Oracle International Corporation

Sam Idicula

Nipun Agarwal

Eric Sedlar

Sivasankaran Chandrasekar

Sabina Petride

Ravi Murthy

Sandeep Agrawal

Venkatanathan Varadarajan

Balasubramanyam Sthanikam

Thomas Baby

Namit Jain

Asha Tarachandani

Bhushan Khaladkar

Nitin Kunal

Seema Sundara

Arun Raghavan

Tomas Karnagel

Jian Wen

Ning Zhang

Vikram Kapoor

David Allen Brown

Erik Schlanger

Michael Alexander Duller

Rishabh Jain

Syam Sundar Pannala

Rajkumar Sen

Gong Zhang

David Joseph Hawkins

Venkatraman Govindaraju

Vijay Medi

Mayur Bency

Mohammed Irfan Rafiq

Thuvan Hoang

Hesam Fathi Moghadam

Anatoly Yakovlev

Cagri Balkesen

Aarti Basant

Farhan Tauheed

Negar Koochakzadeh

Vikas Aggarwal

Pit Fender

Benjamin Schlegel

Thomas Chang

Thomas F Keefe

Vikram Reddy Pesati

Onur Kocberber

Viswanathan Krishnamurthy

Adiel Yoaz

Abhyudaya Agrawal

Anantha Kiran Kandukuri

Sanket Malde

Christopher Joseph Daniels

Kantikiran Pasupuleti

Kirtikar Kashyap

Evangelos Vlachos

Gaurav Chadha

Nitin Kumar Gupta

Boris Klots

Chon Hei Lei

Felix Schmidt

Tanvir Ahmed

Khai Tran

Karoon Rashedi Nia

Tayler Hetherington

Zahra Zohrevand

Fei Ge

Tim Wing Yu

Guang-Tong Zhou

Kevin Moore

Andrea Di Blas

Shenoda Guirguis

Brian Gold

Georgios Giannikis

Ashwini Surpur

Ali Moharrer

Ali Maleki Tabar

Ellen Batbouta

Jingxiao Cai

Jarod Wen

Danica Porobic

Cem Emre Sozgen

Ankur Arora

Indu Bhagat

Nicolas Montoya

Sivasanakan Chandrasekar

Nathan Pemberton

Wolf Roediger

Sandeep Mane

Stephan Wolf

Techniques are described herein for performing efficient matrix multiplication in architectures with scratchpad memories or associative caches using asymmetric allocation of space for the different matrices. The system receives a left matrix and a right matrix. In an embodiment, the system allocates, in a scratchpad memory, asymmetric memory space for tiles for each of the two matrices as well as a dot product matrix. The system proceeds with then performing dot product matrix multiplication involving the tiles of the left and the right matrices, storing resulting dot product values in corresponding allocated dot product matrix tiles. The system then proceeds to write the stored dot product values from the scratchpad memory into main memory.

Asymmetric allocation of SRAM and data layout for efficient matrix-matrix multiplication

Herein are techniques that train regressor(s) to predict how effective would a machine learning model (MLM) be if trained with new hyperparameters and/or dataset. In an embodiment, for each training dataset, a computer derives, from the dataset, values for dataset metafeatures. The computer performs, for each hyperparameters configuration (HC) of a MLM, including landmark HCs: configuring the MLM based on the HC, training the MLM based on the dataset, and obtaining an empirical quality score that indicates how effective was said training the MLM when configured with the HC. A performance tuple is generated that contains: the HC, the values for the dataset metafeatures, the empirical quality score and, for each landmark configuration, the empirical quality score of the landmark configuration and/or the landmark configuration itself. Based on the performance tuples, a regressor is trained to predict an estimated quality score based on a given dataset and a given HC.

Using metamodeling for fast and accurate hyperparameter optimization of machine learning and deep learning models

Techniques are described for generating and applying mini-machine learning variants of machine learning algorithms to save computational resources in tuning and selection of machine learning algorithms. In an embodiment, at least one of the hyper-parameter values for a reference variant is modified to a new hyper-parameter value thereby generating a new variant of machine learning algorithm from the reference variant of machine learning algorithm. A performance score is determined for the new variant of machine learning algorithm using a training dataset, the performance score representing the accuracy of the new machine learning model for the training dataset. By performing training of the new variant of machine learning algorithm with the training data set, a cost metric of the new variant of machine learning algorithm is measured by measuring usage the used computing resources for the training. Based on the cost metric of the new variant of machine learning algorithm and comparing the performance score for the new and reference variants, the system determines whether the modified reference machine algorithm is the mini-machine learning algorithm that is computationally less costly than the reference variant of machine learning algorithm but closely tracks the accuracy thereof.

Mini-machine learning

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.

Automated provisioning for database performance

Herein, horizontally scalable techniques efficiently configure machine learning algorithms for optimal accuracy and without informed inputs. In an embodiment, for each particular hyperparameter, and for each epoch, a computer processes the particular hyperparameter. An epoch explores one hyperparameter based on hyperparameter tuples. A respective score is calculated from each tuple. The tuple contains a distinct combination of values, each of which is contained in a value range of a distinct hyperparameter. All values of a tuple that belong to the particular hyperparameter are distinct. All values of a tuple that belong to other hyperparameters are held constant. The value range of the particular hyperparameter is narrowed based on an intersection point of a first line based on the scores and a second line based on the scores. A machine learning algorithm is optimally configured from repeatedly narrowed value ranges of hyperparameters. The configured algorithm is invoked to obtain a result.

