Abstract: Techniques are provided for dynamic prediction-based regression optimization. In one embodiment, the techniques involve determining, via a process model, a variable state of the process model, wherein the variable state includes a first input state variable, a first output state variable, and a first control parameter, generating, via a short-term prediction module, a first prediction of a first update of the variable state, generating, via a terminal value prediction module, a second prediction of a second update to the variable state, generating, via a control optimization module, a second control parameter based on the first prediction and the second prediction, and controlling, via a processor, a production process of the process model based on the second control parameter.

Abstract: Methods and systems for tuning a model include generating pipelines. The pipelines have elements that include at least an agent, a foundation model, and a tuning type. Hyperparameters of elements of the pipelines are set in accordance with an input task. Elements of the pipelines are tuned in accordance with the input task. The input task is performed using a highest-performance pipeline.

Abstract: A method for Markov Decision Process (“MDP”) decomposition includes receiving data elements for a problem that include finite state data for a set of state variables and a finite set of actions. A portion of the state data corresponding to state variables represents states. The method incudes creating two or more sub-MDPs. Each sub-MDP includes a portion of the set of state variables, the set of actions and a same reward function. The method includes executing each sub-MDP. Results include a policy and an expected reward from the reward function. The policy of the sub-MDP maps states of the sub-MDP to actions. The method includes aggregating, based on the expected rewards of the results, the actions of the policies of the sub-MDPs to create a resultant policy with resultant actions and generating, using state entries for the set of state variables, results to the problem based on the resultant policy.

Abstract: Embodiments of the invention are directed to collecting, by a computer system, sensor data of a manufacturing system, the sensor data being measured at intervals smaller than a time interval of a target measurement of the manufacturing system. The sensor data is determined to have a relationship to the target measurement. A synthetic target measurement is generated at an interval smaller than the time interval based on the relationship. An advance warning is automatically generated for the target measurement based on the synthetic target measurement within the interval smaller than the time interval.

Abstract: A product and methodology is contemplated for monitoring a multivariate process. The product has a computer readable storage medium with program instructions embodied therewith. The program instructions are executable by a computer processor to cause the device to: segment data obtained from the multivariate process into a time series of snapshot intervals, each snapshot interval further segmented into a predetermined plurality of zone intervals; compute a contrastive metric from the segmented data for each variable during each zone interval; compare the computed contrastive metrics to one or more predetermined threshold values to define representationally relevant zone intervals for each variable; apply representation learning to derive zone-based feature vectors for each variable during the corresponding relevant zone intervals; and concatenate the zone-based feature vectors into a representation vector for the multivariate process during the time series of snapshots.

Abstract: According to a present invention embodiment, a system for training a reinforcement learning agent comprises one or more memories and at least one processor coupled to the one or more memories. The system trains a machine learning model based on training data to generate a set of hyperparameters for training the reinforcement learning agent. The training data includes encoded information from hyperparameter tuning sessions for a plurality of different reinforcement learning environments and reinforcement learning agents. The machine learning model determines the set of hyperparameters for training the reinforcement learning agent, and the reinforcement learning agent is trained according to the set of hyperparameters. The machine learning model adjusts the set of hyperparameters based on information from testing of the reinforcement learning agent.

Abstract: According to a present invention embodiment, a system identifies a plurality of configurations for machine learning models. Each configuration indicates a machine learning model and a corresponding technique to determine parameters for the machine learning model. The plurality of configurations are evaluated by training the machine learning model of the plurality of configurations according to the parameters determined by the corresponding technique. Performance of the machine learning models of the plurality of configurations is monitored, and resources used for evaluating at least one configuration are adjusted based on the performance of the machine learning model for the at least one configuration relative to the performance of the machine learning models of others of the plurality of configurations. Embodiments of the present invention further include a method and computer program product for training machine learning models in substantially the same manner described above.

Abstract: One or more systems, computer-implemented methods and/or computer program products to facilitate a process to monitor and/or facilitate a modification to a manufacturing process. A system can comprise a memory that stores computer executable components and a processor that executes the computer executable components stored in the memory. The computer executable components can comprise an initialization component that identifies values of inflow data of one or more inflows of a set of inflows to a manufacturing process as control variables, and a computation optimization component that optimizes one or more intermediate flows, outflows or flow qualities of the manufacturing process using, for mode-specific regression models, decision variables that are based on a set of joint-levels of the control variables. An operation mode determination component can determine operation modes of the manufacturing process that are together defined by a set of joint-levels of the control variables.

Abstract: Disclosed embodiments may include a system for identifying Markov Decision Process (MDP) solutions. The system may receive input data including one or more first states and one or more first actions. The system may identify, via a machine learning model (MLM), a subset of the input data. The system may formulate, via the MLM, a search space based on the subset of the input data, the search space including one or more second states and one or more second actions. The system may conduct, via the MLM, hyperparameter tuning of the search space. The system may generate, via the MLM, an MDP instance based on the hyperparameter tuning. The system may determine, via the MLM, whether the generated MDP instance includes a first MDP solution.

