Computing the best-case energy complexity of satisfying assignments in monotone circuits

Silva, Janio Carlos Nascimento; Souza, Uéverton S.

doi:10.1016/j.tcs.2022.08.005

Search citation statements

Order By: Relevance

Paper Sections

Select...

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2024

Publication Types

Select...

Book1

Article1

Relationship

Self Cite0

Independent2

Authors

Journals

Cited by 2 publications

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Energy and Output Patterns in Boolean Circuits

Sarma,

Uchizawa

2024

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Energy and Output Patterns in Boolean Circuits

Sarma,

Uchizawa

2024

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Trade-Offs Between Energy and Depth of Neural Networks

Uchizawa,

Abe

2024

Neural Computation

View full text Add to dashboard Cite

We present an investigation on threshold circuits and other discretized neural networks in terms of the following four computational resources—size (the number of gates), depth (the number of layers), weight (weight resolution), and energy—where the energy is a complexity measure inspired by sparse coding and is defined as the maximum number of gates outputting nonzero values, taken over all the input assignments. As our main result, we prove that if a threshold circuit C of size s, depth d, energy e, and weight w computes a Boolean function f (i.e., a classification task) of n variables, it holds that log( rk (f))≤ed(logs+logw+logn) regardless of the algorithm employed by C to compute f, where rk (f) is a parameter solely determined by a scale of f and defined as the maximum rank of a communication matrix with regard to f taken over all the possible partitions of the n input variables. For example, given a Boolean function CD n(ξ) =⋁i=1n/2ξi∧ξn/2+i, we can prove that n/2≤ed( log s+logw+logn) holds for any circuit C computing CD n. While its left-hand side is linear in n, its right-hand side is bounded by the product of the logarithmic factors of s,w,n and the linear factors of d,e. If we view the logarithmic terms as having a negligible impact on the bound, our result implies a trade-off between depth and energy: n/2 needs to be smaller than the product of e and d. For other neural network models, such as discretized ReLU circuits and discretized sigmoid circuits, we also prove that a similar trade-off holds. Thus, our results indicate that increasing depth linearly enhances the capability of neural networks to acquire sparse representations when there are hardware constraints on the number of neurons and weight resolution.

show abstract

Computing the best-case energy complexity of satisfying assignments in monotone circuits

Cited by 2 publications

References 28 publications

Energy and Output Patterns in Boolean Circuits

Energy and Output Patterns in Boolean Circuits

Trade-Offs Between Energy and Depth of Neural Networks

Contact Info

Product

Resources

About