Patents by Inventor Tomas Karnagel
Tomas Karnagel has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 11782926Abstract: Embodiments utilize trained query performance machine learning (QP-ML) models to predict an optimal compute node cluster size for a given in-memory workload. The QP-ML models include models that predict query task runtimes at various compute node cardinalities, and models that predict network communication time between nodes of the cluster. Embodiments also utilize an analytical model to predict overlap between predicted task runtimes and predicted network communication times. Based on this data, an optimal cluster size is selected for the workload. Embodiments further utilize trained data capacity machine learning (DC-ML) models to predict a minimum number of compute nodes needed to run a workload. The DC-ML models include models that predict the size of the workload dataset in a target data encoding, models that predict the amount of memory needed to run the queries in the workload, and models that predict the memory needed to accommodate changes to the dataset.Type: GrantFiled: January 12, 2022Date of Patent: October 10, 2023Assignee: Oracle International CorporationInventors: Sam Idicula, Tomas Karnagel, Jian Wen, Seema Sundara, Nipun Agarwal, Mayur Bency
-
Patent number: 11620547Abstract: Techniques for estimating the number of distinct values in a data set using machine learning are provided. In one technique, a sample of a data set is retrieved where the sample is a strict subset of the data set. The sample is analyzed to identify feature values of multiple features of the sample. The feature values are inserted into a machine-learned model that computes a prediction regarding a number of distinct values in the data set. An estimated number of distinct values that is based on the prediction is stored in association with the data set.Type: GrantFiled: May 19, 2020Date of Patent: April 4, 2023Assignee: Oracle International CorporationInventors: Tomas Karnagel, Onur Kocberber, Farhan Tauheed, Nipun Agarwal
-
Patent number: 11615265Abstract: The present invention relates to dimensionality reduction for machine learning (ML) models. Herein are techniques that individually rank features and combine features based on their rank to achieve an optimal combination of features that may accelerate training and/or inferencing, prevent overfitting, and/or provide insights into somewhat mysterious datasets. In an embodiment, a computer ranks features of datasets of a training corpus. For each dataset and for each landmark percentage, a target ML model is configured to receive only a highest ranking landmark percentage of features, and a landmark accuracy achieved by training the ML model with the dataset is measured. Based on the landmark accuracies and meta-features values of the dataset, a respective training tuple is generated for each dataset. Based on all of the training tuples, a regressor is trained to predict an optimal amount of features for training the target ML model.Type: GrantFiled: August 21, 2019Date of Patent: March 28, 2023Assignee: Oracle International CorporationInventors: Tomas Karnagel, Sam Idicula, Hesam Fathi Moghadam, Nipun Agarwal
-
Patent number: 11567937Abstract: Embodiments implement a prediction-driven, rather than a trial-driven, approach to automate database configuration parameter tuning for a database workload. This approach uses machine learning (ML) models to test performance metrics resulting from application of particular database parameters to a database workload, and does not require live trials on the DBMS managing the workload. Specifically, automatic configuration (AC) ML models are trained, using a training corpus that includes information from workloads being run by DBMSs, to predict performance metrics based on workload features and configuration parameter values. The trained AC-ML models predict performance metrics resulting from applying particular configuration parameter values to a given database workload being automatically tuned. Based on correlating changes to configuration parameter values with changes in predicted performance metrics, an optimization algorithm is used to converge to an optimal set of configuration parameters.Type: GrantFiled: May 12, 2021Date of Patent: January 31, 2023Assignee: Oracle International CorporationInventors: Sam Idicula, Tomas Karnagel, Jian Wen, Seema Sundara, Nipun Agarwal, Mayur Bency
-
Patent number: 11544630Abstract: The present invention relates to dimensionality reduction for machine learning (ML) models. Herein are techniques that individually rank features and combine features based on their rank to achieve an optimal combination of features that may accelerate training and/or inferencing, prevent overfitting, and/or provide insights into somewhat mysterious datasets. In an embodiment, a computer calculates, for each feature of a training dataset, a relevance score based on: a relevance scoring function, and statistics of values, of the feature, that occur in the training dataset. A rank based on relevance scores of the features is calculated for each feature. A sequence of distinct subsets of the features, based on the ranks of the features, is generated. For each distinct subset of the sequence of distinct feature subsets, a fitness score is generated based on training a machine learning (ML) model that is configured for the distinct subset.Type: GrantFiled: May 20, 2019Date of Patent: January 3, 2023Assignee: Oracle International CorporationInventors: Tomas Karnagel, Sam Idicula, Nipun Agarwal
-
