Learning Randomly Perturbed Structured Predictors for Direct Loss Minimization
Direct loss minimization is a popular approach for learning predictors over structured label spaces. This approach is computationally appealing as it replaces integration with optimization and allows to propagate gradients in a deep net using loss-perturbed prediction. Recently, this technique was extended to generative models, while introducing a randomized predictor that samples a structure from a randomly perturbed score function. In this work, we learn the variance of these randomized structured predictors and show that it balances better between the learned score function and the randomized noise in structured prediction. We demonstrate empirically the effectiveness of learning the balance between the signal and the random noise in structured discrete spaces.
Code (1)
Tasks
PredictionStructured PredictionSimilar Papers 제목 키워드 기반
Learning Maximum-A-Posteriori Perturbation Models for Structured Prediction in Polynomial Time
MAP perturbation models have emerged as a powerful framework for inference in structured prediction. Such models provide a way to efficiently sample from the Gibbs distribution and facilitate predictions that are robust …
Structured PredictionExploration via linearly perturbed loss minimisation
We introduce exploration via linear loss perturbations (EVILL), a randomised exploration method for structured stochastic bandit problems that works by solving for the minimiser of a linearly perturbed regularised negati…
Thompson SamplingPConv: Simple yet Effective Convolutional Layer for Generative Adversarial Network
This paper presents a novel convolutional layer, called perturbed convolution (PConv), which focuses on achieving two goals simultaneously: improving the generative adversarial network (GAN) performance and alleviating t…
Generative Adversarial NetworkMemorizationDeeSCo: Deep heterogeneous ensemble with Stochastic Combinatory loss for gaze estimation
From medical research to gaming applications, gaze estimation is becoming a valuable tool. While there exists a number of hardware-based solutions, recent deep learning-based approaches, coupled with the availability of …
Gaze EstimationSemi-supervised learning of local structured output predictors
In this paper, we study the problem of semi-supervised structured output prediction, which aims to learn predictors for structured outputs, such as sequences, tree nodes, vectors, etc., from a set of data points of both …
SentenceStructured Prediction