# Learning with risks based on M-location

arXiv: https://arxiv.org/abs/2012.02424 · HTML: https://mlsanity.com/paper/2012.02424/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Dec 2020.

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

- [Spectral risk-based learning using unbounded losses](https://mlsanity.com/paper/2105.04816/) (2021)
- [A Survey of Learning Criteria Going Beyond the Usual Risk](https://mlsanity.com/paper/2110.04996/) (2021)
- [Flexible risk design using bi-directional dispersion](https://mlsanity.com/paper/2203.14434/) (2022)
- [Soft ascent-descent as a stable and flexible alternative to flooding](https://mlsanity.com/paper/2310.10006/) (2023)
- [Criterion Collapse and Loss Distribution Control](https://mlsanity.com/paper/2402.09802/) (2024)
- [Making Robust Generalizers Less Rigid with Loss Concentration](https://mlsanity.com/paper/2408.03619/) (2024)

## Abstract (arXiv)

In this work, we study a new class of risks defined in terms of the location and deviation of the loss distribution, generalizing far beyond classical mean-variance risk functions. The class is easily implemented as a wrapper around any smooth loss, it admits finite-sample stationarity guarantees for stochastic gradient methods, it is straightforward to interpret and adjust, with close links to M-estimators of the loss location, and has a salient effect on the test loss distribution.