Online learning with dynamics: A minimax perspective

Authors: Kush Bhatia, Karthik Sridharan

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

Reproducibility Variable Result LLM Response
Research Type Theoretical Our main results provide sufficient conditions for online learnability for this setup with corresponding rates. The rates are characterized by: 1) a complexity term capturing the expressiveness of the underlying policy class under the dynamics of state change, and 2) a dynamic stability term measuring the deviation of the instantaneous loss from a certain counterfactual loss. Further, we provide matching lower bounds which show that both the complexity terms are indeed necessary.
Researcher Affiliation Academia Kush Bhatia EECS, UC Berkeley kush@cs.berkeley.edu Karthik Sridharan CS, Cornell University sridharan@cs.cornell.edu
Pseudocode No The paper does not contain any pseudocode or algorithm blocks.
Open Source Code No The paper does not mention providing open-source code for the described methodology.
Open Datasets No The paper is theoretical and does not report on experiments using datasets for training. The examples section applies the theoretical framework to existing problem setups, but does not involve computational experiments with data.
Dataset Splits No The paper does not describe experimental validation or dataset splits.
Hardware Specification No The paper is theoretical and does not describe any hardware used for experiments.
Software Dependencies No The paper is theoretical and does not describe any specific software dependencies with version numbers.
Experiment Setup No The paper is theoretical and does not describe a computational experimental setup with hyperparameters or system-level settings.