paper-with-me

Papers

Learning Randomly Perturbed Structured Predictors for Direct Loss Minimization

2020-07-11 · Hedda Cohen Indelman, Tamir Hazan

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.

📄 PDF Abstract BibTeX arXiv:2007.05724

Code (1)

HeddaCohenIndelman/PerturbedStructuredPredictorsDirect 공식 구현 pytorch

Tasks

PredictionStructured Prediction

Similar Papers 제목 키워드 기반

Learning Maximum-A-Posteriori Perturbation Models for Structured Prediction in Polynomial Time

2018-05-21 · ICML 2018 7 · Asish Ghoshal, Jean Honorio

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 Prediction

Exploration via linearly perturbed loss minimisation

2023-11-13 · David Janz, Shuai Liu, Alex Ayoub, Csaba Szepesvári

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 Sampling

PConv: Simple yet Effective Convolutional Layer for Generative Adversarial Network

2021-01-19 · Seung Park, Yoon-Jae Yeo, Yong-Goo Shin

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 NetworkMemorization

DeeSCo: Deep heterogeneous ensemble with Stochastic Combinatory loss for gaze estimation

2020-04-15 · Edouard Yvinec, Arnaud Dapogny, Kévin Bailly

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 Estimation

Semi-supervised learning of local structured output predictors

2016-04-11 · Xin Du

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