Abstract: Provided are systems and methods that enable computerized systems to optimize predictions of joint label probabilities of lists of items returned in response to a query. The proposed approaches take into account the effects of relational interactions among items included in the same list and can improve predictions of a deployed model for either predicting engagement rates, ranking, and/or distillation. Unlike methods that combine label engagement loss with a ranking loss, the proposed methods directly model the joint probability of the vector of labels in a list of examples included in a training dataset (e.g., by modeling conditional probabilities) instead of modeling the marginal and conditional projections of the joint probability and empirically balancing between them to infer some approximation of the joint probability. The approach gives models the ability to refine their label predictions based on the contexts of co-recommended items.

Abstract: The present disclosure provides systems and methods that learn a loss function that, when (approximately) minimized over the training data, produces a model that performs well on test data according to some error metric. The error metric need not be differentiable and may be only loosely related to the loss function. In particular, the present disclosure presents a convex-programming-based algorithm that takes as input observed data from training a small number of models and produces as output a loss function. This algorithm can be used to tune loss function hyperparameters and/or to adjust the loss function on-the-fly during training.

Abstract: The present disclosure provides systems and methods that learn a loss function that, when (approximately) minimized over the training data, produces a model that performs well on test data according to some error metric. The error metric need not be differentiable and may be only loosely related to the loss function. In particular, the present disclosure presents a convex-programming-based algorithm that takes as input observed data from training a small number of models and produces as output a loss function. This algorithm can be used to tune loss function hyperparameters and/or to adjust the loss function on-the-fly during training.

Abstract: Signal-processing devices having memristors are described for performing frequency-discrimination functions, amplitude-discrimination functions, and time-oriented functions. In each case, the time-domain behavior of the memristors described herein enables these functions to be performed. In one embodiment, memristance of an arrangement of memristors of a device is, after an initial transitional period, predominantly at a first level if frequency of an input signal of the device is less than a first frequency and predominantly at a second level if the frequency of the input signal is greater than a second frequency.

Abstract: Signal-processing devices having memristors are described for performing frequency-discrimination functions, amplitude-discrimination functions, and time-oriented functions. In each case, the time-domain behavior of the memristors described herein enables these functions to be performed. In one embodiment, memristance of an arrangement of memristors of a device is, after an initial transitional period, predominantly at a first level if frequency of an input signal of the device is less than a first frequency and predominantly at a second level if the frequency of the input signal is greater than a second frequency.

Abstract: Signal-processing devices having memristors are described for performing frequency-discrimination functions, amplitude-discrimination functions, and time-oriented functions. In each case, the time-domain behavior of the memristors described herein enables these functions to be performed. In one embodiment, memristance of an arrangement of memristors of a device is, after an initial transitional period, predominantly at a first level if frequency of an input signal of the device is less than a first frequency and predominantly at a second level if the frequency of the input signal is greater than a second frequency.

Abstract: Signal-processing devices having memristors are described for performing frequency-discrimination functions, amplitude-discrimination functions, and time-oriented functions. In each case, the time-domain behavior of the memristors described herein enables these functions to be performed. In one embodiment, memristance of an arrangement of memristors of a device is, after an initial transitional period, predominantly at a first level if frequency of an input signal of the device is less than a first frequency and predominantly at a second level if the frequency of the input signal is greater than a second frequency.