Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for processing a network input using a trained neural network with network parameters to generate an output for a machine learning task. The training includes: receiving a set of training examples each including a training network input and a reference output; for each training iteration, generating a corrupted network input for each training network input using a corruption neural network; updating perturbation parameters of the corruption neural network using a first objective function based on the corrupted network inputs; generating an updated corrupted network input for each training network input based on the updated perturbation parameters; and generating a network output for each updated corrupted network input using the neural network; for each training example, updating the network parameters using a second objective function based on the network output and the reference output.

Abstract: Methods and systems for low-latency multi-constraint ranking of content items. One of the methods includes receiving a request to rank a plurality of content items for presentation to a user to maximize a primary objective subject to a plurality of constraints; initializing a dual variable vector; updating the dual variable vector, comprising: determining an overall objective score for the dual variable vector; identifying a plurality of candidate dual variable vectors that includes one or more neighboring node dual variable vectors; determining respective overall objective scores for each of the one or more candidate dual variable vectors; identifying the candidate with the best overall objective score; and determining whether to update the dual variable vector based on whether the identified candidate has a better overall objective score than the dual variable vector; and determining a final ranking for the content items based on the dual variable vector.

Abstract: Techniques for augmenting an appearance of a first object. Embodiments include capturing a visual scene for display. Here, the visual scene includes a physical object and wherein the visual scene is captured using one or more camera devices. The physical object is identified as a first predetermined object type, based on one or more object identifiers associated with the physical object. Embodiments also retrieve visual characteristics information corresponding to the first predetermined object type. A sequence of frames that includes the first object is then rendered for display, where the appearance the first object in the rendered sequence of frames is augmented based on the retrieved visual characteristics information and an appearance of the physical object in the captured visual scene.

Abstract: Techniques for augmenting an appearance of a first object. Embodiments include capturing a visual scene for display. Here, the visual scene includes a physical object and wherein the visual scene is captured using one or more camera devices. The physical object is identified as a first predetermined object type, based on one or more object identifiers associated with the physical object. Embodiments also retrieve visual characteristics information corresponding to the first predetermined object type. A sequence of frames that includes the first object is then rendered for display, where the appearance the first object in the rendered sequence of frames is augmented based on the retrieved visual characteristics information and an appearance of the physical object in the captured visual scene.