Algorithm Configuration for Structured Pfaffian Settings

Authors: Maria Florina Balcan, Anh Tuan Nguyen, Dravyansh Sharma

TMLR 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical In this work, we present new frameworks for providing learning guarantees for parameterized data-driven algorithm design problems in both statistical and online learning settings. For the statistical learning setting, we introduce the Pfaffian GJ framework... For the online learning setting, we provide a new tool for verifying the dispersion property... We use our framework to provide novel learning guarantees for many challenging data-driven design problems of interest
Researcher Affiliation Academia Maria Florina Balcan EMAIL School of Computer Science Carnegie Mellon University Anh Tuan Nguyen EMAIL Machine Learning Department Carnegie Mellon University Dravyansh Sharma EMAIL Toyota Technological Institute at Chicago
Pseudocode Yes Algorithm 1 Approximate incremental quadratic algorithm for RLR with ℓ1 penalty, Rosset, 2004 ... Algorithm 2 Approximate incremental quadratic algorithm for RLR with ℓ2 penalty, Rosset, 2004
Open Source Code No The paper does not provide concrete access to source code for the methodology described. There are no links to repositories, explicit statements about code release, or mentions of code in supplementary materials.
Open Datasets No The paper refers to 'problem instances' and 'underlying problem distribution' for its theoretical analysis but does not mention specific, named publicly available datasets or provide any access information (links, DOIs, citations) for datasets used in experiments. The paper is theoretical in nature and does not describe empirical evaluation on specific datasets.
Dataset Splits No The paper is theoretical and focuses on frameworks and guarantees for data-driven algorithm design. It does not describe empirical experiments using specific datasets, and therefore does not provide information on training/test/validation splits.
Hardware Specification No The paper is theoretical in nature, proposing frameworks and providing learning guarantees. It does not describe any experiments that would require specific hardware, thus no hardware specifications are mentioned.
Software Dependencies No The paper is theoretical, presenting mathematical frameworks and proofs for learning guarantees. It does not describe specific software implementations or list software dependencies with version numbers.
Experiment Setup No The paper is theoretical, focusing on frameworks and learning guarantees. It does not describe an experimental setup with specific hyperparameters, training configurations, or system-level settings for empirical evaluation.