paper-with-me

홈 › Papers

Adversarial Regression. Generative Adversarial Networks for Non-Linear Regression: Theory and Assessment

2019-10-18 · Yoann Boget

Adversarial Regression is a proposition to perform high dimensional non-linear regression with uncertainty estimation. We used Conditional Generative Adversarial Network to obtain an estimate of the full predictive distribution for a new observation. Generative Adversarial Networks (GAN) are implicit generative models which produce samples from a distribution approximating the distribution of the data. The conditional version of it (CGAN) takes the following expression: $\min\limits_G \max\limits_D V(D, G) = \mathbb{E}_{x\sim p_{r}(x)} [log(D(x, y))] + \mathbb{E}_{z\sim p_{z}(z)} [log (1-D(G(z, y)))]$. An approximate solution can be found by training simultaneously two neural networks to model D and G and feeding G with a random noise vector $z$. After training, we have that $G(z, y)\mathrel{\dot\sim} p_{data}(x, y)$. By fixing $y$, we have $G(z|y) \mathrel{\dot\sim} p{data}(x|y)$. By sampling $z$, we can therefore obtain samples following approximately $p(x|y)$, which is the predictive distribution of $x$ for a new $y$. We ran experiments to test various loss functions, data distributions, sample size, size of the noise vector, etc. Even if we observed differences, no experiment outperformed consistently the others. The quality of CGAN for regression relies on fine-tuning a range of hyperparameters. In a broader view, the results show that CGANs are very promising methods to perform uncertainty estimation for high dimensional non-linear regression.

📄 PDF Abstract BibTeX arXiv:1910.09106

Code (1)

yoboget/AdversarialRegression pytorch

Tasks

Generative Adversarial Networkregression

Methods 이 논문이 사용한 방법론

Test 설명 없음

Similar Papers 제목 키워드 기반

Surprises in adversarially-trained linear regression

2022-05-25 · Antônio H. Ribeiro, Dave Zachariah, Thomas B. Schön

State-of-the-art machine learning models can be vulnerable to very small input perturbations that are adversarially constructed. Adversarial training is an effective approach to defend against such examples. It is formul…

regression

Adversarial Orthogonal Regression: Two non-Linear Regressions for Causal Inference

2019-09-10 · M. Reza Heydari, Saber Salehkaleybar, Kun Zhang

We propose two nonlinear regression methods, named Adversarial Orthogonal Regression (AdOR) for additive noise models and Adversarial Orthogonal Structural Equation Model (AdOSE) for the general case of structural equati…

Causal InferenceregressionVocal Bursts Valence Prediction

Diffusing States and Matching Scores: A New Framework for Imitation Learning

2024-10-17 · Runzhe Wu, Yiding Chen, Gokul Swamy, Kianté Brantley 외

Adversarial Imitation Learning is traditionally framed as a two-player zero-sum game between a learner and an adversarially chosen cost function, and can therefore be thought of as the sequential generalization of a Gene…

continuous-controlContinuous ControlGenerative Adversarial NetworkImitation Learning+1

Adversarial Training Makes Weight Loss Landscape Sharper in Logistic Regression

2021-02-05 · Masanori Yamada, Sekitoshi Kanai, Tomoharu Iwata, Tomokatsu Takahashi 외

Adversarial training is actively studied for learning robust models against adversarial examples. A recent study finds that adversarially trained models degenerate generalization performance on adversarial examples when …

regression

Regularization properties of adversarially-trained linear regression

2023-10-16 · NeurIPS 2023 11 · Antônio H. Ribeiro, Dave Zachariah, Francis Bach, Thomas B. Schön

State-of-the-art machine learning models can be vulnerable to very small input perturbations that are adversarially constructed. Adversarial training is an effective approach to defend against it. Formulated as a min-max…

regression