Mikhail Yurochkin

CoRR, 2024

Distributional Preference Alignment of LLMs via Optimal Transport.

[BibT_eX]

[DOI]

Allysson Flavio Melo de Oliveira

Jirí Navrátil

Jerret Ross

CoRR, 2024

Efficient multi-prompt evaluation of LLMs.

[BibT_eX]

[DOI]

CoRR, 2024

A statistical framework for weak-to-strong generalization.

[BibT_eX]

[DOI]

CoRR, 2024

Prompt Exploration with Prompt Regression.

[BibT_eX]

[DOI]

CoRR, 2024

Asymmetry in Low-Rank Adapters of Foundation Models.

[BibT_eX]

[DOI]

Jiacheng Zhu

Haitz Sáez de Ocáriz Borde

Kimia Nadjahi

Rickard Brüel Gabrielsson

Proceedings of the Forty-first International Conference on Machine Learning, 2024

tinyBenchmarks: evaluating LLMs with fewer examples.

[BibT_eX]

[DOI]

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Risk Aware Benchmarking of Large Language Models.

[BibT_eX]

[DOI]

Apoorva Nitsure

Youssef Mroueh

Mattia Rigotti

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Uncertainty Quantification via Stable Distribution Propagation.

[BibT_eX]

[DOI]

Felix Petersen

Aashwin Ananda Mishra

Proceedings of the Twelfth International Conference on Learning Representations, 2024

An Investigation of Representation and Allocation Harms in Contrastive Learning.

[BibT_eX]

[DOI]

Proceedings of the Twelfth International Conference on Learning Representations, 2024

Fusing Models with Complementary Expertise.

[BibT_eX]

[DOI]

Proceedings of the Twelfth International Conference on Learning Representations, 2024

Aligners: Decoupling LLMs and Alignment.

[BibT_eX]

[DOI]

Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2024, 2024

2023

k-Mixup Regularization for Deep Learning via Optimal Transport.

[BibT_eX]

[DOI]

Rickard Brüel Gabrielsson

Trans. Mach. Learn. Res., 2023

Rewiring with Positional Encodings for Graph Neural Networks.

[BibT_eX]

[DOI]

Trans. Mach. Learn. Res., 2023

Estimating Fréchet bounds for validating programmatic weak supervision.

[BibT_eX]

[DOI]

CoRR, 2023

Risk Assessment and Statistical Significance in the Age of Foundation Models.

[BibT_eX]

[DOI]

Apoorva Nitsure

Youssef Mroueh

Mattia Rigotti

CoRR, 2023

GeRA: Label-Efficient Geometrically Regularized Alignment.

[BibT_eX]

[DOI]

CoRR, 2023

Large Language Model Routing with Benchmark Datasets.

[BibT_eX]

[DOI]

CoRR, 2023

Simple Disentanglement of Style and Content in Visual Representations.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2023

Understanding new tasks through the lens of training data via exponential tilting.

[BibT_eX]

[DOI]

Proceedings of the Eleventh International Conference on Learning Representations, 2023

Sampling with Mollified Interaction Energy Descent.

[BibT_eX]

[DOI]

Proceedings of the Eleventh International Conference on Learning Representations, 2023

Learning Proximal Operators to Discover Multiple Optima.

[BibT_eX]

[DOI]

Proceedings of the Eleventh International Conference on Learning Representations, 2023

Fairness Evaluation in Text Classification: Machine Learning Practitioner Perspectives of Individual and Group Fairness.

[BibT_eX]

[DOI]

Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems, 2023

2022

Outlier-Robust Group Inference via Gradient Space Clustering.

[BibT_eX]

[DOI]

Yuchen Zeng

Kangwook Lee

CoRR, 2022

How does overparametrization affect performance on minority groups?

[BibT_eX]

[DOI]

CoRR, 2022

RMExplorer: A Visual Analytics Approach to Explore the Performance and the Fairness of Disease Risk Models on Population Subgroups.

[BibT_eX]

[DOI]

Proceedings of the 2022 IEEE Visualization and Visual Analytics (VIS), 2022

Calibrated Data-Dependent Constraints with Exact Satisfaction Guarantees.

[BibT_eX]

[DOI]

Songkai Xue

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Domain Adaptation meets Individual Fairness. And they get along.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Log-Euclidean Signatures for Intrinsic Distances Between Unaligned Datasets.

[BibT_eX]

[DOI]

Tal Shnitzer

Karthikeyan Natesan Ramamurthy

Justin M. Solomon

Proceedings of the International Conference on Machine Learning, 2022

Fairness of Machine Learning in Search Engines.

[BibT_eX]

[DOI]

Proceedings of the 31st ACM International Conference on Information & Knowledge Management, 2022

Measuring the robustness of Gaussian processes to kernel choice.

[BibT_eX]

[DOI]

William T. Stephenson

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2022

Your fairness may vary: Pretrained language model fairness in toxic text classification.

