Computational Complexity of Neural Networks
https://lunalux.io/introduction-to-neural-networks/computational-complexity-of-neural-networks/
#HackerNews #ComputationalComplexity #NeuralNetworks #AIResearch #MachineLearning #TechTrends
Computational Complexity of Neural Networks
https://lunalux.io/introduction-to-neural-networks/computational-complexity-of-neural-networks/
#HackerNews #ComputationalComplexity #NeuralNetworks #AIResearch #MachineLearning #TechTrends
This is an example of amortized complexity and Strassen's "asymptotic spectra" (nice monograph by Zuiddam & Wigderson: https://www.math.ias.edu/~avi/PUBLICATIONS/WigdersonZu_Final_Draft_Oct2023.pdf)
Strassen developed this to understand the #complexity of matrix multiplication and #tensors, but it turns out to also show up in a bunch of places:
- #Entropy
- #Quantum information
- Shannon capacity of graphs
- Communication complexity https://en.wikipedia.org/wiki/Communication_complexity#Information_Complexity
- Circuit complexity (Robere & Zuiddam https://eccc.weizmann.ac.il/report/2021/035)
#math #probability #ComputationalComplexity #TCS #InformationTheory
Real coin flips are ~49-51 not 50-50 https://www.scientificamerican.com/article/scientists-destroy-illusion-that-coin-toss-flips-are-50-50/
But you can guarantee equal probability with a simple trick! Flip 2x in a row starting with the same side up.
HT->call it H
TH->call it T
HH,TT->try again
(due to von Neumann https://en.wikipedia.org/wiki/Randomness_extractor#Von_Neumann_extractor)
This leads to randomness extractors: from a given random process, what's the biggest uniform distribution you can get efficiently?
Randomness extractors give another interpretation of #entropy:
avg # bits needed to *describe* the outcome
=
# uniformly random bits you can *extract* from the outcome
#math #probability #ComputationalComplexity #TCS #InformationTheory
The New Godel Prize Winner Tastes Great and Is Less Filling
https://blog.computationalcomplexity.org/2025/06/the-new-godel-prize-winner-tastes-great.html
#HackerNews #GodelPrize #ComputationalComplexity #TechNews #Innovation #Humor
Taught a bonus lecture for a course on Algorithms for NP-hard Problems today. Material won't be on the exam, so technically, this lecture was "just for fun".
Quite some pressure to make coming to class on Friday morning 8:45am worth it for a gang of 20-year-olds.
Students were a hoot. They were listening actively and participating. Great to meet them. Had a blast 🙂
Afterwards, some of them thanked me for the "really great lecture" 🥺
Ab-so-lute-ly exhausted now.
#AcademicChatter #AcademicLife #StudentLife #ComputationalComplexity #ComputerScience #Algorithms #AcademicMastodon #Teaching #HigherEducation #University #TUDelft
Dr. Alexandra Kolla will be presenting "Quantum Max Cuts and Local Hamiltonians" in the Codes & Expansions (CodEx) seminar tomorrow Mar 4, 2025 at 10am PST = 19:00 CET. Sign up on the website: https://www.math.colostate.edu/~king/codex/