Ashia Wilson

According to our database, Ashia Wilson authored at least 50 papers between 2013 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of three.

2026

The Fast Mixing Mechanism for Differential Privacy.

Omri Lev, Moshe Shenfeld, Vishwak Srinivasan, Katrina Ligett, Ashia C. Wilson

CoRR, May, 2026

Pandora's Regret: A Proper Scoring Rule for Evaluating Sequential Search.

Gerardo Flores, Yash Deshpande, Jannis R. Brea, Ashia C. Wilson

CoRR, May, 2026

Evaluation without Generation: Non-Generative Assessment of Harmful Model Specialization with Applications to CSAM.

Vinith M. Suriyakumar, Ayush Sekhari, Lena Stempfle, Robertson Wang, Michael Simpson, Rebecca S. Portnoff, Marzyeh Ghassemi, Ashia C. Wilson

CoRR, April, 2026

Alignment has a Fantasia Problem.

Nathanael Jo, Zoe De Simone, Mitchell Gordon, Ashia Wilson

CoRR, April, 2026

Creo: From One-Shot Image Generation to Progressive, Co-Creative Ideation.

Zoe De Simone, Angie W. Boggust, Fredo Durand, Ashia Wilson, Arvind Satyanarayan

CoRR, April, 2026

Online Reasoning Calibration: Test-Time Training Enables Generalizable Conformal LLM Reasoning.

Cai Zhou, Zekai Wang, Menghua Wu, Qianyu Julie Zhu, Flora C. Shi, Chenyu Wang, Ashia Wilson, Tommi S. Jaakkola, Stephen Bates

CoRR, April, 2026

From Cross-Validation to SURE: Asymptotic Risk of Tuned Regularized Estimators.

Karun Adusumilli, Maximilian Kasy, Ashia Wilson

CoRR, March, 2026

Efficient and accurate steering of Large Language Models through attention-guided feature learning.

Parmida Davarmanesh, Ashia Wilson, Adityanarayanan Radhakrishnan

CoRR, February, 2026

Near-Optimal Private Linear Regression via Iterative Hessian Mixing.

Omri Lev, Moshe Shenfeld, Vishwak Srinivasan, Katrina Ligett, Ashia C. Wilson

CoRR, January, 2026

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

Vinith Menon Suriyakumar, Rohan Alur, Ayush Sekhari, Manish Raghavan, Ashia C. Wilson

Trans. Mach. Learn. Res., 2026

Influence Estimation in Statistical Models Using the Fisher Information Matrix.

Omri Lev, Ashia C. Wilson

Trans. Mach. Learn. Res., 2026

Interaction Context Often Increases Sycophancy in LLMs.

Shomik Jain, Charlotte Park, Matt Viana, Ashia Wilson, Dana Calacci

Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems, 2026

2025

Adaptive Kernel Selection for Stein Variational Gradient Descent.

Moritz Melcher, Simon Weissmann, Ashia C. Wilson, Jakob Zech

CoRR, October, 2025

LLM Output Homogenization is Task Dependent.

Shomik Jain, Jack Lanchantin, Maximilian Nickel, Karen Ullrich, Ashia Wilson, Jamelle Watson-Daniels

CoRR, September, 2025

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

Nathanael Jo, Ashia Wilson

CoRR, September, 2025

Extended AI Interactions Shape Sycophancy and Perspective Mimesis.

Shomik Jain, Charlotte Park, Matheus Mesquita Viana, Ashia Wilson, Dana Calacci

CoRR, September, 2025

Bridging Prediction and Intervention Problems in Social Systems.

Lydia T. Liu, Inioluwa Deborah Raji, Angela Zhou, Luke Guerdan, Jessica Hullman, Daniel Malinsky, Bryan Wilder, Simone Zhang, Hammaad Adam, Amanda Coston, Benjamin Laufer, Ezinne Nwankwo, Michael Zanger-Tishler, Eli Ben-Michael, Solon Barocas, Avi Feller, Marissa Gerchick, Talia Gillis, Shion Guha, Daniel E. Ho, Lily Hu, Kosuke Imai, Sayash Kapoor, Joshua Loftus, Razieh Nabi, Arvind Narayanan, Ben Recht, Juan Carlos Perdomo, Matthew J. Salganik, Mark P. Sendak, Alexander Tolbert, Berk Ustun, Suresh Venkatasubramanian, Angelina Wang, Ashia Wilson

CoRR, July, 2025

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

Gerardo Flores, Alyssa H. Smith, Julia A Fukuyama, Ashia C. Wilson

CoRR, June, 2025

Semivalue-based data valuation is arbitrary and gameable.

Hannah Diehl, Ashia C. Wilson

CoRR, June, 2025

UCD: Unlearning in LLMs via Contrastive Decoding.

Vinith M. Suriyakumar, Ayush Sekhari, Ashia Wilson

CoRR, June, 2025

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

Omri Lev, Vishwak Srinivasan, Moshe Shenfeld, Katrina Ligett, Ayush Sekhari, Ashia C. Wilson

CoRR, May, 2025

Layered Unlearning for Adversarial Relearning.

Timothy Qian, Vinith Suriyakumar, Ashia Wilson, Dylan Hadfield-Menell

CoRR, May, 2025

A Consequentialist Critique of Binary Classification Evaluation Practices.

Gerardo Flores, Abigail Schiff, Alyssa H. Smith, Julia A Fukuyama, Ashia C. Wilson

CoRR, April, 2025

Homogeneous Algorithms Can Reduce Competition in Personalized Pricing.

