Open access
Date
2024-03-06Type
- Other Conference Item
ETH Bibliography
no
Altmetrics
Abstract
We propose a game-theoretic formulation for learn ing dimensionality-reducing representations of feature vectors, when a prior knowledge on future prediction tasks is available. We analytically find the value of the game and optimal mixed (randomized) strategies for the case of linear representations, tasks, and the mean squared error loss, and propose an algorithm for general classes of representations, tasks, and loss functions. Show more
Permanent link
https://doi.org/10.3929/ethz-b-000664555Publication status
publishedBook title
International Zurich Seminar on Information and Communication (IZS 2024). ProceedingsPages / Article No.
Publisher
ETH ZurichEvent
Organisational unit
02140 - Dep. Inf.technologie und Elektrotechnik / Dep. of Inform.Technol. Electrical Eng.
Related publications and datasets
Is part of: https://doi.org/10.3929/ethz-b-000664209
Notes
Extended abstractMore
Show all metadata
ETH Bibliography
no
Altmetrics