DH
Daniel Hsu
cs.LGstat.MLmath.STstat.THcs.AIcs.CLcs.DScs.ITcs.NAmath.IT
On Valency
published · living versionsW_73pumvjw·v1 · currentpublished
W_cut2ytv9·v1published
Preprints & journals
119 papers in the corpus · 2002–2026Attention-based representations for multi-task computation2608.04243v1 · Daniel Hsu, Mingyue Xu2026 · 0 citationsarXiv
Behavior Cloning is Not All You Need: The Optimality of On-Policy Distillation for Noisy Expert Feedback2606.30923v1 · Ved Sriraman, Peihan Liu, Daniel Hsu et al.2026 · 0 citationsarXiv
The price of multi-group transductive learning2606.04423v2 · Noah Bergam, Samuel Deng, Daniel Hsu2026 · 0 citationsarXiv
Fixed Universal Transformers2605.31423v2 · Jingwen Liu, Alexandr Andoni, Daniel Hsu2026 · 0 citationsarXiv
A One-Inclusion Graph Approach to Multi-Group Learning2603.23208v2 · Noah Bergam, Samuel Deng, Daniel Hsu2026 · 0 citationsarXiv
ShakyPrepend: A Multi-Group Learner with Improved Sample Complexity2603.07319v1 · Lujing Zhang, Daniel Hsu, Sivaraman Balakrishnan2026 · 0 citationsarXiv
Group-realizable multi-group learning by minimizing empirical risk2601.16922v1 · Navid Ardeshir, Samuel Deng, Daniel Hsu et al.2026 · 0 citationsarXiv
Time-Aware Synthetic Control2601.03099v1 · Saeyoung Rho, Cyrus Illick, Samhitha Narasipura et al.2026 · 0 citationsarXiv
Panprediction: Optimal Predictions for Any Downstream Task and Loss2510.27638v1 · Sivaraman Balakrishnan, Nika Haghtalab, Daniel Hsu et al.2025 · 0 citationsarXiv
Investigating the Association Between Text-Based Indications of Foodborne Illness from Yelp Reviews and New York City Health Inspection Outcomes (2023)2510.16334v1 · Eden Shaveet, Crystal Su, Daniel Hsu et al.2025 · 0 citationsarXiv
Prior Knowledge Makes It Possible: From Sublinear Graph Algorithms to LLM Test-Time Methods2510.16609v3 · Avrim Blum, Daniel Hsu, Cyrus Rashtchian et al.2025 · 0 citationsarXiv
Fast attention mechanisms: a tale of parallelism2509.09001v1 · Jingwen Liu, Hantao Yu, Clayton Sanford et al.2025 · 0 citationsarXiv
Dimension lower bounds for linear approaches to function approximation2508.13346v1 · Daniel Hsu2025 · 0 citationsarXiv
Learning Compositional Functions with Transformers from Easy-to-Hard Data2505.23683v1 · Zixuan Wang, Eshaan Nichani, Alberto Bietti et al.2025 · 0 citationsarXiv
Survey on Algorithms for multi-index models2504.05426v2 · Joan Bruna, Daniel Hsu2025 · 3 citationsarXiv
The piranha problem: Large effects swimming in a small pond.40746854 · Tosh, Christopher, Greengard, Philip, Goodrich, Ben et al.2025 · 19 citationsNotices of the American Mathematical Society. American Mathematical Society. 2025;72(1):15-25
Learning Gaussian Multi-Index Models with Gradient Flow: Time Complexity and Directional Convergence2411.08798v2 · Berfin Simsek, Amire Bendjeddou, Daniel Hsu2024 · 0 citationsarXiv
Interactive Machine Teaching by Labeling Rules and Instances2409.05199v1 · Giannis Karamanolakis, Daniel Hsu, Luis Gravano2024 · 3 citationsarXiv
One-layer transformers fail to solve the induction heads task2408.14332v1 · Clayton Sanford, Daniel Hsu, Matus Telgarsky2024 · 1 citationarXiv
Transformers Provably Learn Sparse Token Selection While Fully-Connected Nets Cannot2406.06893v1 · Zixuan Wang, Stanley Wei, Daniel Hsu et al.2024 · 1 citationarXiv
Group-wise oracle-efficient algorithms for online multi-group learning2406.05287v2 · Samuel Deng, Daniel Hsu, Jingwen Liu2024 · 0 citationsarXiv
Seasonality Patterns in 311-Reported Foodborne Illness Cases and Machine Learning-Identified Indications of Foodborne Illnesses from Yelp Reviews, New York City, 2022-20232405.06138v1 · Eden Shaveet, Crystal Su, Daniel Hsu et al.2024 · 0 citationsarXiv
Transformers, parallel computation, and logarithmic depth2402.09268v1 · Clayton Sanford, Daniel Hsu, Matus Telgarsky2024 · 2 citationsarXiv
Multi-group Learning for Hierarchical Groups2402.00258v3 · Samuel Deng, Daniel Hsu2024 · 0 citationsarXiv
Distribution-Specific Auditing For Subgroup Fairness2401.16439v2 · Daniel Hsu, Jizhou Huang, Brendan Juba2024 · 1 citationarXiv
