Abstract: A serverless computing system is configured to provide access to a machine learning model by at least associating an endpoint, comprising code that accesses the machine learning model, with an extension that interfaces between a serverless compute architecture and the endpoint. A request to perform an inference is received by the system and processed by using the serverless compute architecture to execute a compute function. The compute function cases the extension to interface with the endpoint to cause the machine learning model to perform the inference.

Abstract: A serverless computing system is configured to provide access to a machine learning model by at least associating an endpoint, comprising code that accesses the machine learning model, with an extension that interfaces between a serverless compute architecture and the endpoint. A request to perform an inference is received by the system and processed by using the serverless compute architecture to execute a compute function. The compute function cases the extension to interface with the endpoint to cause the machine learning model to perform the inference.

Abstract: A system is configured to provide access to a machine learning model by using a hybrid configuration comprising a dedicate server on which an instance of a model server is installed, and a serverless compute architecture that interfaces with an instance of the model server using an extension. A first portion of requests directed to the model server are processed by the dedicated server, and a second portion of the requests is processed by the serverless compute architecture.

Abstract: Techniques for packaging and deploying algorithms utilizing containers for flexible machine learning are described. In some embodiments, users can create or utilize simple containers adhering to a specification of a machine learning service in a provider network, where the containers include code for how a machine learning model is to be trained and/or executed. The machine learning service can automatically train a model and/or host a model using the containers. The containers can use a wide variety of algorithms and use a variety of types of languages, libraries, data types, etc. Users can thus implement machine learning training and/or hosting with extremely minimal knowledge of how the overall training and/or hosting is actually performed.

Abstract: Techniques for intelligent compute resource selection and utilization for machine learning training jobs are described. At least a portion of a machine learning (ML) training job is executed a plurality of times using a plurality of different resource configurations, where each of the plurality of resource configurations includes at least a different type or amount of compute instances. A performance metric is measured for each of the plurality of the executions, and can be used along with a desired performance characteristic to generate a recommended resource configuration for the ML training job. The ML training job is executed using the recommended resource configuration.

Abstract: Methods, systems, and computer-readable media for automated problem detection for machine learning models are disclosed. A machine learning analysis system receives data associated with use of a machine learning model. The data was collected by a machine learning inference system and comprises input to the model or a plurality of inferences representing output of the machine learning model. The machine learning analysis system performs analysis of the data associated with the use of the machine learning model. The machine learning analysis system detects one or more problems associated with the use of the machine learning model based at least in part on the analysis. The machine learning analysis system initiates one or more remedial actions associated with the one or more problems associated with the use of the machine learning model.

Abstract: Methods, systems, and computer-readable media for automated problem detection for machine learning models are disclosed. A machine learning analysis system receives data associated with use of a machine learning model. The data was collected by a machine learning inference system and comprises input to the model or a plurality of inferences representing output of the machine learning model. The machine learning analysis system performs analysis of the data associated with the use of the machine learning model. The machine learning analysis system detects one or more problems associated with the use of the machine learning model based at least in part on the analysis. The machine learning analysis system initiates one or more remedial actions associated with the one or more problems associated with the use of the machine learning model.

Abstract: Techniques for packaging and deploying algorithms utilizing containers for flexible machine learning are described. In some embodiments, users can create or utilize simple containers adhering to a specification of a machine learning service in a provider network, where the containers include code for how a machine learning model is to be trained and/or executed. The machine learning service can automatically train a model and/or host a model using the containers. The containers can use a wide variety of algorithms and use a variety of types of languages, libraries, data types, etc. Users can thus implement machine learning training and/or hosting with extremely minimal knowledge of how the overall training and/or hosting is actually performed.

Abstract: Techniques for packaging and deploying algorithms utilizing containers for flexible machine learning are described. In some embodiments, users can create or utilize simple containers adhering to a specification of a machine learning service in a provider network, where the containers include code for how a machine learning model is to be trained and/or executed. The machine learning service can automatically train a model and/or host a model using the containers. The containers can use a wide variety of algorithms and use a variety of types of languages, libraries, data types, etc. Users can thus implement machine learning training and/or hosting with extremely minimal knowledge of how the overall training and/or hosting is actually performed.

Abstract: Respective correlation metrics between token groups of a particular text attribute of a data set and a prediction target attribute are computed. Based on the correlation metrics, a predictive token group list is created. For various observation records of the data set, values of a derived categorical attribute corresponding to the particular text attribute are determined based on matches between the particular text attribute value and the predictive token group list. A measure of the predictive utility of the particular text attribute is obtained using correlations between the categorical attribute and the prediction target attribute.

Abstract: A number of attributes of different attribute types, to be used to assign observation records of a data set to clusters, are identified. Attribute-type-specific distance metrics for the attributes, which can be combined to obtain a normalized aggregated distance of an observation record from a cluster representative, are selected. One or more iterations of a selected clustering methodology are implemented on the data set using resources of a machine learning service until targeted termination criteria are met. A given iteration includes assigning the observations to clusters of a current version of a clustering model based on the aggregated distances from the cluster representatives of the current version, and updating the cluster representatives to generate a new version of the clustering model.

Abstract: Techniques for packaging and deploying algorithms utilizing containers for flexible machine learning are described. In some embodiments, users can create or utilize simple containers adhering to a specification of a machine learning service in a provider network, where the containers include code for how a machine learning model is to be trained and/or executed. The machine learning service can automatically train a model and/or host a model using the containers. The containers can use a wide variety of algorithms and use a variety of types of languages, libraries, data types, etc. Users can thus implement machine learning training and/or hosting with extremely minimal knowledge of how the overall training and/or hosting is actually performed.

Abstract: An approximate data structure to represent clusters of observation records of a data set is identified. A hierarchical representation of a plurality of clusters, including the targeted number of clusters among which the observation records are to be distributed, is generated. Each node of the hierarchy comprises an instance of the approximate data structure. Until a set of termination criteria are met, iterations of a selected clustering methodology are run. In a given iteration, distances of observation records from the cluster representatives of a current version of the model are computed using the hierarchical representation, and a new version of the model with modified cluster representatives is generated.