Nathanael Jo, Ashia C. Wilson, Kathleen Creel, Manish Raghavan

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2025, 2025

Adaptive backtracking line search.

Joao V. Cavalcanti, Laurent Lessard, Ashia C. Wilson

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Allocation Multiplicity: Evaluating the Promises of the Rashomon Set.

Shomik Jain, Margaret Wang, Kathleen Creel, Ashia Wilson

Proceedings of the 2025 ACM Conference on Fairness, Accountability, and Transparency, 2025

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

Vishwak Srinivasan, Andre Wibisono, Ashia Wilson

Proceedings of the International Conference on Algorithmic Learning Theory, 2025

2024

Adaptive Backtracking For Faster Optimization.

Joao V. Cavalcanti, Laurent Lessard, Ashia C. Wilson

CoRR, 2024

Faster Machine Unlearning via Natural Gradient Descent.

Omri Lev, Ashia Wilson

CoRR, 2024

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

Shomik Jain, Kathleen Creel, Ashia Wilson

CoRR, 2024

Position: Scarce Resource Allocations That Rely On Machine Learning Should Be Randomized.

Shomik Jain, Kathleen Creel, Ashia Camage Wilson

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

Mean-field Underdamped Langevin Dynamics and its Spacetime Discretization.

Qiang Fu, Ashia Camage Wilson

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

Algorithmic Pluralism: A Structural Approach To Equal Opportunity.

Shomik Jain, Vinith M. Suriyakumar, Kathleen Creel, Ashia Wilson

Proceedings of the 2024 ACM Conference on Fairness, Accountability, and Transparency, 2024

Fast sampling from constrained spaces using the Metropolis-adjusted Mirror Langevin algorithm.

Vishwak Srinivasan, Andre Wibisono, Ashia C. Wilson

Proceedings of the Thirty Seventh Annual Conference on Learning Theory, June 30, 2024

Automating Transparency Mechanisms in the Judicial System Using LLMs: Opportunities and Challenges.

Ishana Shastri, Shomik Jain, Barbara Engelhardt, Ashia Wilson

Proceedings of the Seventh AAAI/ACM Conference on AI, Ethics, and Society (AIES-24) - Full Archival Papers, October 21-23, 2024, San Jose, California, USA, 2024

As an AI Language Model, "Yes I Would Recommend Calling the Police": Norm Inconsistency in LLM Decision-Making.

Shomik Jain, Dana Calacci, Ashia Wilson

Proceedings of the Seventh AAAI/ACM Conference on AI, Ethics, and Society (AIES-24) - Full Archival Papers, October 21-23, 2024, San Jose, California, USA, 2024

2023

What is a Fair Diffusion Model? Designing Generative Text-To-Image Models to Incorporate Various Worldviews.

Zoe De Simone, Angie W. Boggust, Arvind Satyanarayan, Ashia Wilson

CoRR, 2023

Algorithmic Pluralism: A Structural Approach Towards Equal Opportunity.

Shomik Jain, Vinith M. Suriyakumar, Ashia Wilson

CoRR, 2023

Accelerated Stochastic Optimization Methods under Quasar-convexity.

Qiang Fu, Dongchu Xu, Ashia Camage Wilson

Proceedings of the International Conference on Machine Learning, 2023

2022

Algorithms that Approximate Data Removal: New Results and Limitations.

Vinith M. Suriyakumar, Ashia C. Wilson

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

Multilevel Optimization for Inverse Problems.

Simon Weissmann, Ashia Wilson, Jakob Zech

Proceedings of the Conference on Learning Theory, 2-5 July 2022, London, UK., 2022

2021

A Lyapunov Analysis of Accelerated Methods in Optimization.

Ashia C. Wilson, Ben Recht, Michael I. Jordan

J. Mach. Learn. Res., 2021

2020

The disparate equilibria of algorithmic decision making when individuals invest rationally.

Lydia T. Liu, Ashia Wilson, Nika Haghtalab, Adam Tauman Kalai, Christian Borgs, Jennifer T. Chayes

Proceedings of the FAT* '20: Conference on Fairness, 2020

Approximate Cross-validation: Guarantees for Model Assessment and Selection.

Ashia C. Wilson, Maximilian Kasy, Lester Mackey

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

2019

Accelerating Rescaled Gradient Descent: Fast Optimization of Smooth Functions.

Ashia C. Wilson, Lester Mackey, Andre Wibisono

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

2017

The Marginal Value of Adaptive Gradient Methods in Machine Learning.

Ashia C. Wilson, Rebecca Roelofs, Mitchell Stern, Nati Srebro, Benjamin Recht

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

Breaking Locality Accelerates Block Gauss-Seidel.

Stephen Tu, Shivaram Venkataraman, Ashia C. Wilson, Alex Gittens, Michael I. Jordan, Benjamin Recht

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

2016

A Lyapunov Analysis of Momentum Methods in Optimization.

Ashia C. Wilson, Benjamin Recht, Michael I. Jordan

CoRR, 2016

A Variational Perspective on Accelerated Methods in Optimization.

Andre Wibisono, Ashia C. Wilson, Michael I. Jordan

CoRR, 2016

2013

Streaming Variational Bayes.

Tamara Broderick, Nicholas Boyd, Andre Wibisono, Ashia C. Wilson, Michael I. Jordan

Proceedings of the Advances in Neural Information Processing Systems 26: 27th Annual Conference on Neural Information Processing Systems 2013. Proceedings of a meeting held December 5-8, 2013