Abstract: A computer implemented method for data driven optimization. A number of processor units creates a regression model using historical data in a current neighborhood. The historical data is for a system over time. The number of processor units generates an optimization solution using the regression model created from the current neighborhood and an objective function. The number of processor units determines whether the optimization solution is within the current neighborhood. The number of processor units selects a new neighborhood containing the historical data in response to the optimization solution not being within the current neighborhood. The new neighborhood is based on the optimization solution and becomes the current neighborhood. The number of processor units repeats the creating, generating, determining, and selecting steps in response to the optimization solution not being within the current neighborhood.

Abstract: A relationship between an input, a set-point of a plurality of processes and an output of a corresponding process is learned using machine learning. A regression function is derived for each process based upon historical data. An autoencoder is trained for each process based upon the historical data to form a regularizer and the regression functions and regularizers are merged together into a unified optimization problem. System level optimization is performed using the regression functions and regularizers and a set of optimal set-points of a global optimal solution for operating the processes is determined. An industrial system is operated based on the set of optimal set-points.

Abstract: In an approach for real-time opportunity discovery for productivity enhancement of a production process, a processor extracts a set of features from time series data, through autoencoding using a neural network, based on non-control variables for the time series data. A processor identifies one or more operational modes based on the extracted features including a dimensional reduction with a representation learning from the time series data. A processor identifies a neighborhood of a current operational state based on the extracted features. A processor compares the current operational state to historical operational states based on the time series data at the same operational mode. A processor discovers an operational opportunity based on the comparison of the current operational state to the historical operational states using the neighborhood. A processor identifies control variables in the same mode which variables are relevant to the current operational state.

Abstract: A method includes training, by one or more processing devices, a plurality of machine learning predictive models, thereby generating a plurality of trained machine learning predictive models. The method further includes generating, by the one or more processing devices, a solved machine learning optimization model, based at least in part on the plurality of trained machine learning predictive models. The method further includes outputting, by the one or more processing devices, one or more control input and predicted outputs based at least in part on the solved machine learning optimization model.

Abstract: A relationship between an input, a set-point of a plurality of processes and an output of a corresponding process is learned using machine learning. A regression function is derived for each process based upon historical data. An autoencoder is trained for each process based upon the historical data to form a regularizer and the regression functions and regularizers are merged together into a unified optimization problem. System level optimization is performed using the regression functions and regularizers and a set of optimal set-points of a global optimal solution for operating the processes is determined. An industrial system is operated based on the set of optimal set-points.

Abstract: A computer-implemented method, computer program product, and computer system for automated model predictive control. The computer system trains multiple step look-ahead regression models, using historical states and historical actions for a to-be-optimized system, for each timestep of a past time horizon. Regression models may be either linear or nonlinear in order to capture process dynamics and nonlinearity. The computer system generates optimization constraints for each timestep of a future time horizon. The computer system generates optimization variables, based on the multiple step look-ahead regression models, for each timestep of the future time horizon. The computer system constructs a mixed integer linear programming based optimization model that includes an objective function, the optimization constraints, and the optimization variables. Nonlinear regression models are converted into piecewise linear approximation functions.

Abstract: A method of automatically tuning hyperparameters includes receiving a hyperparameter tuning strategy. Upon determining that one or more computing resources exceed their corresponding predetermined quota, the hyperparameter tuning strategy is rejected. Upon determining that the one or more computing resources do not exceed their corresponding predetermined quota, a machine learning model training is run with a hyperparameter point. Upon determining that one or more predetermined computing resource usage limits are exceeded for the hyperparameter point, the running of the machine learning model training is terminated for the hyperparameter point and the process returns to running the machine learning model training with a new hyperparameter point. Upon determining that training the machine learning model is complete, training results are collected and computing resource utilization metrics are determined.

Abstract: An example system includes a processor to receive historical data, a formal quality measure, a quality threshold, and a mathematical optimization model. At least part of the mathematical optimization model is generated from the historical data. The processor can measure a quality of the mathematical optimization model using the formal quality measure. The processor can then augment the mathematical optimization model such that the measured quality of the augmented mathematical optimization model exceeds the target quality threshold.

Abstract: Systems, computer-implemented methods, and computer program products to facilitate modeling bi-directional effects between events and system variables are provided. According to an embodiment, a system can comprise a processor that executes components stored in memory. The computer executable components comprise a machine learning component that learns mutual dependencies jointly over event occurrence data and transition data, wherein the transition data comprises state variable transitions observed over a multivariate state variable set.

Abstract: A computer implemented method of modeling agent interactions, includes receiving event occurrence data. One or more parent-event types and one or more corresponding child-event types are learned from the event occurrence data. A timeline of the one or more parent-event types and one or more corresponding child-event types is modeled from the event occurrence data. Agent interactions are predicted based on an order of the parent-event types in a predetermined history window.

Abstract: Triggering a prioritized alert and provisioning an action may include receiving historical data associated with a set of projects, the historical data spanning multiple consecutive time periods. A hierarchical data structure is generated that includes occurrences of performance factors in the historical data. Based on the hierarchical data structure, Bayesian scores associated with the performance factors are derived, the Bayesian scores representing likelihood of the performance factors occurring in a given project. The performance factors are ranked based on the Bayesian scores. Based on ranking, an alert and an action may be automatically triggered.