Abstract: Extractive schema linking includes generating a tokenized schema from an SQL schema, a tokenized natural language question, and tokenized candidates. The tokenized candidates are generated by tokenizing candidates from the SQL schema. Each tokenized candidate is formed by a string of tokens having a first token representing an initial delimiter and a last token representing an end delimiter. Vectorial representations of the tokenized schema, the tokenized natural language question, and tokenized candidates are generated, and transformed vectorial representations generated by processing the vectorial representations through a decoder-only model. Concatenated vectors are generated from the transformed vectorial representations of the tokenized candidates, the concatenated vectors generated by concatenating a first transformed vectorial representation corresponding to the first token with a last transformed vectorial representation corresponding to the last token of each tokenized candidate.

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 computer-implemented method, a computer program product, and a computer system for tuning large language models. A computer receives pairs of textual prompts and ground truth labels. A computer creates a data selection scoring function, by repurposing one or more reward functions to compute similarity between the textual prompts and the ground truth labels, where the one or more reward functions measure similarity between textual outputs produced by a large language model and the ground truth labels. A computer selects a training dataset from the pairs of the textual prompts and the ground truth labels, by using the data selection scoring function. A computer tunes the large language model using the training dataset and reinforcement learning with the one or more reward functions.

Abstract: A method, computer program product, and computer system for developing a fine-tuned generative model (GM) that receives metadata and multiple choices as input and is configured to select a best choice, from the multiple choices, for describing the metadata. The GM is a neural network of interconnected nodes with each node having an associated weight. Developing the fine-tuned GM includes: (i) generating training data as input for training a pre-trained GM to become the fine-tuned GM, the training data including P input prompts; and (ii) training the pre-trained GM to become the fine-tuned GM, using reinforcement learning and using the training data as input. The training includes: performing a nested iterative process in which N input prompts are sampled randomly from the P input prompts subject to N<P, followed by iteratively using the N input prompts to dynamically update the weights for a maximum of K iterations.

Abstract: In a method for ranking machine learning (ML) pipelines for a dataset, a processor receives first performance curves predicted by a meta learner model for a plurality of ML pipelines. A processor allocates a first subset of data points from the dataset to each of the plurality of ML pipelines. A processor receives first performance scores for each of the ML pipelines for the first subset of data points. A processor updates the meta learner model using the first performance scores. A processor receives second performance curves from the meta learner model updated with the first performance scores. A processor ranks the plurality of ML pipelines based on the second performance curves.

Abstract: A method of creating a machine learning clustering meta learning model for use in solving a machine learning clustering problem includes obtaining a plurality of information related to the machine learning clustering problem, wherein the plurality of information includes classification datasets, machine learning transformers and clustering estimators, creating a set of clustering datasets using the classification datasets, generating trained clustering pipelines by training the set of unsupervised clustering pipelines responsive to the clustering datasets, processing the trained clustering pipelines to generate internal scores and external scores for the set of clustering datasets, creating an encoded clustering pipeline by encoding the trained clustering pipeline using the external score as a label and generating a trained supervised machine learning model by combining the internal scores and the encoded clustering pipelines.

Abstract: A computer-implemented method, a computer program product, and a computer system for tuning large language models. A computer receives pairs of textual prompts and ground truth labels. A computer creates a data selection scoring function, by repurposing one or more reward functions to compute similarity between the textual prompts and the ground truth labels, where the one or more reward functions measure similarity between textual outputs produced by a large language model and the ground truth labels. A computer selects a training dataset from the pairs of the textual prompts and the ground truth labels, by using the data selection scoring function. A computer tunes the large language model using the training dataset and reinforcement learning with the one or more reward functions.

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 a computer system including a memory communicatively coupled to a processor system. The processor system is operable to perform processor system operations that include using a first machine learning (ML) algorithm to convert to-be-classified-data (TBC-data) from a TBC-data format to a second data format; and extract features from the TBC-data in the second data format. A second ML algorithm is used to perform a task that includes determining, based at least in part on the features of the TBC-data in the second data format, that the TBC-data having the second data format is an outlier.

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: 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 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: To automate time series forecasting machine learning pipeline generation, a data allocation size of time series data may be determined based on one or more characteristics of a time series data set. The time series data may be allocated for use by candidate machine learning pipelines based on the data allocation size. Features for the time series data may be determined and cached by the candidate machine learning pipelines. Predictions of each of the candidate machine learning pipelines using at least the one or more features may be evaluated. A ranked list of machine learning pipelines may be automatically generated from the candidate machine learning pipelines for time series forecasting based upon evaluating predictions of each of the one or more candidate machine learning pipelines.

Abstract: Computer hardware and/or software that performs the following operations: (i) assessing a performance of a plurality of unsupervised machine learning pipelines against a plurality of data sets; (ii) associating the performance with meta-features corresponding to respective pipeline/data set combinations; (iii) training a supervised meta-learning model using the associated performance and meta-features as training data; and (iv) utilizing the trained model to identify one or more pipelines for processing an input data set.

Abstract: A method, a structure, and a computer system for predicting pipeline training requirements. The exemplary embodiments may include receiving one or more worker node features from one or more worker nodes, extracting one or more pipeline features from one or more pipelines to be trained, and extracting one or more dataset features from one or more datasets used to train the one or more pipelines. The exemplary embodiments may further include predicting an amount of one or more resources required for each of the one or more worker nodes to train the one or more pipelines using the one or more datasets based on one or more models that correlate the one or more worker node features, one or more pipeline features, and one or more dataset features with the one or more resources. Lastly, the exemplary embodiments may include identifying a worker node requiring a least amount of the one or more resources of the one or more worker nodes for training the one or more pipelines.

Abstract: Predefined pipelines may be created with predefined meta-features. Time series data may be segmented using lookback window parameters. Meta-features may be determined for windowed data. Those of the predefined pipelines having a maximum amount of matching predefined meta-features may be determined. Those of the lookback window parameters that result in the windowed data having the meta-features most similar to the meta-features of one or more of the plurality of predefined pipelines may be identified.

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: Computer hardware and/or software that performs the following operations: (i) assessing a performance of a plurality of unsupervised machine learning pipelines against a plurality of data sets; (ii) associating the performance with meta-features corresponding to respective pipeline/data set combinations; (iii) training a supervised meta-learning model using the associated performance and meta-features as training data; and (iv) utilizing the trained model to identify one or more pipelines for processing an input data set.