Abstract: Systems, methods, and computer-readable media are disclosed for parallel stochastic gradient descent using linear and non-linear activation functions. One method includes: receiving a set of input examples; receiving a global model; and learning a new global model based on the global model and the set of input examples by iteratively performing the following steps: computing a plurality of local models having a plurality of model parameters based on the global model and at least a portion of the set of input examples; computing, for each local model, a corresponding model combiner based on the global model and at least a portion of the set of input examples; and combining the plurality of local models into the new global model based on the current global model and the plurality of corresponding model combiners.

Abstract: Embodiments of the present invention provide systems, methods, and computer storage media directed to optimizing the generation, evaluation, and selection of tensor circuit specifications for a tensor circuit to perform homomorphic encryption operations on encrypted data. A computing device having an improved compiler and runtime configuration can obtain a tensor circuit and associated schema. The computing device can map the obtained tensor circuit to an equivalent tensor circuit, adapted to perform fully homomorphic encryption (FHE) operations, and instantiated based on the obtained associated scheme. The computing device can then monitor a flow of data through the equivalent FHE-adapted tensor circuit utilizing various tensor circuit specifications determined therefor.

Abstract: Described herein is a system that transmits and combines local models, that individually comprise a set of local parameters computed via stochastic gradient descent (SGD), into a global model that comprises a set of global model parameters. The local models are computed in parallel at different geographic locations along with symbolic representations. The symbolic representations can be used to combine the local models. The global model can determine a likelihood, given a new data instance of a feature set, that a user performs a computer interaction with the content element. For instance, the system can use the model to provide search results in response to a search query submitted by a user. Or, the system can use the model to make a recommendation or suggestion to a user in response to a request for content (e.g., display a targeted advertisement, suggest a news story, etc.).

Abstract: Described herein is a system that transmits and combines local models, that individually comprise a set of local parameters computed via stochastic gradient descent (SGD), into a global model that comprises a set of global model parameters. The local models are computed in parallel at different geographic locations along with symbolic representations. Network transmission of the local models and the symbolic representations, rather than transmission of the large training data subsets processed to compute the local models and symbolic representations, conserves resources and decreases latency. The global model can then be used as a model to determine a likelihood of a course of action being successful for an organization. For example, the course of action can be a purchase of a security or a business operation strategy. In another example, the course of action can be a type of medical treatment for a patient.

Abstract: Described herein is a system transmits and combines local models, that individually include a set of local parameters computed via stochastic gradient descent (SGD), into a global model that includes a set of global model parameters. The local models are computed in parallel at different geographic locations (e.g., different instances of computing infrastructure) along with symbolic representations. Network transmission of the local models and the symbolic representations, rather than transmission of the large training data subsets processed to compute the local models and symbolic representations, conserves resources and decreases latency. The global model can then be used as a model to determine a likelihood that at least a portion of current and/or recently received data traffic is illegitimate data traffic that is associated with a cyber attack. In some instances, the system can implement a remedial action to mitigate the effects of the cyber attack on computing infrastructure.

Abstract: Embodiments of the present invention provide systems, methods, and computer storage media directed to optimizing the generation, evaluation, and selection of tensor circuit specifications for a tensor circuit to perform homomorphic encryption operations on encrypted data. A computing device having an improved compiler and runtime configuration can obtain a tensor circuit and associated schema. The computing device can map the obtained tensor circuit to an equivalent tensor circuit, adapted to perform fully homomorphic encryption (FHE) operations, and instantiated based on the obtained associated scheme. The computing device can then monitor a flow of data through the equivalent FHE-adapted tensor circuit utilizing various tensor circuit specifications determined therefor.

Abstract: Described herein is a system that transmits and combines local models, that individually comprise a set of local parameters computed via stochastic gradient descent (SGD), into a global model that comprises a set of global model parameters. The local models are computed in parallel at different geographic locations along with symbolic representations. Network transmission of the local models and the symbolic representations, rather than transmission of the large training data subsets processed to compute the local models and symbolic representations, conserves resources and decreases latency. The global model can then be used as a model to determine a likelihood of a monitored resource or a user of the monitored resource experiencing a problem with respect to performance or completion of one or more operations. The system can also implement an action to assist in resolving or avoiding the problem.

Abstract: Described herein is a system that transmits and combines local models, that individually comprise a set of local parameters computed via stochastic gradient descent (SGD), into a global model that comprises a set of global model parameters. The local models are computed in parallel at different geographic locations along with symbolic representations. Network transmission of the local models and the symbolic representations, rather than transmission of the large training data subsets processed to compute the local models and symbolic representations, conserves resources and decreases latency. The global model can then be used as a model to determine a likelihood of a course of action being successful for an organization. For example, the course of action can be a purchase of a security or a business operation strategy. In another example, the course of action can be a type of medical treatment for a patient.

Abstract: Described herein is a system transmits and combines local models, that individually comprise a set of local parameters computed via stochastic gradient descent (SGD), into a global model that comprises a set of global model parameters. The local models are computed in parallel at different geographic locations (e.g., different instances of computing infrastructure) along with symbolic representations. Network transmission of the local models and the symbolic representations, rather than transmission of the large training data subsets processed to compute the local models and symbolic representations, conserves resources and decreases latency. The global model can then be used as a model to determine a likelihood that at least a portion of current and/or recently received data traffic is illegitimate data traffic that is associated with a cyber attack. In some instances, the system can implement a remedial action to mitigate the effects of the cyber attack on computing infrastructure.

