Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network using a priority queue. One of the methods includes maintaining data identifying a set of K output sequences that were previously generated; selecting at least one of the output sequences from the set of output sequences; for each selected output sequence, determining a respective score; determining, for each selected sequence, a respective first update to the current values of the controller parameters; generating a batch of new output sequences using the controller neural network; obtaining a respective reward for each of the new output sequences; determining, from the new output sequences and the output sequences in the maintained data, the K output sequences that have the highest rewards; and modifying the maintained data.

Abstract: According to various implementations, generally disclosed herein is a hybrid and hierarchical neural architecture search (NAS) approach. The approach includes performing a search space partitioning scheme to divide the search space into sub-search spaces. The approach further includes performing a first type of NAS, such as a Multi-trial NAS, to cover a search across the sub-search spaces. The approach also includes performing a second type of NAS, such as a One-Shot NAS, to cover each sub-search space. The approach further includes automatically stopping the second type of NAS based on one or more early stopping criteria.

Abstract: A computer-implemented method for performing computer vision with reduced computational cost and improved accuracy can include obtaining, by a computing system including one or more computing devices, input data comprising an input tensor having one or more dimensions, providing, by the computing system, the input data to a machine-learned convolutional attention network, the machine-learned convolutional attention network including two or more network stages, and, in response to providing the input data to the machine-learned convolutional attention network, receiving, by the computing system, a machine-learning prediction from the machine-learned convolutional attention network. The convolutional attention network can include at least one attention block, wherein the attention block includes a relative attention mechanism, the relative attention mechanism including the sum of a static convolution kernel with an adaptive attention matrix.

Abstract: A method for receiving training data for training a neural network (NN) to perform a machine learning (ML) task and for determining, using the training data, an optimized NN architecture for performing the ML task is described. Determining the optimized NN architecture includes: maintaining population data comprising, for each candidate architecture in a population of candidate architectures, (i) data defining the candidate architecture, and (ii) data specifying how recently a neural network having the candidate architecture has been trained while determining the optimized neural network architecture; and repeatedly performing multiple operations using each of a plurality of worker computing units to generate a new candidate architecture based on a selected candidate architecture having the best measure of fitness, adding the new candidate architecture to the population, and removing from the population the candidate architecture that was trained least recently.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for determining neural network architectures. One of the methods includes generating, using a controller neural network having controller parameters and in accordance with current values of the controller parameters, a batch of output sequences. The method includes, for each output sequence in the batch: generating an instance of a child convolutional neural network (CNN) that includes multiple instances of a first convolutional cell having an architecture defined by the output sequence; training the instance of the child CNN to perform an image processing task; and evaluating a performance of the trained instance of the child CNN on the task to determine a performance metric for the trained instance of the child CNN; and using the performance metrics for the trained instances of the child CNN to adjust current values of the controller parameters of the controller neural network.

Abstract: An example method for pretraining a machine-learned model is provided. The example method includes obtaining a plurality of different combinations of configuration parameters of a pretraining objective framework. The example method includes generating, using the pretraining objective framework, a plurality of corrupted training examples from one or more training examples, wherein the plurality of corrupted training examples are respectively generated according to the plurality of different combinations. The example method includes inputting the plurality of corrupted training examples into the machine-learned model, wherein the machine-learned model is configured to generate uncorrupted subportions corresponding to corrupted subportions of the corrupted training examples. The example method includes obtaining, from the machine-learned model, a plurality of outputs respectively generated by the machine-learned model based on the plurality of corrupted training examples.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for determining, for each of one or more categorical features, a respective vocabulary of categorical feature values of the categorical feature that should be active during processing of inputs by a machine learning model. In one aspect, a method comprises: generating a batch of output sequences, each output sequence in the batch specifying, for each of the categorical features, a respective vocabulary of categorical feature values of the categorical feature that should be active; for each output sequence in the batch, determining a performance metric of the machine learning model on a machine learning task after the machine learning model has been trained to perform the machine learning task with only the respective vocabulary of categorical feature values of each categorical feature specified by the output sequence being active.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for performing a machine learning task on an input to generate an output. In one aspect, one of the method includes receiving input data that describes an input of a machine learning task; receiving candidate output data that describes a set of candidate classification outputs of the machine learning task for the input; generating an input sequence that includes the input and the set of candidate classification outputs; processing the input sequence using a neural network to generate a network output that specifies a respective score for each candidate classification output in the set of candidate classification outputs; and generating an output of the machine learning task for the input, comprising selecting, as the output, a selected candidate classification output from the set of candidate classification outputs using the respective scores.

