https://github.com/augustunderground/baceball

Bayesian Methods with ACE

https://github.com/augustunderground/baceball

Science Score: 13.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
  • codemeta.json file
    Found codemeta.json file
  • .zenodo.json file
  • DOI references
  • Academic publication links
  • Academic email domains
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (6.5%) to scientific vocabulary

Keywords

analog-circuit bayesian-optimization hy optimization scikit-optimize visualization
Last synced: 5 months ago · JSON representation

Repository

Bayesian Methods with ACE

Basic Info
  • Host: GitHub
  • Owner: AugustUnderground
  • License: mit
  • Language: Hy
  • Default Branch: master
  • Homepage:
  • Size: 74 MB
Statistics
  • Stars: 0
  • Watchers: 2
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Topics
analog-circuit bayesian-optimization hy optimization scikit-optimize visualization
Created over 4 years ago · Last pushed over 4 years ago
Metadata Files
Readme License

README.md

bAC²Eball

Using Bayesian methods for hyper parameter optimization with AC²E takes about as long as nine innings.

Best Model NAND4

objective

| Description | Value | |-------------|-------------| | optimzer | gp_minimize | | estimator | GBRT | | generator | sobol | | acquisitor | PI | | wn0 | 0.000015 | | wn1 | 0.000029 | | wn2 | 0.000045 | | wn3 | 0.000072 | | wp | 0.000041 | | vs0 | 1.6602 | | vs1 | 1.652853 | | vs2 | 1.662488 | | vs3 | 1.659937 | | cost | 0.021502 |

See the reports on optimizing an inverter chain and a schmitt trigger for a detailed comparison of algorithms offered by scikit-optimize.

These plots were generated by running bace.hy.

Setup

The basic setup is as follows:

hy (optimizer :func design-objective :dimensions design-space :n-calls 128 :n-random-starts 32 :base-estimator estimator :initial-point-generator generator :acq-func acquisitor :xi 0.01 :kappa 1.96 :random-state 666 :n-jobs 42 :verbose True)

Where - optimizer ∈ [forest-minimize gbrt-minimize gp-minimize] - estimator ∈ ["GP" "RF" "ET" "GBRT"] - generator ∈ ["random" "sobol" "halton" "hammersly" "lhs" "grid"] - acquisitor ∈ ["LCB" "EI" "PI"]

Dependencies

WIP

  • [ ] Vary kappa and xi
  • [ ] Find way to benchmark ps variants
  • [ ] Try optimizing amplifiers

Design Objective NAND4

inverter chain

Optimize the widths [wn0, wn1, wn2, wn3, wp] such that the switching voltages vsi = vdd / 2 = 1.65V where i ∈ [0,1,2,3].

Design Space

hy (setv design-space [ (space.Real 0.4e-6 150e-6 :name "wn0" :prior "normal") (space.Real 0.4e-6 150e-6 :name "wn1" :prior "normal") (space.Real 0.4e-6 150e-6 :name "wn2" :prior "normal") (space.Real 0.4e-6 150e-6 :name "wn3" :prior "normal") (space.Real 0.4e-6 150e-6 :name "wp" :prior "normal") ])

Owner

  • Name: ynk
  • Login: AugustUnderground
  • Kind: user
  • Location: Innsmouth
  • Company: @electronics-and-drives

PhD Student at Reutlingen University

GitHub Events

Total
Last Year

Issues and Pull Requests

Last synced: 9 months ago

All Time
  • Total issues: 0
  • Total pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Total issue authors: 0
  • Total pull request authors: 0
  • Average comments per issue: 0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 0
  • Pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Issue authors: 0
  • Pull request authors: 0
  • Average comments per issue: 0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
Top Authors
Issue Authors
Pull Request Authors
Top Labels
Issue Labels
Pull Request Labels

Dependencies

requirements.txt pypi
  • hace *
  • joblib *
  • matplotlib *
  • numpy *
  • pandas *
  • skopt *
  • torch *