Preprints

• TableShift: A Domain Shift Benchmark for Tabular Data.
  Josh Gardner, Zoran Popović, Ludwig Schmidt.
  In submission. arXiv soon!
  [code]

• OpenFlamingo: An Open-Source Framework for Training Vision-Language Models with In-Context Learning
  Anas Awadalla, Irena Gao, Josh Gardner, Jack Hessel, Yusuf Hanafy, Wanrong Zhu, Kalyani Marathe, Yonatan Bitton, Samir Gadre, Jenia Jitsev, Simon Kornblith, Pang Wei Koh, Gabriel Ilharco, Mitchell Wortsman, Ludwig Schmidt.
  Paper coming soon!
  [blog] [code]

Journal and Conference Papers

• Cross-Institutional Transfer Learning for Educational Models: Implications for Model Performance, Fairness, and Equity.
  Josh Gardner, Renzhe Yu, Quan Nguyen, Christopher Brooks, Rene Kizilcec.
  ACM Conference on Fairness, Accountability, and Transparency (ACM FAccT) 2023.
  [pdf] [arxiv] [code]

• Subgroup Robustness Grows on Trees: An Empirical Baseline Study.
  Josh Gardner, Zoran Popović, Ludwig Schmidt.
  Neural Information Processing Systems (NeurIPS) 2022.
  [arxiv] [code]

• Scaling Polyphonic Transcription with Mixtures of Monophonic Transcription.
  Ian Simon, Josh Gardner, Curtis Hawthorne, Ethan Manilow, Jesse Engel.
  International Society for Music Information Retrieval (ISMIR) 2022.
  [pdf]

• Multi-Instrument Music Synthesis with Spectrogram Diffusion.
  Curtis Hawthorne, Ian Simon, Adam Roberts, Neil Zeghidour, Josh Gardner, Ethan Manilow, Jesse Engel.
  International Society for Music Information Retrieval (ISMIR) 2022.
  [arxiv] [code]

• MT3: Multi-Task Multitrack Music Transcription
  Josh Gardner, Ian Simon, Ethan Manilow, Curtis Hawthorne, Jesse Engel.
  International Conference on Learning Representations (ICLR) 2022.
  Spotlight Presentation (top 6.7% of submissions)
  [arxiv] [web] [blog] [code]

• Advances and Open Problems in Federated Learning.
  Peter Kairouz, H. Brendan McMahan, [...], Josh Gardner, [...] . (59 authors.)
  Foundations and Trends® in Machine Learning (2021): Vol. 14: No. 1-2, pp 1-210.
  [doi]

• Driving with Data in the Motor City: Mining and Modeling Vehicle Fleet Maintenance Data.
  Josh Gardner, Jawad Mroueh, Natalia Jenuwine, Noah Weaverdyck, Samuel Krassenstein, Arya Farahi, Danai Koutra.
  IEEE International Conference on Data Science and Advanced Analytics (DSAA20).
  [arxiv]

• Modeling and Experimental Design for MOOC Dropout Prediction: A Replication Perspective.
  Josh Gardner, Yuming Yang, Ryan Baker and Christopher Brooks.
  Proceedings of the 12th International Conference on Educational Data Mining (EDM19).
  [pdf]

• Evaluating the Fairness of Predictive Student Models Through Slicing Analysis
  Josh Gardner, Christopher Brooks, and Ryan Baker.
  Proceedings of the 9th International Conference on Learning Analytics and Knowledge (LAK19).
  Best Paper Award
  [pdf]

• Beyond A/B Testing: Sequential Randomization for Developing Interventions in Scaled Digital Learning Environments.
  Timothy NeCamp, Josh Gardner, Christopher Brooks.
  Proceedings of the 9th International Conference on Learning Analytics and Knowledge (LAK19).
  [pdf]

• MORF: A Framework for Predictive Modeling and Replication At Scale With Privacy-Restricted MOOC Data.
  Josh Gardner, Miguel Andres-Bray, Christopher Brooks, and Ryan Baker.
  Proceedings of the 2018 IEEE International Conference on Big Data. Presented at 3rd Workshop on Open Science in Big Data (OSBD).
  [pdf]

• Learn From Your (Markov) Neighbor: Coenrollment, Assortativity, and Grade Prediction in Undergraduate Courses.
  Josh Gardner, Christopher Brooks, and Warren Li.
  The Journal of Learning Analytics.
  [pdf]

• Evaluating Predictive Models of Student Success: Closing the Methodological Gap.
  Josh Gardner, Christopher Brooks.
  The Journal of Learning Analytics.
  [pdf]

• Student Success Prediction in MOOCs.
  Josh Gardner, Christopher Brooks
  User Modeling and User-Adapted Interaction (UMUAI): The Journal of Personalization Research
  [pdf]

• How Gender Cues in Educational Video Impact Participation and Retention
  Christopher Brooks, Josh Gardner, Kaifeng Chen.
  Proceedings of the 2018 International Conference on the Learning Sciences (ICLS).
  [pdf]

• Replicating MOOC Predictive Models at Scale.
  Josh Gardner, Christopher Brooks, Juan Miguel Andres, Ryan S. Baker
  Proceedings of the Fifth ACM Conference on Learning@Scale (L@S).
  [pdf]

• Coenrollment Networks and their Relationship to Grades in Undergraduate Education.
  Josh Gardner, Christopher Brooks
  Proceedings of the 8th International Conference on Learning Analytics and Knowledge (LAK18)
  [pdf]

• Dropout Model Evaluation in MOOCs.
  Josh Gardner, Christopher Brooks
  Eighth AAAI Symposium on Educational Advances in Artificial Intelligence (EAAI-18)
  [pdf]

Workshop Papers (Peer-Reviewed)

• The Chamber Ensemble Generator: Limitless High-Quality Data via Generative Modeling.
  Yusong Wu, Josh Gardner, Ethan Manilow, Ian Simon, Curtis Hawthorne, Jesse Engel (2022).
  Workshop on Machine Learning for Audio Synthesis (MLAS) at ICML 2022 [link].
  [arxiv] [blog] [dataset]

• Enabling End-To-End Machine Learning Replicability: A Case Study in Educational Data Mining
  Josh Gardner, Yuming Yang, Ryan S. Baker, and Christopher Brooks
  Workshop on Enabling Reproducibility in Machine Learning at the Thirty-fifth International Conference on Machine Learning (REPML@ICML).
  [pdf]

• A Statistical Framework for Predictive Model Evaluation in MOOCs
  Josh Gardner, Christopher Brooks
  Fourth Annual Meeting of the ACM Conference on Learning@Scale (L@S)
  [pdf]

• Predictive Models with the Coenrollment Graph: Network-Based Grade Prediction in Undergraduate Courses
  Josh Gardner, Christopher Brooks
  The Third International Workshop on Graph-Based Educational Data Mining at 10th International Conference on Educational Data Mining

• Statistical Approaches to the Model Comparison Task in Learning Analytics
  Josh Gardner, Christopher Brooks
  Workshop on Methodology in Learning Analytics (MLA) at 7th International Conference on Learning Analytics and Knowledge

Patents

• Robust Model Performance Across Disparate Sub-Groups Within a Same Group
  Josh Gardner, Wei Huang
  [google patents]

• Privacy-Preserving Machine Learning Predictions
  Wei Huang, Josh Gardner, Michael William Daub, Alexander E. Mayorov
  [google patents]

• Cookie Space Domain Adaptation for Device Attribute Prediction
  Josh Gardner, Wei Huang, Michael William Daub, Alexander E. Mayorov