Amazon Technologies, Inc.

Rodolphe Jenatton

Giovanni Zappella

Valerio Perrone

Leo Parker Dirac

David Spike Palfrey

Jim Huang

Cedric Philippe Archambeau

Samuel Theodore Sandler

Yu Gan

Matthias Seeger

Miroslav Miladinovic

Fabian Lutz-Frank Wauthier

Cédric Philippe Archambeau

Marcel Ackermann

Iaroslav Shcherbatyi

Hyperparameters for tuning a machine learning system may be optimized using Bayesian optimization with constraints. The hyperparameter optimization may be performed for a received training set and received constraints. Respective probabilistic models for the machine learning system and constraint functions may be initialized, then hyperparameter optimization may include iteratively identifying respective values for hyperparameters using analysis of the respective models performed using an acquisition function implementing entropy search on the respective models, training the machine learning system using the identified values to determine measures of accuracy and constraint metrics, and updating the respective models using the determined measures.

Hyperparameter optimization with operational constraints

Techniques for tuning a machine learning algorithm using automatically determined optimal hyperparameters are described. An exemplary method includes receiving a request to determine a search space for at least one hyperparameter of a machine learning algorithm; determining, according to the request, optimal hyperparameter values from the search space for at least the one hyperparameter of the machine learning algorithm based on an evaluation of hyperparameters from the same machine learning algorithm on different datasets; and tuning the machine learning algorithm using the determined optimal hyperparameter values for the at least one hyperparameter of the machine learning algorithm to generate a machine learning model.

Automatic determination of hyperparameters

Systems, methods, and computer-readable media are disclosed for maximizing quantifiable user interaction via modification of adjustable parameters. In one embodiment, an example method may include determining a first output to maximize, where the first output is a function of a first adjustable parameter and a second adjustable parameter, determining first data comprising a first actual value of the first output when the first adjustable parameter is set to a first value and the second adjustable parameter is set to a second value, and determining a first predictive model that generates a first predicted value of the first output. Example methods may include determining, using the first predictive model, a third value for the first adjustable parameter and a fourth value for the second adjustable parameter to maximize the first predicted value, and sending the third value and the fourth value.

Maximizing quantifiable user interaction via modification of adjustable parameters

An optimizer for a software execution environment determines an objective function and permitted settings for various tunable parameters of the environment. To represent the execution environment, the optimizer generates a Bayesian optimization model employing Gaussian process priors. The optimizer implements a plurality of iterations of execution of the model, interleaved with observation collection intervals. During a given observation collection interval, tunable parameter settings suggested by the previous model execution iteration are used in the execution environment, and the observations collected during the interval are used as inputs for the next model execution iteration. When an optimization goal is attained, the tunable settings that led to achieving the goal are stored.

Tuning software execution environments using Bayesian models

A system is disclosed that identifies early adopter users by creating a directed graph of item access information for an item category and performing a page rank type process on the item access information. This directed graph may be created in a reverse temporal order. The early adopter users can be identified as the users with nodes in the directed graph that have a threshold number or rate of incoming links directly or indirectly pointing towards the nodes. Using the early adopter users as a sample, systems herein can determine whether to recommend an item based on the popularity of the item with respect to the early adopter users. Further, systems herein can determine an inventory level to maintain for an item based on the popularity of the item with respect to the early adopter users.

Automated graph-based identification of early adopter users

Growing community of inventors

Berlin, Germany

Rodolphe Jenatton