​​​Latest publications

​​​

• Aligning Evaluation with Clinical Priorities: Calibration, Label Shift, and Error Costs

        Joint with Gerardo Flores, Alyssa Smith, and Julia Fukuyama. 

​        Conference on Neural Information Processing Systems (NeurIPS). 2025.

        [arXiv]

​

• The Gaussian Mixing Mechanism: Renyi Differential Privacy via Gaussian Sketches

​        Joint with Omri Lev, Vishwak Srinivasan, Moshe Shenfeld, Katrina Ligett, and Ayush Sekhari​.

​        Conference on Neural Information Processing Systems (NeurIPS). 2025.

        [arXiv]

​

• Homogeneous Algorithms Can Reduce Competition in Personalized Pricing

        Joint with Nathan Jo, Kathleen Creel, and Manish Raghavan.

​        Conference on Neural Information Processing Systems (NeurIPS). 2025.

        [arXiv]

        

• Adaptive Backtracking Line Search

        Joint with Laurent Lessard and Joao Cavalcanti. 

        International Conference on Learning Representations (ICLR). 2025

        [arXiv]

​

• ​High-accuracy sampling from constrained spaces with the Metropolis-adjusted Preconditioned Langevin Algorithm

        Joint with Vishwak Srinivasan and Andre Wibisono.​

       International Conference on Algorithmic Learning Theory (ALT). 2025.

​        [arXiv] ​

​

• Allocation Multiplicity: Evaluating the Promises of the Rashomon Set​​

        Joint with Shomik Jain, Margaret Wang, and Kathleen Creel

        ACM Conference on Fairness, Accountability and Transparency  (FAccT). 2025. 

       [arXiv]​​​

​

• Algorithmic Pluralism: A Structural Approach To Equal Opportunity

        Joint with Shomik Jain, Vinith Suriyakumar, and Kathleen Creel

       ACM Conference on Fairness, Accountability and Transparency  (FAccT, best paper). 2024.

       ACM conference on Equity and Access in Algorithms, Mechanisms, and Optimization (EAAMO, non-archival). 2023. 

​       [arXiv] ​​​

​

• Scarce Resource Allocations That Rely On Machine Learning Should Be Randomized

        Joint with Shomik Jain and Kathleen Creel​ 

        International Conference on Machine Learning (ICML). 2024.

        [arXiv]​​​

​

​​​​​​​

​

Latest preprints

​​​​​​​​​

• ​Adaptive kernel selection for Stein Variational Gradient Descent

        Joint with Moritz Melcher, Simon Weissmann, and Jakob Zech. 2025.

        NeurIPs 2025 Workshop on Dynamics at the Frontiers of Optimization, Sampling, and Games

        [arXiv]

 

• Rethinking LLM Evaluation: How Long-term Interaction Shapes Sycophancy

        Joint with Shomik Jain, Charlotte Park, Matheus Vianna, and Dana Calacci. 2025

        [arXiv]

​

• A Consequentialist Critique of Binary Classification Evaluation: Theory, Practice, and Tools.

        Joint with G Flores, A Schiff, AH Smith, JA Fukuyama. 2025

        [arXiv]

​

• Unstable Unlearning: The Hidden Risk of Concept Resurgence in Diffusion Models

        Joint with Vinith Suriyakumar, Rohan Alur, Ayush Sekhari and Manish Raghavan. 2024.

        ICLR 2025 Workshop on Navigating and Addressing Data Problems for Foundation Models

        [arXiv]

​

• What Does Your Benchmark Really Measure? A Framework for Robust Inference of AI Capabilities

        Joint with Nathan Jo

        [arXiv]

​

• LLM Output Homogenization is Task Dependent

        Joint with Shomik Jain, Jack Lanchantin, Maximilian Nickel, Karen Ullrich and Jamelle Watson-Daniels

        [arXiv]