Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for performing a multi-modal machine learning task using a neural network. In one aspect, a method comprises, receiving a request to perform a machine learning task on an input tuple comprising a first network input in a first modality and a second network input in a second modality; processing the first network input to generate a first embedded sequence; processing the second network input to generate a second embedded sequence; processing the first embedded sequence and the second embedded sequence using an attention neural network to generate an updated first embedded sequence and an updated second embedded sequence; and processing the updated first embedded sequence and the updated second embedded sequence to generate a final representation for the first network input and a final representation for the second network input.

Abstract: Hyperparameters for tuning a machine learning system may be optimized using Bayesian optimization with constraints. The hyperparameter optimization may be performed for a received training set and received constraints. Respective probabilistic models for the machine learning system and constraint functions may be initialized, then hyperparameter optimization may include iteratively identifying respective values for hyperparameters using analysis of the respective models performed using an acquisition function implementing entropy search on the respective models, training the machine learning system using the identified values to determine measures of accuracy and constraint metrics, and updating the respective models using the determined measures.

Abstract: Hyperparameters for tuning a machine learning system may be optimized using Bayesian optimization with constraints. The hyperparameter optimization may be performed for a received training set and received constraints. Respective probabilistic models for the machine learning system and constraint functions may be initialized, then hyperparameter optimization may include iteratively identifying respective values for hyperparameters using analysis of the respective models performed using an acquisition function implementing entropy search on the respective models, training the machine learning system using the identified values to determine measures of accuracy and constraint metrics, and updating the respective models using the determined measures.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating predictions about images. One of the systems includes a neural network comprising a sequence of one or more network blocks that are each configured to perform operations comprising: obtaining a block input that represents an intermediate representation of an input image; determining a plurality of patches of the block input or of an updated representation of the block input, wherein each patch comprises a different subset of elements of the block input or of the updated representation of the block input; assigning each patch to one or more respective expert modules of a plurality of expert modules of the network block; for each patch of the plurality of patches, processing the patch using the corresponding expert modules to generate respective module outputs; and generating a block output by combining the module outputs.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating an ensemble of neural networks. In particular, the neural networks in the ensemble are trained using different hyperparameters from one another.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for performing a machine learning task on a network input to generate a network output. In one aspect, one of the systems includes a neural network configured to perform the machine learning task, the neural network including one or more expert neural network blocks that each include multiple routers and multiple expert neural networks.

Abstract: Techniques for tuning a machine learning algorithm using automatically determined optimal hyperparameters are described. An exemplary method includes receiving a request to determine a search space for at least one hyperparameter of a machine learning algorithm; determining, according to the request, optimal hyperparameter values from the search space for at least the one hyperparameter of the machine learning algorithm based on an evaluation of hyperparameters from the same machine learning algorithm on different datasets; and tuning the machine learning algorithm using the determined optimal hyperparameter values for the at least one hyperparameter of the machine learning algorithm to generate a machine learning model.

Abstract: Systems, methods, and computer-readable media are disclosed for maximizing quantifiable user interaction via modification of adjustable parameters. In one embodiment, an example method may include determining a first output to maximize, where the first output is a function of a first adjustable parameter and a second adjustable parameter, determining first data comprising a first actual value of the first output when the first adjustable parameter is set to a first value and the second adjustable parameter is set to a second value, and determining a first predictive model that generates a first predicted value of the first output. Example methods may include determining, using the first predictive model, a third value for the first adjustable parameter and a fourth value for the second adjustable parameter to maximize the first predicted value, and sending the third value and the fourth value.

Abstract: An optimizer for a software execution environment determines an objective function and permitted settings for various tunable parameters of the environment. To represent the execution environment, the optimizer generates a Bayesian optimization model employing Gaussian process priors. The optimizer implements a plurality of iterations of execution of the model, interleaved with observation collection intervals. During a given observation collection interval, tunable parameter settings suggested by the previous model execution iteration are used in the execution environment, and the observations collected during the interval are used as inputs for the next model execution iteration. When an optimization goal is attained, the tunable settings that led to achieving the goal are stored.

Abstract: A system is disclosed that identifies early adopter users by creating a directed graph of item access information for an item category and performing a page rank type process on the item access information. This directed graph may be created in a reverse temporal order. The early adopter users can be identified as the users with nodes in the directed graph that have a threshold number or rate of incoming links directly or indirectly pointing towards the nodes. Using the early adopter users as a sample, systems herein can determine whether to recommend an item based on the popularity of the item with respect to the early adopter users. Further, systems herein can determine an inventory level to maintain for an item based on the popularity of the item with respect to the early adopter users.