Efficient Estimation of the Central Mean Subspace via Smoothed Gradient Outer Products2312.15469v2 · Gan Yuan, Mingyue Xu, Samory Kpotufe et al.2023 · 1 citationarXiv
On the sample complexity of parameter estimation in logistic regression with normal design2307.04191v4 · Daniel Hsu, Arya Mazumdar2023 · 0 citationsarXiv
Group conditional validity via multi-group learning2303.03995v2 · Samuel Deng, Navid Ardeshir, Daniel Hsu2023 · 0 citationsarXiv
Intrinsic dimensionality and generalization properties of the -norm inductive bias2206.05317v2 · Navid Ardeshir, Daniel Hsu, Clayton Sanford2022 · 0 citationsarXiv
Statistical-Computational Trade-offs in Tensor PCA and Related Problems via Communication Complexity2204.07526v2 · Rishabh Dudeja, Daniel Hsu2022 · 11 citationsarXiv
Masked prediction tasks: a parameter identifiability view2202.09305v1 · Bingbin Liu, Daniel Hsu, Pradeep Ravikumar et al.2022 · 0 citationsarXiv
Near-Optimal Statistical Query Lower Bounds for Agnostically Learning Intersections of Halfspaces with Gaussian Marginals2202.05096v1 · Daniel Hsu, Clayton Sanford, Rocco Servedio et al.2022 · 2 citationsarXiv
Learning Tensor Representations for Meta-Learning2201.07348v1 · Samuel Deng, Yilin Guo, Daniel Hsu et al.2022 · 1 citationarXiv
Simple and near-optimal algorithms for hidden stratification and multi-group learning2112.12181v2 · Christopher Tosh, Daniel Hsu2021 · 0 citationsarXiv
Bayesian decision-making under misspecified priors with applications to meta-learning2107.01509v1 · Max Simchowitz, Christopher Tosh, Akshay Krishnamurthy et al.2021 · 9 citationsarXiv
Support vector machines and linear regression coincide with very high-dimensional features2105.14084v2 · Navid Ardeshir, Clayton Sanford, Daniel Hsu2021 · 15 citationsarXiv
Generalization bounds via distillation2104.05641v1 · Daniel Hsu, Ziwei Ji, Matus Telgarsky et al.2021 · 14 citationsarXiv
On the Approximation Power of Two-Layer Networks of Random ReLUs2102.02336v2 · Daniel Hsu, Clayton Sanford, Rocco A. Servedio et al.2021 · 6 citationsProceedings of Thirty Fourth Conference on Learning Theory, PMLR 134 (2021) 2423-2461
Biased Programmers? Or Biased Data? A Field Experiment in Operationalizing AI Ethics2012.02394v1 · Bo Cowgill, Fabrizio Dell'Acqua, Samuel Deng et al.2020 · 175 citationsarXiv
Detecting Foodborne Illness Complaints in Multiple Languages Using English Annotations Only2010.05194v1 · Ziyi Liu, Giannis Karamanolakis, Daniel Hsu et al.2020 · 1 citationarXiv
Cross-Lingual Text Classification with Minimal Resources by Transferring a Sparse Teacher2010.02562v1 · Giannis Karamanolakis, Daniel Hsu, Luis Gravano2020 · 20 citationsarXiv
On the proliferation of support vectors in high dimensions2009.10670v2 · Daniel Hsu, Vidya Muthukumar, Ji Xu2020 · 29 citationsarXiv
Contrastive learning, multi-view redundancy, and linear models2008.10150v2 · Christopher Tosh, Akshay Krishnamurthy, Daniel Hsu2020 · 25 citationsarXiv
Statistical Query Lower Bounds for Tensor PCA2008.04101v2 · Rishabh Dudeja, Daniel Hsu2020 · 10 citationsarXiv
Interpreting deep learning models for weak lensing2007.06529v2 · Jos'e Manuel Zorrilla Matilla, Manasi Sharma, Daniel Hsu et al.2020 · 48 citationsarXiv
Ensuring Fairness Beyond the Training Data2007.06029v2 · Debmalya Mandal, Samuel Deng, Suman Jana et al.2020 · 27 citationsarXiv
Classification vs regression in overparameterized regimes: Does the loss function matter?2005.08054v2 · Vidya Muthukumar, Adhyyan Narang, Vignesh Subramanian et al.2020 · 69 citationsJournal of Machine Learning Research, 22(222):1-69, 2021
Reply to Loog et al.: Looking beyond the peaking phenomenon.32371494 · Belkin, Mikhail, Hsu, Daniel, Ma, Siyuan et al.2020 · 6 citationsProceedings of the National Academy of Sciences of the United States of America. 2020;117(20):10627
Contrastive estimation reveals topic posterior information to linear models2003.02234v1 · Christopher Tosh, Akshay Krishnamurthy, Daniel Hsu2020 · 17 citationsarXiv
A New Framework for Query Efficient Active Imitation Learning1912.13037v1 · Daniel Hsu2019 · 2 citationsarXiv
Career total: 183 works. 119 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.