Abstract: Systems and methods for flexible parameter sharing for multi-task learning are provided. A training method can include obtaining a test input, selecting a particular task from one or more tasks, and training a multi-task machine-learned model for the particular task by performing a forward pass using the test input and one or more connection probability matrices to generate a sample distribution of test outputs, training the components of the machine-learned model based at least in part on the sample distribution, and performing a backwards pass to train a connection probability matrix of the multi-task machine-learned model using a straight-through Gumbel-softmax approximation.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for providing a machine learning model that is trained to perform a machine learning task. In one aspect, a method comprises receiving a request to train a machine learning model on a set of training examples; determining a set of one or more meta-data values characterizing the set of training examples; using a mapping function to map the set of meta-data values characterizing the set of training examples to data identifying a particular machine learning model architecture; selecting, using the particular machine learning model architecture, a final machine learning model architecture for performing the machine learning task; and training a machine learning model having the final machine learning model architecture on the set of training examples.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network system to perform multiple machine learning tasks.

Abstract: Systems, methods, and computer readable media related to generating query variants for a submitted query. In many implementations, the query variants are generated utilizing a generative model. A generative model is productive, in that it can be utilized to actively generate a variant of a query based on application of tokens of the query to the generative model, and optionally based on application of additional input features to the generative model.

Abstract: Systems, methods, and computer readable media related to generating query variants for a submitted query. In many implementations, the query variants are generated utilizing a generative model. A generative model is productive, in that it can be utilized to actively generate a variant of a query based on application of tokens of the query to the generative model, and optionally based on application of additional input features to the generative model.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating neural network architectures. One of the methods includes receiving a request to determine an architecture for a task neural network; maintaining data specifying a plurality of candidate architectures for the task neural network; repeatedly performing operations comprising: selecting one or more candidate architectures in the maintained data to be modified; generating a new candidate architecture from the selected candidate architecture by, for each hyperparameter in the set of hyperparameters, selecting the value for the hyperparameter for the new candidate architecture; and adding data specifying the new candidate architecture to the maintained data; and selecting, as the final architecture for the task neural network, one of the candidate architectures specified in the maintained data.

Abstract: A method of determining a final architecture for a task neural network for performing a target machine learning task is described. The target machine learning task is associated with a target training dataset.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for determining neural network architectures. One of the methods includes receiving training data for training a task neural network to perform a particular machine learning task; and selecting, from a space of possible architectures, an architecture for the task neural network, wherein the space of possible architectures is represented as a graph of nodes connected by edges, each node in the graph representing a decision point in selecting the architecture and each edge in the graph representing an action.

Abstract: Systems and methods for flexible parameter sharing for multi-task learning are provided. A training method can include obtaining a test input, selecting a particular task from one or more tasks, and training a multi-task machine-learned model for the particular task by performing a forward pass using the test input and one or more connection probability matrices to generate a sample distribution of test outputs, training the components of the machine-learned model based at least in part on the sample distribution, and performing a backwards pass to train a connection probability matrix of the multi-task machine-learned model using a straight-through Gumbel-softmax approximation.

Abstract: Systems, methods, and computer readable media related to generating query variants for a submitted query. In many implementations, the query variants are generated utilizing a generative model. A generative model is productive, in that it can be utilized to actively generate a variant of a query based on application of tokens of the query to the generative model, and optionally based on application of additional input features to the generative model.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating neural network architectures. One of the methods includes receiving a request to determine an architecture for a task neural network; maintaining data specifying a plurality of candidate architectures for the task neural network; repeatedly performing operations comprising: selecting one or more candidate architectures in the maintained data to be modified; generating a new candidate architecture from the selected candidate architecture by, for each hyperparameter in the set of hyperparameters, selecting the value for the hyperparameter for the new candidate architecture; and adding data specifying the new candidate architecture to the maintained data; and selecting, as the final architecture for the task neural network, one of the candidate architectures specified in the maintained data.