# Variational Walkback: Learning a Transition Operator as a Stochastic Recurrent Net

arXiv: https://arxiv.org/abs/1711.02282 · HTML: https://mlsanity.com/paper/1711.02282/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Nov 2017.

## Built on by (most cited first, 30 of 30)

- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [Structured Denoising Diffusion Models in Discrete State-Spaces](https://mlsanity.com/paper/2107.03006/) (2021)
- [DiffWave: A Versatile Diffusion Model for Audio Synthesis](https://mlsanity.com/paper/2009.09761/) (2020)
- [Diffusion Models: A Comprehensive Survey of Methods and Applications](https://mlsanity.com/paper/2209.00796/) (2022)
- [Tackling the Generative Learning Trilemma with Denoising Diffusion GANs](https://mlsanity.com/paper/2112.07804/) (2021)
- [A Continuous Time Framework for Discrete Denoising Models](https://mlsanity.com/paper/2205.14987/) (2022)
- [Aligning Text-to-Image Diffusion Models with Reward Backpropagation](https://mlsanity.com/paper/2310.03739/) (2023)
- [A Survey on Generative Diffusion Model](https://mlsanity.com/paper/2209.02646/) (2022)
- [Score-Based Generative Modeling with Critically-Damped Langevin Diffusion](https://mlsanity.com/paper/2112.07068/) (2021)
- [A Variational Perspective on Diffusion-Based Generative Models and Score Matching](https://mlsanity.com/paper/2106.02808/) (2021)
- [On Fast Sampling of Diffusion Probabilistic Models](https://mlsanity.com/paper/2106.00132/) (2021)
- [Annealed Flow Transport Monte Carlo](https://mlsanity.com/paper/2102.07501/) (2021)
- [Truncated Diffusion Probabilistic Models and Diffusion-based Adversarial Auto-Encoders](https://mlsanity.com/paper/2202.09671/) (2022)
- [Monte Carlo Variational Auto-Encoders](https://mlsanity.com/paper/2106.15921/) (2021)
- [Learning to Generate 3D Shapes with Generative Cellular Automata](https://mlsanity.com/paper/2103.04130/) (2021)
- [Posterior samples of source galaxies in strong gravitational lenses with score-based priors](https://mlsanity.com/paper/2211.03812/) (2022)
- [Fast Sampling via Discrete Non-Markov Diffusion Models with Predetermined Transition Time](https://mlsanity.com/paper/2312.09193/) (2023)
- [EGC: Image Generation and Classification via a Diffusion Energy-Based Model](https://mlsanity.com/paper/2304.02012/) (2023)
- [Traditional Classification Neural Networks are Good Generators: They are Competitive with DDPMs and GANs](https://mlsanity.com/paper/2211.14794/) (2022)
- [VocBench: A Neural Vocoder Benchmark for Speech Synthesis](https://mlsanity.com/paper/2112.03099/) (2021)
- [Generative Diffusion From An Action Principle](https://mlsanity.com/paper/2310.04490/) (2023)
- [Policy Gradient With Serial Markov Chain Reasoning](https://mlsanity.com/paper/2210.06766/) (2022)
- [Forward-Free Diffusion Language Models with BPTT-Free Looped Refinement](https://mlsanity.com/paper/2606.08357/) (2026)
- [Signature and Log-signature for the Study of Empirical Distributions Generated with GANs](https://mlsanity.com/paper/2203.03226/) (2022)
- [Learning Stationary Markov Processes with Contrastive Adjustment](https://mlsanity.com/paper/2303.05497/) (2023)
- [Audio is all in one: speech-driven gesture synthetics using WavLM pre-trained model](https://mlsanity.com/paper/2308.05995/) (2023)
- [Combinatorial Complex Score-based Diffusion Modelling through Stochastic Differential Equations](https://mlsanity.com/paper/2406.04916/) (2024)
- [Quasi Monte Carlo methods enable extremely low-dimensional deep generative models](https://mlsanity.com/paper/2601.18676/) (2026)

## Abstract (arXiv)

We propose a novel method to directly learn a stochastic transition operator whose repeated application provides generated samples. Traditional undirected graphical models approach this problem indirectly by learning a Markov chain model whose stationary distribution obeys detailed balance with respect to a parameterized energy function. The energy function is then modified so the model and data distributions match, with no guarantee on the number of steps required for the Markov chain to converge. Moreover, the detailed balance condition is highly restrictive: energy based models corresponding to neural networks must have symmetric weights, unlike biological neural circuits. In contrast, we develop a method for directly learning arbitrarily parameterized transition operators capable of expressing non-equilibrium stationary distributions that violate detailed balance, thereby enabling us to learn more biologically plausible asymmetric neural networks and more general non-energy based dynamical systems. The proposed training objective, which we derive via principled variational methods, encourages the transition operator to "walk back" in multi-step trajectories that start at data-points, as quickly as possible back to the original data points. We present a series of experimental results illustrating the soundness of the proposed approach, Variational Walkback (VW), on the MNIST, CIFAR-10, SVHN and CelebA datasets, demonstrating superior samples compared to earlier attempts to learn a transition operator. We also show that although each rapid training trajectory is limited to a finite but variable number of steps, our transition operator continues to generate good samples well past the length of such trajectories, thereby demonstrating the match of its non-equilibrium stationary distribution to the data distribution. Source Code: http://github.com/anirudh9119/walkback_nips17