Online Minimax Multiobjective Optimization: Multicalibeating and Other Applications

Authors: Daniel Lee, Georgy Noarov, Mallesh Pai, Aaron Roth

NeurIPS 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical We introduce a simple but general online learning framework in which a learner plays against an adversary in a vector-valued game that changes every round... We demonstrate the power of our framework by using it to (re)derive optimal bounds and efficient algorithms across a variety of domains... Our derivation is elementary and based on a minimax argument... 3. If you ran experiments... [N/A] (a) Did you include the code, data, and instructions needed to reproduce the main experimental results...? [N/A] (b) Did you specify all the training details...? [N/A]
Researcher Affiliation Academia 1 University of Pennsylvania, 2 Rice University daniellee@alumni.upenn.edu, gnoarov@seas.upenn.edu, mallesh.pai@rice.edu, aaroth@cis.upenn.edu
Pseudocode Yes Algorithm 1: General Algorithm for the Learner that Achieves Sublinear AMF Regret
Open Source Code No 3. If you ran experiments... (a) Did you include the code, data, and instructions needed to reproduce the main experimental results (either in the supplemental material or as a URL)? [N/A]
Open Datasets No 3. If you ran experiments... (a) Did you include the code, data, and instructions needed to reproduce the main experimental results (either in the supplemental material or as a URL)? [N/A]
Dataset Splits No 3. If you ran experiments... (b) Did you specify all the training details (e.g., data splits, hyperparameters, how they were chosen)? [N/A]
Hardware Specification No 3. If you ran experiments... (d) Did you include the total amount of compute and the type of resources used (e.g., type of GPUs, internal cluster, or cloud provider)? [N/A]
Software Dependencies No The paper describes theoretical algorithms and proofs, and does not mention specific software dependencies with version numbers required for reproducibility.
Experiment Setup No 3. If you ran experiments... (b) Did you specify all the training details (e.g., data splits, hyperparameters, how they were chosen)? [N/A]