every CPWL function has infinitely many suc…

Expression of Fractals Through Neural Network Functions

2019-05-27 · Nadav Dym, Barak Sober, Ingrid Daubechies

To help understand the underlying mechanisms of neural networks (NNs), several groups have, in recent years, studied the number of linear regions $\ell$ of piecewise linear functions generated by deep neural networks (DN…

Formalizing Piecewise Affine Activation Functions of Neural Networks in Coq

2023-01-30 · Andrei Aleksandrov, Kim Völlinger

Verification of neural networks relies on activation functions being piecewise affine (pwa) -- enabling an encoding of the verification problem for theorem provers. In this paper, we present the first formalization of pw…