RN
Robert Nowak
cs.LGstat.MLcs.AIcs.ITmath.ITmath.STstat.THcs.CVcs.CLmath.OC
On Valency
published · living versionsW_akyz4vha·v1 · currentpublished
On Finding the Largest Mean Among Many
with Kevin Jamieson, Matthew Malloy, Sebastien Bubeck
1 version
W_snudtqx3·v1published
Preprints & journals
108 papers in the corpus · 1998–2026Understanding Why Language Models Hallucinate: Testing Reasoning Against Priors2607.00447v2 · Yangfan Hu, Xuhan Tong, Haoyue Bai et al.2026 · 0 citationsarXiv
The Long-Horizon Task Mirage? Diagnosing Where and Why Agentic Systems Break2604.11978v1 · Xinyu Jessica Wang, Haoyue Bai, Yiyou Sun et al.2026 · 0 citationsarXiv
Which LLMs Get the Joke? Probing Non-STEM Reasoning Abilities with HumorBench2507.21476v1 · Reuben Narad, Siddharth Suresh, Jiayi Chen et al.2025 · 0 citationsarXiv
Improving Task Diversity in Label Efficient Supervised Finetuning of LLMs2507.21482v1 · Abhinav Arabelly, Jagrut Nemade, Robert D Nowak et al.2025 · 1 citationarXiv
Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds2506.03100v3 · Yang Guo, Yutian Tao, Yifei Ming et al.2025 · 0 citationsarXiv
Global Minimizers of -Regularized Objectives Yield the Sparsest ReLU Neural Networks2505.21791v4 · Julia Nakhleh, Robert D. Nowak2025 · 0 citationsarXiv
Bridging the Creativity Understanding Gap: Small-Scale Human Alignment Enables Expert-Level Humor Ranking in LLMs2502.20356v1 · Kuan Lok Zhou, Jiayi Chen, Siddharth Suresh et al.2025 · 0 citationsarXiv
Optimal Recovery Meets Minimax Estimation2502.17671v3 · Ronald DeVore, Robert D. Nowak, Rahul Parhi et al.2025 · 1 citationarXiv
Unifying Generative and Dense Retrieval for Sequential Recommendation2411.18814v2 · Liu Yang, Fabian Paischer, Kaveh Hassani et al.2024 · 0 citationsarXiv
Deep Active Learning in the Open World2411.06353v2 · Tian Xie, Jifan Zhang, Haoyue Bai et al.2024 · 0 citationsarXiv
The Effects of Multi-Task Learning on ReLU Neural Network Functions2410.21696v4 · Julia Nakhleh, Joseph Shenouda, Robert D. Nowak2024 · 0 citationsarXiv
AHA: Human-Assisted Out-of-Distribution Generalization and Detection2410.08000v1 · Haoyue Bai, Jifan Zhang, Robert Nowak2024 · 1 citationarXiv
ReLUs Are Sufficient for Learning Implicit Neural Representations2406.02529v2 · Joseph Shenouda, Yamin Zhou, Robert D. Nowak2024 · 3 citationsarXiv
An Experimental Design Framework for Label-Efficient Supervised Finetuning of Large Language Models2401.06692v3 · Gantavya Bhatt, Yifang Chen, Arnav M. Das et al.2024 · 7 citationsarXiv
Improved Algorithm for Deep Active Learning under Imbalance via Optimal Separation2312.09196v4 · Shyam Nuggehalli, Jifan Zhang, Lalit Jain et al.2023 · 2 citationsarXiv
Multi-task Representation Learning for Pure Exploration in Bilinear Bandits2311.00327v1 · Subhojyoti Mukherjee, Qiaomin Xie, Josiah P. Hanna et al.2023 · 0 citationsarXiv
On Penalty Methods for Nonconvex Bilevel Optimization and First-Order Stochastic Approximation2309.01753v2 · Jeongyeol Kwon, Dohyun Kwon, Stephen Wright et al.2023 · 1 citationarXiv
Weighted variation spaces and approximation by shallow ReLU networks2307.15772v2 · Ronald DeVore, Robert D. Nowak, Rahul Parhi et al.2023 · 4 citationsApplied and Computational Harmonic Analysis, vol. 74, no. 101713, pp. 1-22, 2025
LabelBench: A Comprehensive Framework for Benchmarking Adaptive Label-Efficient Learning2306.09910v4 · Jifan Zhang, Yifang Chen, Gregory Canal et al.2023 · 1 citationarXiv
Variation Spaces for Multi-Output Neural Networks: Insights on Multi-Task Learning and Network Compression2305.16534v3 · Joseph Shenouda, Rahul Parhi, Kangwook Lee et al.2023 · 1 citationJournal of Machine Learning Research, vol. 25, no. 231, pp. 1-40, 2024
Filtered Iterative Denoising for Linear Inverse Problems2302.07972v1 · Danica Fliss, Willem Marais, Robert D. Nowak2023 · 0 citationsarXiv
Algorithm Selection for Deep Active Learning with Imbalanced Datasets2302.07317v3 · Jifan Zhang, Shuai Shao, Saurabh Verma et al.2023 · 10 citationsarXiv
A Fully First-Order Method for Stochastic Bilevel Optimization2301.10945v1 · Jeongyeol Kwon, Dohyun Kwon, Stephen Wright et al.2023 · 8 citationsarXiv
Deep Learning Meets Sparse Regularization: A Signal Processing Perspective2301.09554v3 · Rahul Parhi, Robert D. Nowak2023 · 30 citationsIEEE Signal Processing Magazine, vol. 40, no. 6, pp. 63-74, Sept. 2023
