Sam Idicula

Securing End User Access To Application Databases

Workload-Driven Index Selections

Automated provisioning for database performance

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

FAST, PREDICTIVE, AND ITERATION-FREE AUTOMATED MACHINE LEARNING PIPELINE

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

Automated configuration parameter tuning for database performance

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

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

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

Predicting machine learning or deep learning model training time

Automatic feature subset selection based on meta-learning

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

Mini-machine learning

Automated provisioning for database performance

Automated configuration parameter tuning for database performance

Automatic feature subset selection using feature ranking and scalable automatic search

Disk drive failure prediction with neural networks

AUTOMATED WINDOW BASED FEATURE GENERATION FOR TIME-SERIES FORECASTING AND ANOMALY DETECTION

Hybrid instrumentation framework for multicore low power processors

Scalable distributed computation framework for data-intensive computer vision workloads

Hybrid declarative query compiler and optimizer framework

Efficient partitioning of relational data

Tail-based top-N query evaluation

USING META-LEARNING FOR AUTOMATIC GRADIENT-BASED HYPERPARAMETER OPTIMIZATION FOR MACHINE LEARNING AND DEEP LEARNING MODELS

Hybrid instrumentation framework for multicore low power processors

Distributed relational dictionaries

Massively parallel and in-memory execution of grouping and aggregation in a heterogeneous system

Adaptive resolution histogram on complex datatypes

Complete, correct and fast compile-time encoding inference on the basis of an underlying type system

Boomerang join: a network efficient, late-materialized, distributed join technique

Scalable and efficient distributed auto-tuning of machine learning and deep learning models

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

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

Assymetric allocation of SRAM and data layout for efficient matrix multiplication

High-performance data repartitioning for cloud-scale clusters

Matrix multiplication at memory bandwidth

Dynamic grouping of in-memory data processing operations

Consistent query execution for big data analytics in a hybrid database

Tail-based top-N query evaluation

Tuple encoding aware direct memory access engine for scratchpad enabled multi-core processors

Dynamic operation scheduling for distributed data processing

Scalable distributed computation framework for data-intensive computer vision workloads

Efficient parallel algorithm for integral image computation for many-core CPUs

Memory management for sparse matrix multiplication

Efficient partitioning of relational data

Application-level dynamic scheduling of network communication for efficient re-partitioning of skewed data

Database tuple-encoding-aware data partitioning in a direct memory access engine

Row identification number generation in database direct memory access engine

Performing database operations using a vectorized approach or a non-vectorized approach

Partition aware evaluation of top-N queries

Run length encoding aware direct memory access filtering engine for scratchpad enabled multicore processors

Tuple encoding aware direct memory access engine for scratchpad enabled multicore processors

Version control based on a dual-range validity model

Scheduled network communication for efficient re-partitioning of data

Method for failure-resilient data placement in a distributed query processing system

Multi-system query execution plan

Adaptive handling of skew for distributed joins in a cluster

Adaptive resolution hsitogram

Workload aware data placement for join-based query processing in a cluster

Hybrid binary XML storage model for efficient XML processing

Hybrid binary XML storage model for efficient XML processing

Estimating a cost of performing database operations using vectorized instructions

Data compaction using vectorized instructions

Efficient pushdown of joins in a heterogeneous database system involving a large-scale low-power cluster

Massively parallel and in-memory execution of grouping and aggregation in a heterogeneous system

Pushdown of sorting and set operations (union, intersection, minus) to a large number of low-power cores in a heterogeneous system

Technique for skipping irrelevant portions of documents during streaming XPath evaluation

Efficient pushdown of joins in a heterogeneous database system involving a large-scale low-power cluster

Optimal data representation and auxiliary structures for in-memory database query processing

Automatic denormalization for analytic query processing in large-scale clusters

Efficient file access in a large repository using a two-level cache

Efficient validation of binary XML data

Techniques for efficient queries on a file system-like repository

Hybrid binary XML storage model for efficient XML processing

Operationally complete hierarchical repository in a relational database

Techniques for fast and scalable XML generation and aggregation over binary XML

Techniques for efficient and scalable processing of complex sets of XML schemas

Efficient validation of binary XML data

Techniques for efficient queries on a file system-like repository

Efficient file access in a large repository using a two-level cache

Operationally complete hierarchical repository in a relational database

Leveraging XML capabilities of a database to enhance handling of document data

Technique to gather statistics on very large hierarchical collections in a scalable and efficient manner

Technique for skipping irrelevant portions of documents during streaming XPath evaluation

Query optimization by specifying path-based predicate evaluation in a path-based query operator

Efficient way to evaluate aggregations on XML data using path-based row sources

Cache-based predicate handling for queries on XML data using uncorrelated path-based row sources

Efficient way to evaluate uncorrelated path-based row sources with XML storage

Estimating cardinalities of XML table constructs within queries

Method and system for optimizing row level security in database systems

Mechanism for deferred rewrite of multiple XPath evaluations over binary XML

HIGH PERFORMANCE SECURE CACHING IN THE MID-TIER

Document fidelity with binary XML storage