Abstract: A method for receiving training data for training a neural network (NN) to perform a machine learning (ML) task and for determining, using the training data, an optimized NN architecture for performing the ML task is described. Determining the optimized NN architecture includes: maintaining population data comprising, for each candidate architecture in a population of candidate architectures, (i) data defining the candidate architecture, and (ii) data specifying how recently a neural network having the candidate architecture has been trained while determining the optimized neural network architecture; and repeatedly performing multiple operations using each of a plurality of worker computing units to generate a new candidate architecture based on a selected candidate architecture having the best measure of fitness, adding the new candidate architecture to the population, and removing from the population the candidate architecture that was trained least recently.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for using memory-optimized contrastive learning to train image encoder and text encoder neural networks.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for determining neural network architectures. One of the methods includes generating, using a controller neural network having controller parameters and in accordance with current values of the controller parameters, a batch of output sequences. The method includes, for each output sequence in the batch: generating an instance of a child convolutional neural network (CNN) that includes multiple instances of a first convolutional cell having an architecture defined by the output sequence; training the instance of the child CNN to perform an image processing task; and evaluating a performance of the trained instance of the child CNN on the task to determine a performance metric for the trained instance of the child CNN; and using the performance metrics for the trained instances of the child CNN to adjust current values of the controller parameters of the controller neural network.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for determining, for each of one or more categorical features, a respective vocabulary of categorical feature values of the categorical feature that should be active during processing of inputs by a machine learning model. In one aspect, a method comprises: generating a batch of output sequences, each output sequence in the batch specifying, for each of the categorical features, a respective vocabulary of categorical feature values of the categorical feature that should be active; for each output sequence in the batch, determining a performance metric of the machine learning model on a machine learning task after the machine learning model has been trained to perform the machine learning task with only the respective vocabulary of categorical feature values of each categorical feature specified by the output sequence being active.

Abstract: A method for searching for an output machine learning (ML) algorithm to perform an ML task is described. The method comprising: receiving data specifying an input ML algorithm; receiving data specifying a search algorithm that searches for candidate ML algorithms and an evaluation function that evaluates the performance of candidate ML algorithms; generating data representing a symbolic tree from the input ML algorithm; generating data representing a hyper symbolic tree from the symbolic tree; searching an algorithm search space that defines a set of possible concrete symbolic trees from the hyper symbolic tree for candidate ML algorithms and training the candidate ML algorithms to determine a respective performance metric for each candidate ML algorithm; and selecting one or more trained candidate ML algorithms among the trained candidate ML algorithms based on the determined performance metrics.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating a computer chip placement. One of the methods includes obtaining netlist data for a computer chip; and generating a computer chip placement, comprising placing a respective macro node at each time step in a sequence comprising a plurality of time steps, the placing comprising, for each time step: generating an input representation for the time step; processing the input representation using a node placement neural network having a plurality of network parameters, wherein the node placement neural network is configured to process the input representation in accordance with current values of the network parameters to generate a score distribution over a plurality of positions on the surface of the computer chip; and assigning the macro node to be placed at the time step to a position from the plurality of positions using the score distribution.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for searching for an architecture for an activation-normalization layer to be included in a neural network to replace a set of layers that receive a layer input comprising a plurality of values, apply one or more normalization operations to the values in the layer input to generate a normalized layer input, and apply an element-wise activation function to the normalized layer input to generate a layer output.

Abstract: Aspects of the disclosure provide for hardware-aware progressive training of machine learning models. A training system trains a model in accordance with a training process and different values specified in a training schedule for both hardware-level and model-level performance settings. Hardware-level performance settings can cause hardware features of computing resources used to train the model to be enabled, disabled, or modified at various points during training. Model-level performance settings can take on a variety of values to adjust characteristics of the machine learning model being trained or of the training process, during different stages of training. The training system can identify and apply complementary values of hardware- and model-level performance settings to generate training schedules that improve model training speed at earlier stages of training, while improving model quality at later stages of training.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a machine learning model using teacher annealing.

Abstract: Systems and methods are provided that train a machine-learned language encoding model through the use of a contrastive learning task. In particular, the present disclosure describes a contrastive learning task where the encoder learns to distinguish input tokens from plausible alternatives. In some implementations, on each training example the proposed method masks out some subset (e.g., 15%) of the original input tokens, replaces the masked tokens with samples from a “generator” (e.g., which may be a small masked language model), and then trains the encoder to predict whether each token comes from the original data or is a replacement produced by the generator.

Abstract: Systems and methods of the present disclosure can include a computer-implemented method for efficient machine-learned model training. The method can include obtaining a plurality of training samples for a machine-learned model. The method can include, for one or more first training iterations, training, based at least in part on a first regularization magnitude configured to control a relative effect of one or more regularization techniques, the machine-learned model using one or more respective first training samples of the plurality of training samples. The method can include, for one or more second training iterations, training, based at least in part on a second regularization magnitude greater than the first regularization magnitude, the machine-learned model using one or more respective second training samples of the plurality of training samples.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating a computer chip placement. One of the methods includes obtaining netlist data for a computer chip; and generating a computer chip placement, comprising placing a respective macro node at each time step in a sequence comprising a plurality of time steps, the placing comprising, for each time step: generating an input representation for the time step; processing the input representation using a node placement neural network having a plurality of network parameters, wherein the node placement neural network is configured to process the input representation in accordance with current values of the network parameters to generate a score distribution over a plurality of positions on the surface of the computer chip; and assigning the macro node to be placed at the time step to a position from the plurality of positions using the score distribution.