Patent number: 11520834Abstract: Techniques are described for generating an approximate frequency histogram using a series of Bloom filters (BF). For example, to estimate the f1 and f2 cardinalities in a dataset, an ordered chain of three BFs is established (“BF1”, “BF2”, and “BF3”). An insertion operation is performed for each datum in the dataset, whereby the BFs are tested in order (starting at BF1) for the datum. If the datum is represented in a currently-tested BF, the subsequent BF in the chain is tested for the datum. If the datum is not represented in the currently-tested BF, the datum is added to the BF, a counter for the BF is incremented, and the insertion operation for the current datum ends. To estimate the cardinality of f1-values in the dataset, the BF2-counter is subtracted from the BF1-counter. Similarly, to estimate the cardinality of f2-values in the dataset, the BF3-counter is subtracted from the BF2-counter.Type: GrantFiled: July 28, 2021Date of Patent: December 6, 2022Assignee: Oracle International CorporationInventors: Tomas Karnagel, Suratna Budalakoti, Onur Kocberber, Nipun Agarwal, Alan Wood
-
Publication number: 20220138199Abstract: Embodiments utilize trained query performance machine learning (QP-ML) models to predict an optimal compute node cluster size for a given in-memory workload. The QP-ML models include models that predict query task runtimes at various compute node cardinalities, and models that predict network communication time between nodes of the cluster. Embodiments also utilize an analytical model to predict overlap between predicted task runtimes and predicted network communication times. Based on this data, an optimal cluster size is selected for the workload. Embodiments further utilize trained data capacity machine learning (DC-ML) models to predict a minimum number of compute nodes needed to run a workload. The DC-ML models include models that predict the size of the workload dataset in a target data encoding, models that predict the amount of memory needed to run the queries in the workload, and models that predict the memory needed to accommodate changes to the dataset.Type: ApplicationFiled: January 12, 2022Publication date: May 5, 2022Inventors: Sam Idicula, Tomas Karnagel, Jian Wen, Seema Sundara, Nipun Agarwal, Mayur Bency
-
Patent number: 11256698Abstract: Embodiments utilize trained query performance machine learning (QP-ML) models to predict an optimal compute node cluster size for a given in-memory workload. The QP-ML models include models that predict query task runtimes at various compute node cardinalities, and models that predict network communication time between nodes of the cluster. Embodiments also utilize an analytical model to predict overlap between predicted task runtimes and predicted network communication times. Based on this data, an optimal cluster size is selected for the workload. Embodiments further utilize trained data capacity machine learning (DC-ML) models to predict a minimum number of compute nodes needed to run a workload. The DC-ML models include models that predict the size of the workload dataset in a target data encoding, models that predict the amount of memory needed to run the queries in the workload, and models that predict the memory needed to accommodate changes to the dataset.Type: GrantFiled: April 11, 2019Date of Patent: February 22, 2022Assignee: Oracle International CorporationInventors: Sam Idicula, Tomas Karnagel, Jian Wen, Seema Sundara, Nipun Agarwal, Mayur Bency
-
Publication number: 20210406717Abstract: Herein are approaches for self-optimization of a database management system (DBMS) such as in real time. Adaptive just-in-time sampling techniques herein estimate database content statistics that a machine learning (ML) model may use to predict configuration settings that conserve computer resources such as execution time and storage space. In an embodiment, a computer repeatedly samples database content until a dynamic convergence criterion is satisfied. In each iteration of a series of sampling iterations, a subset of rows of a database table are sampled, and estimates of content statistics of the database table are adjusted based on the sampled subset of rows. Immediately or eventually after detecting dynamic convergence, a machine learning (ML) model predicts, based on the content statistic estimates, an optimal value for a configuration setting of the DBMS.Type: ApplicationFiled: June 29, 2020Publication date: December 30, 2021Inventors: Farhan Tauheed, Onur Kocberber, Tomas Karnagel, Nipun Agarwal
-
Publication number: 20210365805Abstract: Techniques for estimating the number of distinct values in a data set using machine learning are provided. In one technique, a sample of a data set is retrieved where the sample is a strict subset of the data set. The sample is analyzed to identify feature values of multiple features of the sample. The feature values are inserted into a machine-learned model that computes a prediction regarding a number of distinct values in the data set. An estimated number of distinct values that is based on the prediction is stored in association with the data set.Type: ApplicationFiled: May 19, 2020Publication date: November 25, 2021Inventors: Tomas Karnagel, Onur Kocberber, Farhan Tauheed, Nipun Agarwal
-
Publication number: 20210263934Abstract: Embodiments implement a prediction-driven, rather than a trial-driven, approach to automate database configuration parameter tuning for a database workload. This approach uses machine learning (ML) models to test performance metrics resulting from application of particular database parameters to a database workload, and does not require live trials on the DBMS managing the workload. Specifically, automatic configuration (AC) ML models are trained, using a training corpus that includes information from workloads being run by DBMSs, to predict performance metrics based on workload features and configuration parameter values. The trained AC-ML models predict performance metrics resulting from applying particular configuration parameter values to a given database workload being automatically tuned. Based on correlating changes to configuration parameter values with changes in predicted performance metrics, an optimization algorithm is used to converge to an optimal set of configuration parameters.Type: ApplicationFiled: May 12, 2021Publication date: August 26, 2021Inventors: Sam Idicula, Tomas Karnagel, Jian Wen, Seema Sundara, Nipun Agarwal, Mayur Bency