[BibT_eX]

[DOI]

Ioana Baldini

Dennis Wei

Moninder Singh

Proceedings of the Findings of the Association for Computational Linguistics: ACL 2022, 2022

Communication-Efficient Model Fusion.

[BibT_eX]

[DOI]

Proceedings of the Federated Learning, 2022

Personalization in Federated Learning.

[BibT_eX]

[DOI]

Karthikeyan Natesan Ramamurthy

Proceedings of the Federated Learning, 2022

2021

On efficient multilevel Clustering via Wasserstein distances.

[BibT_eX]

[DOI]

J. Mach. Learn. Res., 2021

Your fairness may vary: Group fairness of pretrained language models in toxic text classification.

[BibT_eX]

[DOI]

Ioana Baldini

Dennis Wei

Moninder Singh

CoRR, 2021

Measuring the sensitivity of Gaussian processes to kernel choice.

[BibT_eX]

[DOI]

William T. Stephenson

CoRR, 2021

Individually Fair Ranking.

[BibT_eX]

[DOI]

CoRR, 2021

Post-processing for Individual Fairness.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Does enforcing fairness mitigate biases caused by subpopulation shift?

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

On sensitivity of meta-learning to support data.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Outlier-Robust Optimal Transport.

[BibT_eX]

[DOI]

Proceedings of the 38th International Conference on Machine Learning, 2021

SenSeI: Sensitive Set Invariance for Enforcing Individual Fairness.

[BibT_eX]

[DOI]

Proceedings of the 9th International Conference on Learning Representations, 2021

Individually Fair Gradient Boosting.

[BibT_eX]

[DOI]

Proceedings of the 9th International Conference on Learning Representations, 2021

Statistical inference for individual fairness.

[BibT_eX]

[DOI]

Proceedings of the 9th International Conference on Learning Representations, 2021

Individually Fair Rankings.

[BibT_eX]

[DOI]

Proceedings of the 9th International Conference on Learning Representations, 2021

2020

Black Loans Matter: Distributionally Robust Fairness for Fighting Subgroup Discrimination.

[BibT_eX]

[DOI]

CoRR, 2020

There is no trade-off: enforcing fairness can improve accuracy.

[BibT_eX]

[DOI]

CoRR, 2020

Online Semi-Supervised Learning with Bandit Feedback.

[BibT_eX]

[DOI]

CoRR, 2020

IBM Federated Learning: an Enterprise Framework White Paper V0.1.

[BibT_eX]

[DOI]

CoRR, 2020

Continuous Regularized Wasserstein Barycenters.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Two Simple Ways to Learn Individual Fairness Metrics from Data.

[BibT_eX]

[DOI]

Proceedings of the 37th International Conference on Machine Learning, 2020

Model Fusion with Kullback-Leibler Divergence.

[BibT_eX]

[DOI]

Proceedings of the 37th International Conference on Machine Learning, 2020

Training individually fair ML models with sensitive subspace robustness.

[BibT_eX]

[DOI]

Amanda Bower

Proceedings of the 8th International Conference on Learning Representations, 2020

Federated Learning with Matched Averaging.

[BibT_eX]

[DOI]

Hongyi Wang

Dimitris S. Papailiopoulos

Yasaman Khazaeni

Proceedings of the 8th International Conference on Learning Representations, 2020

Auditing ML Models for Individual Bias and Unfairness.

[BibT_eX]

[DOI]

Songkai Xue

Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics, 2020

2019

Learning fair predictors with Sensitive Subspace Robustness.

[BibT_eX]

[DOI]

Amanda Bower

CoRR, 2019

Scalable inference of topic evolution via models for latent geometric structures.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Hierarchical Optimal Transport for Document Representation.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Statistical Model Aggregation via Parameter Matching.

[BibT_eX]

[DOI]

Soumya Ghosh

Trong Nghia Hoang

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Alleviating Label Switching with Optimal Transport.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Dirichlet Simplex Nest and Geometric Inference.

[BibT_eX]

[DOI]

Proceedings of the 36th International Conference on Machine Learning, 2019

Bayesian Nonparametric Federated Learning of Neural Networks.

[BibT_eX]

[DOI]

Soumya Ghosh

Trong Nghia Hoang

Yasaman Khazaeni

Proceedings of the 36th International Conference on Machine Learning, 2019

2018

Streaming dynamic and distributed inference of latent geometric structures.

[BibT_eX]

[DOI]

CoRR, 2018

2017

Multi-way Interacting Regression via Factorization Machines.

[BibT_eX]

[DOI]

XuanLong Nguyen

Nikolaos Vasiloglou

Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017

Conic Scan-and-Cover algorithms for nonparametric topic modeling.

[BibT_eX]

[DOI]

Aritra Guha

XuanLong Nguyen

Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017

Multilevel Clustering via Wasserstein Means.

[BibT_eX]

[DOI]

Proceedings of the 34th International Conference on Machine Learning, 2017

2016

Geometric Dirichlet Means Algorithm for topic inference.

[BibT_eX]

[DOI]