# InfoCNF: An Efficient Conditional Continuous Normalizing Flow with Adaptive Solvers

arXiv: https://arxiv.org/abs/1912.03978 · HTML: https://mlsanity.com/paper/1912.03978/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Dec 2019.

## Built on by (most cited first, 6 of 6)

- [Second-Order Neural ODE Optimizer](https://mlsanity.com/paper/2109.14158/) (2021)
- [Reinforcement Learning for Generative AI: A Survey](https://mlsanity.com/paper/2308.14328/) (2023)
- [TO-FLOW: Efficient Continuous Normalizing Flows with Temporal Optimization adjoint with Moving Speed](https://mlsanity.com/paper/2203.10335/) (2022)
- [Learning Subgrid-scale Models with Neural Ordinary Differential Equations](https://mlsanity.com/paper/2212.09967/) (2022)
- [Viscos Flows: Variational Schur Conditional Sampling With Normalizing Flows](https://mlsanity.com/paper/2107.02474/) (2021)
- [On Tuning Neural ODE for Stability, Consistency and Faster Convergence](https://mlsanity.com/paper/2312.01657/) (2023)

## Abstract (arXiv)

Continuous Normalizing Flows (CNFs) have emerged as promising deep generative models for a wide range of tasks thanks to their invertibility and exact likelihood estimation. However, conditioning CNFs on signals of interest for conditional image generation and downstream predictive tasks is inefficient due to the high-dimensional latent code generated by the model, which needs to be of the same size as the input data. In this paper, we propose InfoCNF, an efficient conditional CNF that partitions the latent space into a class-specific supervised code and an unsupervised code that shared among all classes for efficient use of labeled information. Since the partitioning strategy (slightly) increases the number of function evaluations (NFEs), InfoCNF also employs gating networks to learn the error tolerances of its ordinary differential equation (ODE) solvers for better speed and performance. We show empirically that InfoCNF improves the test accuracy over the baseline while yielding comparable likelihood scores and reducing the NFEs on CIFAR10. Furthermore, applying the same partitioning strategy in InfoCNF on time-series data helps improve extrapolation performance.