Abstract: Described herein is a system that transmits and combines local models, that individually comprise a set of local parameters computed via stochastic gradient descent (SGD), into a global model that comprises a set of global model parameters. The local models are computed in parallel at different geographic locations along with symbolic representations. Network transmission of the local models and the symbolic representations, rather than transmission of the large training data subsets processed to compute the local models and symbolic representations, conserves resources and decreases latency. The global model can then be used as a model to determine a likelihood of a monitored resource or a user of the monitored resource experiencing a problem with respect to performance or completion of one or more operations. The system can also implement an action to assist in resolving or avoiding the problem.

Abstract: Described herein is a system that transmits and combines local models, that individually comprise a set of local parameters computed via stochastic gradient descent (SGD), into a global model that comprises a set of global model parameters. The local models are computed in parallel at different geographic locations along with symbolic representations. The symbolic representations can be used to combine the local models. The global model can determine a likelihood, given a new data instance of a feature set, that a user performs a computer interaction with the content element. For instance, the system can use the model to provide search results in response to a search query submitted by a user. Or, the system can use the model to make a recommendation or suggestion to a user in response to a request for content (e.g., display a targeted advertisement, suggest a news story, etc.).

Abstract: Systems, methods, and computer-readable media are disclosed for parallel stochastic gradient descent using linear and non-linear activation functions. One method includes: receiving a set of input examples; receiving a global model; and learning a new global model based on the global model and the set of input examples by iteratively performing the following steps: computing a plurality of local models having a plurality of model parameters based on the global model and at least a portion of the set of input examples; computing, for each local model, a corresponding model combiner based on the global model and at least a portion of the set of input examples; and combining the plurality of local models into the new global model based on the current global model and the plurality of corresponding model combiners.

Abstract: Concepts and technologies are described herein providing technologies for mining patterns in temporal data streams. Data is broken into data sub-portions. Dependencies in computation between one or more of the data sub-portions are broken using symbolic data types. Symbolic summaries of computations of sub-portions are performed in parallel and are reduced to generate an output.

Abstract: Concepts and technologies are described herein providing technologies for mining patterns in temporal data streams. Data is broken into data sub-portions. Dependencies in computation between one or more of the data sub-portions are broken using symbolic data types. Symbolic summaries of computations of sub-portions are performed in parallel and are reduced to generate an output.

Abstract: The techniques and/or systems described herein implement parallel processing of a dynamic programming problem across stages and/or clusters by breaking dependencies between stages and/or clusters. For instance, the techniques and/or systems may identify dependencies between sub-problems of the dynamic programming problem and group the sub-problems into stages. The techniques and/or systems may also group the stages into clusters (e.g., at least two clusters to be parallel processed). Then, the techniques and/or systems generate one or more solutions to use instead of actual solutions so that the dynamic programming problem can be parallel processed across stages and/or clusters.

Abstract: The techniques and/or systems described herein implement parallel processing of a dynamic programming problem across stages and/or clusters by breaking dependencies between stages and/or clusters. For instance, the techniques and/or systems may identify dependencies between sub-problems of the dynamic programming problem and group the sub-problems into stages. The techniques and/or systems may also group the stages into clusters (e.g., at least two clusters to be parallel processed). Then, the techniques and/or systems generate one or more solutions to use instead of actual solutions so that the dynamic programming problem can be parallel processed across stages and/or clusters.

Abstract: Selectively rebooting components of a computer system. One or more tables which list respective costs to reboot the components and respective likelihoods that reboots of the respective components will correct respective problems with the computer system are generated. Each of the costs is based on a time to reboot or delays caused by the reboot of the respective component. In response to a subsequent problem with the computer system, an order to reboot components of the computer system is determined from the table based on the costs and likelihoods that the reboot will correct the problem, such that a component of the computer system characterized by a relatively low cost and high likelihood to correct the problem will be rebooted before another component characterized by a relatively high cost and low likelihood to correct the problem. The tables are updated through actual experience.

Abstract: Selectively rebooting components of a computer system. One or more tables which list respective costs to reboot the components and respective likelihoods that reboots of the respective components will correct respective problems with the computer system are generated. Each of the costs is based on a time to reboot or delays caused by the reboot of the respective component. In response to a subsequent problem with the computer system, an order to reboot components of the computer system is determined from the table based on the costs and likelihoods that the reboot will correct the problem, such that a component of the computer system characterized by a relatively low cost and high likelihood to correct the problem will be rebooted before another component characterized by a relatively high cost and low likelihood to correct the problem. The tables are updated through actual experience.

Abstract: A system and method for tracking an electronic document includes a document preparation tool that can accept document content and form data, encrypt the content data, provide a document ID, prepare instructions for generating a data input form and package the encrypted data, document ID and instructions in the electronic document. When a user accesses the electronic document, the instructions can display the data input form to the user. A local file containing the document ID and the user ID can be created on the user's computer system and the content can be decrypted and presented to the user. Files on the document can be updated to include the user ID and a listing of the actions taken by the user with respect to the opened document and the data in the local file and document files can be transmitted to a server for storage in a database.