# Probabilistic Adaptive Computation Time

arXiv: https://arxiv.org/abs/1712.00386 · HTML: https://mlsanity.com/paper/1712.00386/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Dec 2017.

## Built on by (most cited first, 4 of 4)

- [Confident Adaptive Language Modeling](https://mlsanity.com/paper/2207.07061/) (2022)
- [Overthinking the Truth: Understanding how Language Models Process False Demonstrations](https://mlsanity.com/paper/2307.09476/) (2023)
- [Accelerating Inference in Large Language Models with a Unified Layer Skipping Strategy](https://mlsanity.com/paper/2404.06954/) (2024)
- [Securing Multi-turn Conversational Language Models From Distributed Backdoor Triggers](https://mlsanity.com/paper/2407.04151/) (2024)

## Abstract (arXiv)

We present a probabilistic model with discrete latent variables that control the computation time in deep learning models such as ResNets and LSTMs. A prior on the latent variables expresses the preference for faster computation. The amount of computation for an input is determined via amortized maximum a posteriori (MAP) inference. MAP inference is performed using a novel stochastic variational optimization method. The recently proposed Adaptive Computation Time mechanism can be seen as an ad-hoc relaxation of this model. We demonstrate training using the general-purpose Concrete relaxation of discrete variables. Evaluation on ResNet shows that our method matches the speed-accuracy trade-off of Adaptive Computation Time, while allowing for evaluation with a simple deterministic procedure that has a lower memory footprint.