Distributed Grid Descent: an algorithm for hyperparameter tuning guided by Bayesian inference, designed to run on multiple processes and potentially many machines with no central point of control

Related tags

AlgorithmsDistributedGridDescent
Overview

Distributed Grid Descent

An implementation of Distributed Grid Descent: an algorithm for hyperparameter tuning guided by Bayesian inference, designed to run on multiple processes and potentially many machines with no central point of control as described in Appendix B of Working Memory Graphs [Loynd et al., 2019].

Note: This project is a work in progress. Please contact me if you like to contribute and help to develop a fully fledged python library out of it.

Usage

import numpy as np
from dgd import DistributedGridDescent

model = ... # model wrapper
data = {
    "train_data": ...
}

param_grid = {
    "learning_rate":[3e-3, 1e-3, 3e-4, 1e-4, 3e-5, 1e-5],
    "optimizer":["adam", "rmsprop"],
    "lr_annealing":[False, 0.95, 0.99],
    "batch_size":[32, 64, 128, 256, 1024],
    "num_linear_layers":[1, 2, 4, 8, 16],
    "num_neurons":[512, 256, 128, 64, 32, 16],
    "dropout":[0.0, 0.1, 0.3, 0.5],
    "l2":[0.0, 0.01, 0.1]
}

dgd = DistributedGridDescent(model, param_grid, metric=np.mean, n_jobs=-1)
dgd.run(data)

print(dgd.best_params_)
df = pd.DataFrame(dgd.results_).set_index("ID").sort_values(by=["metric"],ascending=False)

Examples and Tutorials

See sklearn_example.py, pytorch_example.py, rosenbrock_example.py and tensorflow_example.py in the examples folder for examples of basic usage of dgd.
See rosenbrock_server_example.py for an example of distributed usage.

Strong and weak scaling analysis

scaling_analysis

Algorithm

Input: Set of hyperparameters H, each having a discrete, ordered set of possible values.  
Input: Maximum number of training steps N per run.  
repeat  
    Download any new results.  
    if no results so far then
        Choose a random configuration C from the grid defined by H.
    else
        Identify the run set S with the highest metric.
        Initialize neighborhood B to contain only S.
        Expand B by adding all possible sets whose configurations differ from that of S by one step in exactly one hyperparameter setting.
        Calculate a ceiling M = Count(B) + 1.
        Weight each run set x in B M - Count(x).
        Sample a random run set S' from B according to run set weights.
        Choose configuration C from S'.
    end if
    Perform one training run of N steps using C.
    Calculate the runs Metric.
    Log the result on shared storage.
until terminated by user.

See Appendix B of Loynd et al., 2019 for details.

Owner
Martin
Machine Learning Engineer at heart MSc Student in Computational Science & Engineering :computer: :books: :wrench: @ ETH Zürich :switzerland:
Martin
GitHub Repository
zoofs is a Python library for performing feature selection using an variety of nature inspired wrapper algorithms. The algorithms range from swarm-intelligence to physics based to Evolutionary. It's easy to use ,flexible and powerful tool to reduce your feature size.

zoofs is a Python library for performing feature selection using a variety of nature-inspired wrapper algorithms. The algorithms range from swarm-intelligence to physics-based to Evolutionary. It's e

Jaswinder Singh 168 Dec 30, 2022
A python implementation of the Basic Photometric Stereo Algorithm

Photometric-Stereo A python implementation of the Basic Photometric Stereo Algorithm Result Usage run Photometric_Stereo.py Code Tree |data #原始数据，tga格

20 Dec 19, 2022
causal-learn: Causal Discovery for Python

causal-learn: Causal Discovery for Python Causal-learn is a python package for causal discovery that implements both classical and state-of-the-art ca

589 Dec 29, 2022
Python algorithm to determine the optimal elevation threshold of a GNSS receiver, by using a statistical test known as the Brown-Forsynthe test.

Levene and Brown-Forsynthe: Test for variances Application to Global Navigation Satellite Systems (GNSS) Python algorithm to determine the optimal ele

Nicolas Gachancipa 2 Aug 09, 2022
Implementation of Apriori Algorithm for Association Analysis

Implementation of Apriori Algorithm for Association Analysis

3 Nov 14, 2021
Better control of your asyncio tasks

quattro: task control for asyncio quattro is an Apache 2 licensed library, written in Python, for task control in asyncio applications. quattro is inf

Tin Tvrtković 37 Dec 28, 2022
The test data, code and detailed description of the AW t-SNE algorithm

AW-t-SNE The test data, code and result of the AW t-SNE algorithm Structure of the folder Datasets: This folder contains two datasets, the MNIST datas

1 Mar 09, 2022
Algorithms-in-Python - Programs related to DSA in Python for placement practice

Algorithms-in-Python Programs related to DSA in Python for placement practice CO

MAINAK CHAUDHURI 2 Feb 02, 2022
A simple library for implementing common design patterns.

PyPattyrn from pypattyrn.creational.singleton import Singleton class DummyClass(object, metaclass=Singleton): # DummyClass is now a Singleton!

1.7k Jan 01, 2023
sudoku solver using CSP forward-tracking algorithms.

Sudoku sudoku solver using CSP forward-tracking algorithms. Description Sudoku is a logic-based game that consists of 9 3x3 grids that create one larg

Cindy 0 Dec 27, 2021
Supplementary Data for Evolving Reinforcement Learning Algorithms

evolvingrl Supplementary Data for Evolving Reinforcement Learning Algorithms This dataset contains 1000 loss graphs from two experiments: 500 unique g

John Co-Reyes 42 Sep 21, 2022
My dynamic programming algorithms for exercise and fun

My Dynamic Programming Algorithms giraycoskun [email protected]

Giray Coskun 1 Nov 13, 2021
A tictactoe where you never win, implemented using minimax algorithm

Unbeatable_TicTacToe A tictactoe where you never win, implemented using minimax algorithm Requirements Make sure you have the pygame module along with

Jessica Jolly 3 Jul 28, 2022
Our implementation of Gillespie's Stochastic Simulation Algorithm (SSA)

SSA Our implementation of Gillespie's Stochastic Simulation Algorithm (SSA) Requirements python =3.7 numpy pandas matplotlib pyyaml Command line usag

Anoop Lab 1 Jan 27, 2022
FLIght SCheduling OPTimization - a simple optimization library for flight scheduling and related problems in the discrete domain

Fliscopt FLIght SCheduling OPTimization 🛫 or fliscopt is a simple optimization library for flight scheduling and related problems in the discrete dom

33 Dec 17, 2022
My own Unicode compression algorithm

Zee Code ZCode is a custom compression algorithm I originally developed for a competition held for the Spring 2019 Datastructures and Algorithms cours

Vahid Zehtab 2 Oct 20, 2021
Algorithms written in different programming languages

Data Structures and Algorithms Clean example implementations of data structures and algorithms written in different languages. List of implementations

Zoran Pandovski 1.3k Jan 03, 2023
FingerPy is a algorithm to measure, analyse and monitor heart-beat using only a video of the user's finger on a mobile cellphone camera.

FingerPy is a algorithm using python, scipy and fft to measure, analyse and monitor heart-beat using only a video of the user's finger on a m

Thiago S. Brasil 37 Oct 21, 2022
Implementation of an ordered dithering algorithm used in computer graphics

Ordered Dithering Project In this project, we use an ordered dithering method to turn an RGB image, first to a gray scale image and then, turn the gra

1 Oct 26, 2021
Algorithmic Trading with Python

Source code for Algorithmic Trading with Python (2020) by Chris Conlan

Chris Conlan 1.3k Jan 03, 2023