---
title: "Generative Adversarial Nets"
description: "Generative Adversarial Nets asks how a model can learn to create convincing new samples without an explicit likelihood or a Markov chain. Read it to see how a generator and discriminator turn that problem into a two-player game, why the ideal judge eventually answers one half, and why the elegant equilibrium does not make practical training automatically stable."
canonical_url: "https://fanout.sh/daily/2026-08-29-generative-adversarial-nets"
md_url: "https://fanout.sh/daily/2026-08-29-generative-adversarial-nets.md"
last_updated: "2026-08-29"
access: "public"
---

# Generative Adversarial Nets

Generative Adversarial Nets asks how a model can learn to create convincing new samples without an explicit likelihood or a Markov chain. Read it to see how a generator and discriminator turn that problem into a two-player game, why the ideal judge eventually answers one half, and why the elegant equilibrium does not make practical training automatically stable.

## Paper details

- Authors: Goodfellow, Pouget-Abadie, Mirza, Xu, Warde-Farley, Ozair, Courville, and Bengio

- Venue: NeurIPS 2014

- Track: AI Research

- Difficulty: Easy

- Reading time: 35 min

- Original paper: https://proceedings.neurips.cc/paper_files/paper/2014/file/f033ed80deb0234979a61f95710dbe25-Paper.pdf

## What you will learn

- How a generator maps noise into samples while a discriminator learns to separate generated examples from real data and sends a useful gradient back.

- Why the minimax objective reaches its ideal distribution-space optimum when generated and real distributions match and the best discriminator returns one half.

- Why alternating updates, the non-saturating generator loss, synchronization, implicit density, discrete data, collapse, and limited evaluation keep the theorem separate from practical training.

## Continue exploring

[Explore GANs in Fanout](https://fanout.sh/knowledge-graph?node=ai-research%3Aconcept%3Agan): Connect the original generator-discriminator game to Fanout's GAN glossary node, generative models, latent variables, backpropagation, and later adversarial objectives.

---
This representation contains public Fanout content only. Protected Pro lessons, account data, billing, checkout, and pricing are not included.

Browse the public content map: https://fanout.sh/sitemap.md