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

Last update: Jan 01, 2022

Related tags

Algorithms DistributedGridDescent

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

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.

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

Overview

Distributed Grid Descent

Usage

Examples and Tutorials

Strong and weak scaling analysis

Algorithm

Owner

Martin

Path finding algorithm visualizer with python

A Python program to easily solve the n-queens problem using min-conflicts algorithm

A lightweight, object-oriented finite state machine implementation in Python with many extensions

Classic algorithms including Fizz Buzz, Bubble Sort, the Fibonacci Sequence, a Sudoku solver, and more.

A genetic algorithm written in Python for educational purposes.

A fast python implementation of the SimHash algorithm.

An NUS timetable generator which uses a genetic algorithm to optimise timetables to suit the needs of NUS students.

Tic-tac-toe with minmax algorithm.

This application solves sudoku puzzles using a backtracking recursive algorithm

A collection of Python Scripts made for fun, while exploring Python 🐍

Implementation of Apriori Algorithm for Association Analysis

Algorithms and utilities for SAR sensors

Algorithms implemented in Python

Genetic algorithms are heuristic search algorithms inspired by the process that supports the evolution of life.

TikTok X-Gorgon & X-Khronos Generation Algorithm

Algorithms written in different programming languages

The DarkRift2 networking framework written in Python 3

A litle algorithm that i made for transform a picture in a spreadsheet.

Rover. Finding the shortest pass by Dijkstra’s shortest path algorithm

Exact algorithm for computing two-sided statistical tolerance intervals under a normal distribution assumption using Python.