Gradient-based auto-tuning for machine learning and deep learning models

Techniques are provided for selection of machine learning algorithms based on performance predictions by using hyperparameter predictors. In an embodiment, for each mini-machine learning model (MML model), a respective hyperparameter predictor set that predicts a respective set of hyperparameter settings for a data set is trained. Each MML model represents a respective reference machine learning model (RML model). Data set samples are generated from the data set. Meta-feature sets are generated, each meta-feature set describing a respective data set sample. A respective target set of hyperparameter settings are generated for said each MML model using a hypertuning algorithm. The meta-feature sets and the respective target set of hyperparameter settings are used to train the respective hyperparameter predictor set. Each hyperparameter predictor set is used during training and inference to improve the accuracy of automatically selecting a RML model per data set.

Using hyperparameter predictors to improve accuracy of automatic machine learning model selection

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.

Automatic feature subset selection based on meta-learning

Techniques are described herein for predicting disk drive failure using a machine learning model. The framework involves receiving disk drive sensor attributes as training data, preprocessing the training data to select a set of enhanced feature sequences, and using the enhanced feature sequences to train a machine learning model to predict disk drive failures from disk drive sensor monitoring data. Prior to the training phase, the RNN LSTM model is tuned using a set of predefined hyper-parameters. The preprocessing, which is performed during the training and evaluation phase as well as later during the prediction phase, involves using predefined values for a set of parameters to generate the set of enhanced sequences from raw sensor reading. The enhanced feature sequences are generated to maintain a desired healthy/failed disk ratio, and only use samples leading up to a last-valid-time sample in order to honor a pre-specified heads-up-period alert requirement.

Disk drive failure prediction with neural networks

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. The optimal set of configuration parameter values is automatically applied for the given workload.

Automated configuration parameter tuning for database performance

According to an embodiment, a method includes generating a first dataset sample from a dataset, calculating a first validation score for the first dataset sample and a machine learning model, and determining whether a difference in validation score between the first validation score and a second validation score satisfies a first criteria. If the difference in validation score does not satisfy the first criteria, the method includes generating a second dataset sample from the dataset. If the difference in validation score does satisfy the first criteria, the method includes updating a convergence value and determining whether the updated convergence value satisfies a second criteria. If the updated convergence value satisfies the second criteria, the method includes returning the first dataset sample. If the updated convergence value does not satisfy the second criteria, the method includes generating the second dataset sample from the dataset.

Adaptive sampling for imbalance mitigation and dataset size reduction in machine learning

Techniques are provided for selection of machine learning algorithms based on performance predictions by trained algorithm-specific regressors. In an embodiment, a computer derives meta-feature values from an inference dataset by, for each meta-feature, deriving a respective meta-feature value from the inference dataset. For each trainable algorithm and each regression meta-model that is respectively associated with the algorithm, a respective score is calculated by invoking the meta-model based on at least one of: a respective subset of meta-feature values, and/or hyperparameter values of a respective subset of hyperparameters of the algorithm. The algorithm(s) are selected based on the respective scores. Based on the inference dataset, the selected algorithm(s) may be invoked to obtain a result. In an embodiment, the trained regressors are distinctly configured artificial neural networks. In an embodiment, the trained regressors are contained within algorithm-specific ensembles. Techniques are also provided for optimal training of regressors and/or ensembles.

Algorithm-specific neural network architectures for automatic machine learning model selection

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.

Automatic feature subset selection using feature ranking and scalable automatic search

Herein are techniques to generate candidate rulesets for machine learning (ML) explainability (MLX) for black-box ML models. In an embodiment, an ML model generates classifications that each associates a distinct example with a label. A decision tree that, based on the classifications, contains tree nodes is received or generated. Each node contains label(s), a condition that identifies a feature of examples, and a split value for the feature. When a node has child nodes, the feature and the split value that are identified by the condition of the node are set to maximize information gain of the child nodes. Candidate rules are generated by traversing the tree. Each rule is built from a combination of nodes in a tree traversal path. Each rule contains a condition of at least one node and is assigned to a rule level. Candidate rules are subsequently optimized into an optimal ruleset for actual use.

Method for generating rulesets using tree-based models for black-box machine learning explainability

Herein are techniques for exploring hyperparameters of a machine learning model (MLM) and to train a regressor to predict a time needed to train the MLM based on a hyperparameter configuration and a dataset. In an embodiment that is deployed in production inferencing mode, for each landmark configuration, each containing values for hyperparameters of a MLM, a computer configures the MLM based on the landmark configuration and measures time spent training the MLM on a dataset. An already trained regressor predicts time needed to train the MLM based on a proposed configuration of the MLM, dataset meta-feature values, and training durations and hyperparameter values of landmark configurations of the MLM. When instead in training mode, a regressor in training ingests a training corpus of MLM performance history to learn, by reinforcement, to predict a training time for the MLM for new datasets and/or new hyperparameter configurations.

Predicting machine learning or deep learning model training time

Techniques are described herein for building a framework for declarative query compilation using both rule-based and cost-based approaches for database management. The framework involves constructing and using: a set of rule-based properties tables that contain optimization parameters for both logical and physical optimization, a recursive algorithm to form candidate physical query plans that is based on the rule based tables, and a cost model for estimating the cost of a generated physical query plan that is used with the rule based properties tables to prune inferior query plans.

Hybrid declarative query compiler and optimizer framework

Growing community of inventors

Santa Clara, CA, United States of America

Sam Idicula