-
Patent number: 11061902Abstract: Embodiments implement a prediction-driven, rather than a trial-driven, approach to automate database configuration parameter tuning for a database workload. This approach uses machine learning (ML) models to test performance metrics resulting from application of particular database parameters to a database workload, and does not require live trials on the DBMS managing the workload. Specifically, automatic configuration (AC) ML models are trained, using a training corpus that includes information from workloads being run by DBMSs, to predict performance metrics based on workload features and configuration parameter values. The trained AC-ML models predict performance metrics resulting from applying particular configuration parameter values to a given database workload being automatically tuned. Based on correlating changes to configuration parameter values with changes in predicted performance metrics, an optimization algorithm is used to converge to an optimal set of configuration parameters.Type: GrantFiled: March 11, 2019Date of Patent: July 13, 2021Assignee: Oracle International CorporationInventors: Sam Idicula, Tomas Karnagel, Jian Wen, Seema Sundara, Nipun Agarwal, Mayur Bency
-
Publication number: 20200327357Abstract: The present invention relates to dimensionality reduction for machine learning (ML) models. Herein are techniques that individually rank features and combine features based on their rank to achieve an optimal combination of features that may accelerate training and/or inferencing, prevent overfitting, and/or provide insights into somewhat mysterious datasets. In an embodiment, a computer ranks features of datasets of a training corpus. For each dataset and for each landmark percentage, a target ML model is configured to receive only a highest ranking landmark percentage of features, and a landmark accuracy achieved by training the ML model with the dataset is measured. Based on the landmark accuracies and meta-features values of the dataset, a respective training tuple is generated for each dataset. Based on all of the training tuples, a regressor is trained to predict an optimal amount of features for training the target ML model.Type: ApplicationFiled: August 21, 2019Publication date: October 15, 2020Inventors: TOMAS KARNAGEL, SAM IDICULA, HESAM FATHI MOGHADAM, NIPUN AGARWAL
-
Publication number: 20200125568Abstract: Embodiments utilize trained query performance machine learning (QP-ML) models to predict an optimal compute node cluster size for a given in-memory workload. The QP-ML models include models that predict query task runtimes at various compute node cardinalities, and models that predict network communication time between nodes of the cluster. Embodiments also utilize an analytical model to predict overlap between predicted task runtimes and predicted network communication times. Based on this data, an optimal cluster size is selected for the workload. Embodiments further utilize trained data capacity machine learning (DC-ML) models to predict a minimum number of compute nodes needed to run a workload. The DC-ML models include models that predict the size of the workload dataset in a target data encoding, models that predict the amount of memory needed to run the queries in the workload, and models that predict the memory needed to accommodate changes to the dataset.Type: ApplicationFiled: April 11, 2019Publication date: April 23, 2020Inventors: Sam Idicula, Tomas Karnagel, Jian Wen, Seema Sundara, Nipun Agarwal, Mayur Bency
-
Publication number: 20200125545Abstract: Embodiments implement a prediction-driven, rather than a trial-driven, approach to automate database configuration parameter tuning for a database workload. This approach uses machine learning (ML) models to test performance metrics resulting from application of particular database parameters to a database workload, and does not require live trials on the DBMS managing the workload. Specifically, automatic configuration (AC) ML models are trained, using a training corpus that includes information from workloads being run by DBMSs, to predict performance metrics based on workload features and configuration parameter values. The trained AC-ML models predict performance metrics resulting from applying particular configuration parameter values to a given database workload being automatically tuned. Based on correlating changes to configuration parameter values with changes in predicted performance metrics, an optimization algorithm is used to converge to an optimal set of configuration parameters.Type: ApplicationFiled: March 11, 2019Publication date: April 23, 2020Inventors: Sam Idicula, Tomas Karnagel, Jian Wen, Seema Sundara, Nipun Agarwal, Mayur Bency
-
Publication number: 20200118036Abstract: The present invention relates to dimensionality reduction for machine learning (ML) models. Herein are techniques that individually rank features and combine features based on their rank to achieve an optimal combination of features that may accelerate training and/or inferencing, prevent overfitting, and/or provide insights into somewhat mysterious datasets. In an embodiment, a computer calculates, for each feature of a training dataset, a relevance score based on: a relevance scoring function, and statistics of values, of the feature, that occur in the training dataset. A rank based on relevance scores of the features is calculated for each feature. A sequence of distinct subsets of the features, based on the ranks of the features, is generated. For each distinct subset of the sequence of distinct feature subsets, a fitness score is generated based on training a machine learning (ML) model that is configured for the distinct subset.Type: ApplicationFiled: May 20, 2019Publication date: April 16, 2020Inventors: Tomas Karnagel, Sam Idicula, Nipun Agarwal