Learning with risks based on M-location
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.
Code (1)
Tasks
Stochastic OptimizationSimilar Papers 제목 키워드 기반
Assessing the Geolocation Capabilities, Limitations and Societal Risks of Generative Vision-Language Models
Geo-localization is the task of identifying the location of an image using visual cues alone. It has beneficial applications, such as improving disaster response, enhancing navigation, and geography education. Recently, …
"I'm not for sale" -- Perceptions and limited awareness of privacy risks by digital natives about location data
Although mobile devices benefit users in their daily lives in numerous ways, they also raise several privacy concerns. For instance, they can reveal sensitive information that can be inferred from location data. This loc…
Risk Aggregation and Allocation in the Presence of Systematic Risk via Stable Laws
In order to properly manage risk, practitioners must understand the aggregate risks they are exposed to. Additionally, to properly price policies and calculate bonuses the relative riskiness of individual business units …
On a law of large numbers for insurance risks
This note presents a kind of the strong law of large numbers for an insurance risk caused by a single catastrophic event rather than by an accumulation of independent and identically distributed risks. We derive this res…
Tracing patients' PLOD with mobile phones: Mitigation of epidemic risks through patients' locational open data
In the cases when public health authorities confirm a patient with highly contagious disease, they release the summaries about patient locations and travel information. However, due to privacy concerns, these releases do…