Optimal Bounds between f-Divergences and Integral Probability Metrics

Authors: Rohit Agrawal, Thibaut Horel

ICML 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical Starting from a tight variational representation of the f-divergence, we derive a generalization of the moment generating function, which we show exactly characterizes the best lower bound of the f-divergence as a function of a given IPM. Using this characterization, we obtain new bounds on IPMs defined by classes of unbounded functions, while also recovering in a unified manner well-known results for bounded and subgaussian functions (e.g. Pinsker s inequality and Hoeffding s lemma).
Researcher Affiliation Academia 1Harvard John A. Paulson School of Engineering and Applied Sciences, Cambridge, Massachusetts, USA 2Institute for Data, Systems, and Society, MIT, Cambridge, Massachusetts, USA.
Pseudocode No The paper does not contain structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide concrete access to source code for the methodology described.
Open Datasets No The paper is theoretical and does not use or describe datasets.
Dataset Splits No The paper is theoretical and does not involve data partitioning for training, validation, or testing.
Hardware Specification No The paper is theoretical and does not describe the hardware used for experiments.
Software Dependencies No The paper is theoretical and does not provide specific ancillary software details with version numbers.
Experiment Setup No The paper is theoretical and does not describe an experimental setup with hyperparameters or training configurations.