# The Extreme Value Machine

arXiv: https://arxiv.org/abs/1506.06112 · HTML: https://mlsanity.com/paper/1506.06112/

## Key facts

- Cited by 78 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Jun 2015.

## Built on by (most cited first, 30 of 78)

- [Generalized Out-of-Distribution Detection: A Survey](https://mlsanity.com/paper/2110.11334/) (2021)
- [Open-World Semi-Supervised Learning](https://mlsanity.com/paper/2102.03526/) (2021)
- [Adversarial Reciprocal Points Learning for Open Set Recognition](https://mlsanity.com/paper/2103.00953/) (2021)
- [FeTrIL: Feature Translation for Exemplar-Free Class-Incremental Learning](https://mlsanity.com/paper/2211.13131/) (2022)
- [Towards Discovery and Attribution of Open-world GAN Generated Images](https://mlsanity.com/paper/2105.04580/) (2021)
- [Learning Bounds for Open-Set Learning](https://mlsanity.com/paper/2106.15792/) (2021)
- [Open Set Action Recognition via Multi-Label Evidential Learning](https://mlsanity.com/paper/2303.12698/) (2023)
- [A Survey on Open Set Recognition](https://mlsanity.com/paper/2109.00893/) (2021)
- [vCache: Verified Semantic Prompt Caching](https://mlsanity.com/paper/2502.03771/) (2025)
- [CNS-Net: Conservative Novelty Synthesizing Network for Malware Recognition in an Open-set Scenario](https://mlsanity.com/paper/2305.01236/) (2023)
- [Deep Learning and Traffic Classification: Lessons learned from a commercial-grade dataset with hundreds of encrypted and zero-day applications](https://mlsanity.com/paper/2104.03182/) (2021)
- [Open World Object Detection: A Survey](https://mlsanity.com/paper/2410.11301/) (2024)
- [Towards Visual Semantics](https://mlsanity.com/paper/2104.12379/) (2021)
- [Regression modelling of spatiotemporal extreme U.S. wildfires via partially-interpretable neural networks](https://mlsanity.com/paper/2208.07581/) (2022)
- [Collective Decision of One-vs-Rest Networks for Open Set Recognition](https://mlsanity.com/paper/2103.10230/) (2021)
- [Towards Accurate Open-Set Recognition via Background-Class Regularization](https://mlsanity.com/paper/2207.10287/) (2022)
- [Glocal Energy-based Learning for Few-Shot Open-Set Recognition](https://mlsanity.com/paper/2304.11855/) (2023)
- [MDENet: Multi-modal Dual-embedding Networks for Malware Open-set Recognition](https://mlsanity.com/paper/2305.01245/) (2023)
- [A VAE Approach to Sample Multivariate Extremes](https://mlsanity.com/paper/2306.10987/) (2023)
- [Self-Supervised Features Improve Open-World Learning](https://mlsanity.com/paper/2102.07848/) (2021)
- [Bayesian Embeddings for Few-Shot Open World Recognition](https://mlsanity.com/paper/2107.13682/) (2021)
- [Measuring Human Perception to Improve Open Set Recognition](https://mlsanity.com/paper/2209.03519/) (2022)
- [Large-Scale Open-Set Classification Protocols for ImageNet](https://mlsanity.com/paper/2210.06789/) (2022)
- [AI, Meet Human: Learning Paradigms for Hybrid Decision Making Systems](https://mlsanity.com/paper/2402.06287/) (2024)
- [WOT-Class: Weakly Supervised Open-world Text Classification](https://mlsanity.com/paper/2305.12401/) (2023)
- [Deep Compact Polyhedral Conic Classifier for Open and Closed Set Recognition](https://mlsanity.com/paper/2102.12570/) (2021)
- [Evaluation of Various Open-Set Medical Imaging Tasks with Deep Neural Networks](https://mlsanity.com/paper/2110.10888/) (2021)
- [Human-in-the-loop Handling of Knowledge Drift](https://mlsanity.com/paper/2103.14874/) (2021)
- [Vocabulary-informed Zero-shot and Open-set Learning](https://mlsanity.com/paper/2301.00998/) (2023)
- [Managing the unknown: a survey on Open Set Recognition and tangential areas](https://mlsanity.com/paper/2312.08785/) (2023)

## Abstract (arXiv)

It is often desirable to be able to recognize when inputs to a recognition function learned in a supervised manner correspond to classes unseen at training time. With this ability, new class labels could be assigned to these inputs by a human operator, allowing them to be incorporated into the recognition function --- ideally under an efficient incremental update mechanism. While good algorithms that assume inputs from a fixed set of classes exist, e.g., artificial neural networks and kernel machines, it is not immediately obvious how to extend them to perform incremental learning in the presence of unknown query classes. Existing algorithms take little to no distributional information into account when learning recognition functions and lack a strong theoretical foundation. We address this gap by formulating a novel, theoretically sound classifier --- the Extreme Value Machine (EVM). The EVM has a well-grounded interpretation derived from statistical Extreme Value Theory (EVT), and is the first classifier to be able to perform nonlinear kernel-free variable bandwidth incremental learning. Compared to other classifiers in the same deep network derived feature space, the EVM is accurate and efficient on an established benchmark partition of the ImageNet dataset.