# Adaptive Inference: Theoretical Limits and Unexplored Opportunities

arXiv: https://arxiv.org/abs/2402.04359 · HTML: https://mlsanity.com/paper/2402.04359/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 28 references that are in the map.
- First posted on arXiv 6 Feb 2024.

## Builds on (most cited first, 19 of 19)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling](https://mlsanity.com/paper/2304.01373/) (2023)
- [Dynamic Neural Networks: A Survey](https://mlsanity.com/paper/2102.04906/) (2021)
- [From Words to Watts: Benchmarking the Energy Costs of Large Language Model Inference](https://mlsanity.com/paper/2310.03003/) (2023)
- [Carbontracker: Tracking and Predicting the Carbon Footprint of Training Deep Learning Models](https://mlsanity.com/paper/2007.03051/) (2020)
- [Edge AI: On-Demand Accelerating Deep Neural Network Inference via Edge Computing](https://mlsanity.com/paper/1910.05316/) (2019)
- [Resolution Adaptive Networks for Efficient Inference](https://mlsanity.com/paper/2003.07326/) (2020)
- [AR-Net: Adaptive Frame Resolution for Efficient Action Recognition](https://mlsanity.com/paper/2007.15796/) (2020)
- [Adaptive Inference through Early-Exit Networks: Design, Challenges and Directions](https://mlsanity.com/paper/2106.05022/) (2021)
- [A Survey on Model Compression and Acceleration for Pretrained Language Models](https://mlsanity.com/paper/2202.07105/) (2022)
- [Great Power, Great Responsibility: Recommendations for Reducing Energy for Training Language Models](https://mlsanity.com/paper/2205.09646/) (2022)
- [Adaptive Gating in Mixture-of-Experts based Language Models](https://mlsanity.com/paper/2310.07188/) (2023)
- [AutoMoE: Heterogeneous Mixture-of-Experts with Adaptive Computation for Efficient Neural Machine Translation](https://mlsanity.com/paper/2210.07535/) (2022)
- [Finding the SWEET Spot: Analysis and Improvement of Adaptive Inference in Low Resource Settings](https://mlsanity.com/paper/2306.02307/) (2023)
- [Retrospective: EIE: Efficient Inference Engine on Sparse and Compressed Neural Network](https://mlsanity.com/paper/2306.09552/) (2023)

## Abstract (arXiv)

This paper introduces the first theoretical framework for quantifying the efficiency and performance gain opportunity size of adaptive inference algorithms. We provide new approximate and exact bounds for the achievable efficiency and performance gains, supported by empirical evidence demonstrating the potential for 10-100x efficiency improvements in both Computer Vision and Natural Language Processing tasks without incurring any performance penalties. Additionally, we offer insights on improving achievable efficiency gains through the optimal selection and design of adaptive inference state spaces.