Active Learning with Neural Networks: Insights from Nonparametric Statistics2210.08367v2 · Yinglun Zhu, Robert Nowak2022 · 0 citationsarXiv
PathProx: A Proximal Gradient Algorithm for Weight Decay Regularized Deep Neural Networks2210.03069v4 · Liu Yang, Jifan Zhang, Joseph Shenouda et al.2022 · 0 citationsarXiv
One for All: Simultaneous Metric and Preference Learning over Multiple Users2207.03609v1 · Gregory Canal, Blake Mason, Ramya Korlakai Vinayak et al.2022 · 3 citationsarXiv
A stochastic Farris transform for genetic data under the multispecies coalescent with applications to data requirements.35394192 · Dasarathy, Gautam, Mossel, Elchanan, Nowak, Robert et al.2022 · 5 citationsJournal of mathematical biology. 2022;84(5):36
Efficient Active Learning with Abstention2204.00043v3 · Yinglun Zhu, Robert Nowak2022 · 3 citationsarXiv
GALAXY: Graph-based Active Learning at the Extreme2202.01402v2 · Jifan Zhang, Julian Katz-Samuels, Robert Nowak2022 · 13 citationsarXiv
Nearly Optimal Algorithms for Level Set Estimation2111.01768v1 · Blake Mason, Romain Camilleri, Subhojyoti Mukherjee et al.2021 · 2 citationsarXiv
Near-Minimax Optimal Estimation With Shallow ReLU Neural Networks2109.08844v3 · Rahul Parhi, Robert D. Nowak2021 · 30 citationsIEEE Transactions on Information Theory, vol. 69, no. 2, pp. 1125-1140, Feb. 2023
Near Instance Optimal Model Selection for Pure Exploration Linear Bandits2109.05131v2 · Yinglun Zhu, Julian Katz-Samuels, Robert Nowak2021 · 0 citationsarXiv
Pure Exploration in Kernel and Neural Bandits2106.12034v2 · Yinglun Zhu, Dongruo Zhou, Ruoxi Jiang et al.2021 · 4 citationsarXiv
What Kinds of Functions do Deep Neural Networks Learn? Insights from Variational Spline Theory2105.03361v3 · Rahul Parhi, Robert D. Nowak2021 · 37 citationsSIAM Journal on Mathematics of Data Science, vol. 4, no. 2, pp. 464-489, 2022
Correction to: Evidence for Distinct Facial Signals of Reward, Affiliation, and Dominance from Both Perception and Production Tasks.36042916 · Martin, Jared D, Wood, Adrienne, Cox, William T L et al.2022 · 0 citationsAffective science. 2021;2(1):31
Nearest Neighbor Search Under Uncertainty2103.05057v1 · Blake Mason, Ardhendu Tripathy, Robert Nowak2021 · 0 citationsarXiv
Pareto Optimal Model Selection in Linear Bandits2102.06593v2 · Yinglun Zhu, Robert Nowak2021 · 1 citationarXiv
Evidence for Distinct Facial Signals of Reward, Affiliation, and Dominance from Both Perception and Production Tasks.34368782 · Martin, Jared D, Wood, Adrienne, Cox, William T L et al.2024 · 46 citationsAffective science. 2021;2(1):14-30
Chernoff Sampling for Active Testing and Extension to Active Regression2012.08073v4 · Subhojyoti Mukherjee, Ardhendu Tripathy, Robert Nowak2020 · 1 citationarXiv
Similarity Search for Efficient Active Learning and Search of Rare Concepts2007.00077v2 · Cody Coleman, Edward Chou, Julian Katz-Samuels et al.2020 · 25 citationsarXiv
On Regret with Multiple Best Arms2006.14785v2 · Yinglun Zhu, Robert Nowak2020 · 4 citationsarXiv
Finding All {\epsilon}-Good Arms in Stochastic Bandits2006.08850v2 · Blake Mason, Lalit Jain, Ardhendu Tripathy et al.2020 · 5 citationsarXiv
Banach Space Representer Theorems for Neural Networks and Ridge Splines2006.05626v3 · Rahul Parhi, Robert D. Nowak2020 · 43 citationsJournal of Machine Learning Research, vol. 22, no. 43, pp. 1-40, 2021
Optimal Confidence Regions for the Multinomial Parameter2002.01044v2 · Matthew L. Malloy, Ardhendu Tripathy, Robert D. Nowak2020 · 7 citationsarXiv
The Role of Neural Network Activation Functions1910.02333v3 · Rahul Parhi, Robert D. Nowak2019 · 133 citationsIEEE Signal Processing Letters, vol. 27, pp. 1779-1783, 2020
Cognitive Task Analysis for Implicit Knowledge About Visual Representations With Similarity Learning Methods.31529528 · Mason, Blake, Rau, Martina A, Nowak, Robert2020 · 5 citationsCognitive science. 2019;43(9):e12744
Should Adversarial Attacks Use Pixel p-Norm?1906.02439v1 · Ayon Sen, Xiaojin Zhu, Liam Marshall et al.2019 · 15 citationsarXiv
MaxGap Bandit: Adaptive Algorithms for Approximate Ranking1906.00547v1 · Sumeet Katariya, Ardhendu Tripathy, Robert Nowak2019 · 3 citationsarXiv
Learning Nearest Neighbor Graphs from Noisy Distance Samples1905.13267v1 · Blake Mason, Ardhendu Tripathy, Robert Nowak2019 · 3 citationsarXiv
Career total: 354 works. 108 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.