Pre-prints and Talks/Media
Research Insights on Redemptive Usecases
with CHAI.
Missional AI 2025.Belief-based AI Fairness
with CHAI.
CHAI Speaker Series 2023.Introduction to AI at Accord
with CHAI.
Accord 2023.
AI Alignment and Society/Media
Cultural Perspectives and Expectations for Generative AI: A Global Survey Approach
with Erin van Liemt, et al.
Nature (in submission).Preference Learning Algorithms Do Not Learn Preference Rankings
with Angelica Chen, Sadhika Malladi, Lily H. Zhang, Xinyi Chen, Rajesh Ranganath, Kyunghyun Cho.
Neurips 2024.Ontology of Belief Diversity: A Community-Based Epistemological Approach
with Tyler Fischella, Erin van Liemt.
AIES 2024.Getting Aligned on Representational Alignment
with multiple authors.
ArXiV 2023.Leveraging Contextual Counterfactuals Toward Belief Calibration
with Michael S. Lee, Sherol Chen
ICML 2023.
Papers
DynMuon: A Dynamic Spectral Shaping View of Muon
with Fangzhou Wu, Rikhav Shah, Sandeep Silwal.
Neurips 2026 (In Submission).Noisy Pairwise-Comparison Random Search for Smooth Nonconvex Optimization
with Taha El Bakkali, Rayane Bouftini, Omar Saadi.
ICML 2026.Randomization Boost KV Caching, Learning Balances Query Load: A Joint Perspective
with Fangzhou Wu and Sandeep Silwal.
ICLR 2026.Prompts Generalize with Low Data: Non-vacuous Generalization Bounds for Optimizing Prompts with More Informative Priors
with David Madras and Joshua Safyan.
ICML 2025.Reinforcement Learning under State and Outcome Uncertainty: A Foundational Distributional Perspective
with Larry Preuett and Muhammad Ahmad.
RLC 2025.Beyond Worst-Case Dimensionality Reduction for Sparse Vectors
with Sandeep Silwal and David Woodruff.
ICLR 2025.Quantifying Knowledge Distillation Using Partial Information Decomposition
with Pasan Dissanayake, Faisal Hamman, Barproda Halder, Ilia Sucholutsky, Sanghamitra Dutta.
AIStats 2025.Optimized Tradeoffs for Private Prediction with Majority Ensembling
with Shuli Jiang, Gauri Joshi.
TMLR 2024.Optimal Scalarizations for Sublinear Hypervolume Regret
Solo paper.
Neurips 2024.The Vizier Gaussian Process Bandit Algorithm
with Xingyou Song, Chansoo Lee, Emily Fertig, Tzu-Kuo Huang, Lior Belenki, Greg Kochanski, Setareh Ariafar, Srinivas Vasudevan, Sagi Perel, Daniel Golovin.
ArXiv 2024.Predicting from Strings: Language Model Embeddings for Bayesian Optimization
with Tung Nguyen, Bangding Yang, Chansoo Lee, Jorg Bornschein, Yingjie Miao, Sagi Perel, Yutian Chen, Xingyou Song.
ArXiV 2024 (In Submission).Quantifying Spuriousness of Biased Datasets Using Partial Information Decomposition
with Barproda Halder, Faisal Hamman, Pasan Dissanayake, Ilia Sucholutsky, Sanghamitra Dutta.
ICML 2024.Adaptive Regret for Bandits Made Possible: Two Queries Suffice
with Zhou Lu, Xinyi Chen, Fred Zhang, David Woodruff, Elad Hazan.
ICLR 2024.Set Learning for Accurate and Calibrated Models
with Lukas Muttenthaler, Robert A. Vandermeulen, Thomas Unterthiner, Klaus-Robert Müller.
ICLR 2024.Hardness of Low Rank Approximation of Entrywise Transformed Matrix Products
with Tamas Sarlos, Xingyou Song, David Woodruff
Neurips 2023.Computing Approximate ell_p Sensitivities
with Swati Padmanabhan, David Woodruff.
Neurips 2023.Robust Algorithms on Adaptive Inputs from Bounded Adversaries
with Yeshwanth Cherapanamjeri, Sandeep Silwal, David Woodruff, Fred Zhang, Samson Zhou.
ICLR 2023.Towards Learning Universal Hyperparameter Optimizers with Transformers
with Yutian Chen, Xingyou Song, Chansoo Lee, Zi Wang, David Dohan, Kazuya Kawakami, Greg Kochanski, Arnaud Doucet, Marc'aurelio Ranzato, Sagi Perel, Nando de Freitas.
Neurips 2022. [Google AI Blog]Optimal Query Complexities for Dynamic Trace Estimation
with David Woodruff, Fred Zhang.
Neurips 2022 (Spotlight).Leveraging Initial Hints for Free in Stochastic Linear Bandits
with Ashok Cutkosky, Chris Dann, Abhimanyu Das.
ALT 2022.Optimal Sketching for Trace Estimation
with Shuli Jiang, Hai Pham, David Woodruff.
Neurips 2021 (Spotlight).One Network Fits All? Modular versus Monolithic Task Formulations in Neural Networks
with Atish Agarwala, Abhimanyu Das, Brendan Juba, Rina Panigrahy, Vatsal Sharan, Xin Wang.
ICLR 2021.Random Hypervolume Scalarizations for Provable Multi-Objective Black Box Optimization
with Daniel Golovin.
ICML 2020.Gradientless Descent: High-Dimensional Zeroth-Order Optimization [slides]
with Daniel Golovin, John Karro, Greg Kochanski, Chansoo Lee, Xingyou Song.
ICLR 2020 (Spotlight).Span Recovery for Deep Neural Networks with Applications to Input Obfuscation
with Rajesh Jayaram, David Woodruff.
ICLR 2020.Regularized Weighted Low Rank Approximation
with Frank Ban, David Woodruff.
Neurips 2019.Solving Empirical Risk Minimization in the Current Matrix Multiplication Time
with Zhao Song, Yin Tat Lee.
COLT 2019.Optimal Sequence Length Requirements for Phylogenetic Tree Reconstruction with Indels
with Arun Ganesh.
STOC 2019.Using INC Within Divide-and-Conquer Phylogeny Estimation
with Thien Le, Aaron Sy, Erin Molloy, Satish Rao, Tandy Warnow.
AlCoB 2019.New Absolute Fast Converging Phylogeny Estimation Methods with Improved Scalability and Accuracy
with Satish Rao, Tandy Warnow.
WABI 2018.Convergence Results for Neural Networks via Electrodynamics
with Rina Panigrahy, Sushant Sachdeva.
ITCS 2018.Forbidden Directed Minors and Kelly-width
with Shiva Kintali.
Theoretical Computer Science 2017, Vol. 662.