Pareto-optimal data compression for binary classification tasks
The goal of lossy data compression is to reduce the storage cost of a data set X while retaining as much information as possible about something (Y) that you care about. For example, what aspects of an image X contain the most information about whether it depicts a cat? Mathematically, this correspo...
Main Authors: | Tegmark, Max Erik, Wu, Tailin |
---|---|
Other Authors: | Massachusetts Institute of Technology. Department of Physics |
Format: | Article |
Published: |
Multidisciplinary Digital Publishing Institute
2020
|
Online Access: | https://hdl.handle.net/1721.1/125546 |
Similar Items
-
Pareto-Optimal Data Compression for Binary Classification Tasks
by: Tegmark, Max Erik, et al.
Published: (2021) -
Pareto-Optimal Clustering with the Primal Deterministic Information Bottleneck
by: Tan, Andrew K., et al.
Published: (2022) -
Toward an artificial intelligence physicist for unsupervised learning
by: Wu, Tailin, et al.
Published: (2021) -
Efficient Continuous Pareto Exploration in Multi-Task Learning
by: Ma, Pingchuan
Published: (2023) -
Pareto-optimal phylogenetic tree reconciliation
by: Libeskind-Hadas, Ran, et al.
Published: (2015)