On Relaxing Determinism in Arithmetic Circuits

08/22/2017
by   Arthur Choi, et al.
0

The past decade has seen a significant interest in learning tractable probabilistic representations. Arithmetic circuits (ACs) were among the first proposed tractable representations, with some subsequent representations being instances of ACs with weaker or stronger properties. In this paper, we provide a formal basis under which variants on ACs can be compared, and where the precise roles and semantics of their various properties can be made more transparent. This allows us to place some recent developments on ACs in a clearer perspective and to also derive new results for ACs. This includes an exponential separation between ACs with and without determinism; completeness and incompleteness results; and tractability results (or lack thereof) when computing most probable explanations (MPEs).

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/07/2022

Tractable Boolean and Arithmetic Circuits

Tractable Boolean and arithmetic circuits have been studied extensively ...
research
02/15/2020

Symmetric Arithmetic Circuits

We introduce symmetric arithmetic circuits, i.e. arithmetic circuits wit...
research
03/01/2016

Convolutional Rectifier Networks as Generalized Tensor Decompositions

Convolutional rectifier networks, i.e. convolutional neural networks wit...
research
10/25/2021

A Compilation of Succinctness Results for Arithmetic Circuits

Arithmetic circuits (AC) are circuits over the real numbers with 0/1-val...
research
07/23/2021

Lower Bounds for Symmetric Circuits for the Determinant

Dawar and Wilsenach (ICALP 2020) introduce the model of symmetric arithm...
research
02/11/2021

A Compositional Atlas of Tractable Circuit Operations: From Simple Transformations to Complex Information-Theoretic Queries

Circuit representations are becoming the lingua franca to express and re...
research
11/27/2014

On the Expressive Efficiency of Sum Product Networks

Sum Product Networks (SPNs) are a recently developed class of deep gener...

Please sign up or login with your details

Forgot password? Click here to reset