• Corpus ID: 252846366

Adversarial random forests for density estimation and generative modeling

  title={Adversarial random forests for density estimation and generative modeling},
  author={David Watson and Kristin Blesch and Jan Kapar and Marvin N. Wright},
We propose methods for density estimation and data synthesis using a novel form of unsupervised random forests. Inspired by generative adversarial networks, we implement a recursive procedure in which trees gradually learn structural properties of the data through alternating rounds of generation and discrimination. The method is provably consistent under minimal assumptions. Unlike classic tree-based alternatives, our approach provides smooth (un)conditional densities and allows for fully… 

Figures and Tables from this paper



Joints in Random Forests

It is demonstrated that DTs and RFs can naturally be interpreted as generative models, by drawing a connection to Probabilistic Circuits, a prominent class of tractable probabilistic models and leading to Generative Decision Trees (GeDTs) and Generative Forests (GeFs), a family of novel hybrid generative-discriminative models.

Modeling Tabular data using Conditional GAN

TGAN, which uses a conditional generative adversarial network to address challenges of modeling the probability distribution of rows in tabular data, outperforms Bayesian methods on most of the real datasets whereas other deep learning methods could not.

Density Estimation for Statistics and Data Analysis

The Kernel Method for Multivariate Data: Three Important Methods and Density Estimation in Action.

Continuous Mixtures of Tractable Probabilistic Models

This paper investigates a hybrid approach, namely continuous mixtures of tractable models with a small latent dimension, which proves remarkably effective, as PCs learned this way set new state-of-the-art for tractable model on many standard density estimation benchmarks.

Hierarchical Text-Conditional Image Generation with CLIP Latents

This work proposes a two-stage model: a prior that generates a CLIP image embedding given a text caption, and a decoder that generates an image conditioned on the imageembedding, and shows that explicitly generating image representations improves image diversity with minimal loss in photorealism and caption similarity.

Predictive Distribution Modeling Using Transformation Forests

A novel approach based on a parametric family of distributions characterized by their transformation function is proposed, which introduces “transformation forests” as an adaptive local likelihood estimator of conditional distribution functions.

Distributional Random Forests: Heterogeneity Adjustment and Multivariate Distributional Regression

We propose an adaptation of the Random Forest algorithm to estimate the conditional distribution of a possibly multivariate response. We suggest a new splitting criterion based on the MMD two-sample

How good is my GAN?

This paper introduces two measures based on image classification—GAN-train and GAN-test, which approximate the recall (diversity) and precision (quality of the image) of GANs respectively and evaluates a number of recent GAN approaches based on these two measures and demonstrates a clear difference in performance.

A Classification-Based Study of Covariate Shift in GAN Distributions

A basic, and still largely unanswered, question in the context of Generative Adversarial Networks (GANs) is whether they are truly able to capture all the fundamental characteristics of the