Publications

Google Scholar Profiles

Recent Publications

2024
- Taming False Positives in Out-of-Distribution Detection with Human Feedback
  Harit Vishwakarma, Heguang Lin, Ramya Korlakai Vinayak
  AISTATS 2024
- Learning Populations of Preferences via Pairwise Comparison Queries
  Gokcan Tatli, Reid (Yi) Chen, Ramya Korlakai Vinayak
  AISTATS, 2024
- The Expressive Power of Low-Rank Adaptation
  Yuchen Zeng and Kangwook Lee
  ICLR 2024
- Image Clustering Conditioned on Text Criteria
  Sehyun Kwon, Jaeseung Park, Minkyu Kim, Jaewoong Cho, Ernest K. Ryu, and Kangwook Lee
  ICLR 2024
- Teaching Arithmetic to Small Transformers
  Nayoung Lee, Kartik Sreenivasan, Jason Lee, Kangwook Lee, and Dimitris Papailiopoulos
  ICLR 2024
- Looped Transformers are Better at Learning Learning Algorithms
  Liu Yang, Kangwook Lee, Robert D Nowak, and Dimitris Papailiopoulos
  ICLR 2024
- Limitations of Face Image Generation
  Harrison Rosenberg, Shimaa Ahmed, Guruprasad V Ramesh, Ramya Korlakai Vinayak, Kassem Fawaz
  AAAI, 2024
2023
- Crowdsourced Clustering via Active Querying: Practical Algorithm with Theoretical Guarantees
  Reid (Yi) Chen, Ramya Korlakai Vinayak, Babak Hassibi
  AAAI HCOMP, 2023
- Efficiently Learning Relative Similarity Embeddings with Crowdsourcing
  
  Scott Sievert, Robert Nowak, Timothy Rogers
  
  Journal of Open Source Software
- Deep learning meets sparse regularization: A signal processing perspective
  
  Rahul Parhi, Robert D Nowak
  
  IEEE Signal Processing Magazine
- A Continuous Transform for Localized Ridgelets
  
  Joseph Shenouda, Rahul Parhi, Robert D Nowak
  
  SampTA 2023
- Promises and Pitfalls of Threshold-based Auto-labeling
  Harit Vishwakarma, Heguang Lin, Frederic Sala, Ramya Korlakai Vinayak
  NeurIPS, 2023. (Spotlight).
- Algorithm Selection for Deep Active Learning with Imbalanced Datasets
  
  Jifan Zhang, Shuai Shao, Saurabh Verma, Robert Nowak
  
  NeurIPS 2023
- Multi-task Representation Learning for Pure Exploration in Bilinear Bandits
  
  Subhojyoti Mukherjee, Qiaomin Xie, Josiah P Hanna, Robert Nowak
  
  NeurIPS 2023
- DPOK: Reinforcement Learning for Fine-tuning Text-to-Image Diffusion Models
  Ying Fan, Olivia Watkins, Yuqing Du, Hao Liu, Moonkyung Ryu, Craig Boutilier, Pieter Abbeel, Mohammad Ghavamzadeh, Kangwook Lee, Kimin Lee
  NeurIPS 2023
- Prompted LLMs as Chatbot Modules for Long Open-domain Conversation
  Gibbeum Lee, Volker Hartmann, Jongho Park, Dimitris Papailiopoulos, and Kangwook Lee
  ACL 2023 (Findings, Short)
- Why Is Prompt Tuning for Vision-Language Models Robust to Noisy Labels?
  Cheng-En Wu, Yu Tian, Haichao Yu, Heng Wang, Pedro Morgado, Yu Hen Hu, Linjie Yang
  ICCV 2023
- A Unified Audio-Visual Learning Framework for Localization, Separation, and Recognition
  Shentong Mo, Pedro Morgado
  ICML 2023

- Feed two birds with one scone: Exploiting wild data for both out-of-distribution generalization and detection
  
  Haoyue Bai, Gregory Canal, Xuefeng Du, Jeongyeol Kwon, Robert D Nowak, Yixuan Li
  
  ICML 2023
- A fully first-order method for stochastic bilevel optimization
  
  Jeongyeol Kwon, Dohyun Kwon, Stephen Wright, Robert D Nowak
  
  ICML 2023
- Improving Fair Training under Correlation Shifts
  Yuji Roh, Kangwook Lee, Steven Euijong Whang, Changho Suh
  ICML 2023
- Optimizing DDPM Sampling with Shortcut Fine-Tuning
  Ying Fan, Kangwook Lee
  ICML 2023
- Looped Transformers as Programmable Computers
  Angeliki Giannou*, Shashank Rajput*, Jy-yong Sohn, Kangwook Lee, Jason D. Lee, Dimitris Papailiopoulos
  ICML 2023
- Equal Improvability: A New Fairness Notion Considering the Long-Term Impact
  Ozgur Guldogan*, Yuchen Zeng*, Jy-yong Sohn, Ramtin Pedarsani, and Kangwook Lee
  ICLR 2023
2022
- Efficient Active Learning with Abstention
  Y. Zhu, and R. Nowak
  NeurIPS 2022
- Active learning with neural networks: Insights from nonparametric statistics
  Y. Zhu, and R. Nowak
  NeurIPS 2022
- One for All: Simultaneous Metric and Preference Learning over Multiple Users
  G. Canal, B. Mason, R. K. Vinayak, and R. Nowak
  NeurIPS 2022
- Rare Gems: Finding Lottery Tickets at Initialization
  K. Sreenivasan, J. Sohn, L. Yang, M. Grinde, A. Nagle, H. Wang, E. P. Xing, K. Lee, and D. Papailiopoulos
  NeurIPS 2022
- LIFT: Language-Interfaced FineTuning for Non-Language Machine Learning Tasks
  T. Dinh, Y. Zeng, R. Zhang, Z. Lin, S. Rajput, M. Gira, J. Sohn, D. Papailiopoulos, and K. Lee
  NeurIPS 2022
- Score-based generative modeling secretly minimizes the Wasserstein distance
  D. Kwon, Y. Fan, and K. Lee
  NeurIPS 2022
- Utilizing Language-Image Pretraining for Efficient and Robust Bilingual Word Alignment
  T. Dinh, J. Sohn, S. Rajput, T. Ossowski, Y. Ming, J. Hu, D. Papailiopoulos, and K. Lee
  Findings of EMNLP 2022
- Near-minimax optimal estimation with shallow ReLU neural networksR. Parhi, and R. Nowak
  IEEE Transactions on Information Theory
- ReVar: Strengthening policy evaluation via reduced variance sampling
  S. Mukherjee, J. P. Hanna, R. Nowak
  UAI 2022
- Similarity search for efficient active learning and search of rare concepts
  C. Coleman, E. Chou, J. Katz-Samuels, S. Culatana, P. Bailis, A. C. Berg, R. Nowak, R. Sumbaly, M. Zaharia, and I. Z. Yalniz
  AAAI 2022
- On Continuous-Domain Inverse Problems with Sparse Superpositions of Decaying Sinusoids as Solutions
  R. Parhi, and R. Nowak
  ICASSP 2022
- A stochastic Farris transform for genetic data under the multispecies coalescent with applications to data requirements
  G. Dasarathy, E. Mossel, R. Nowak, and S. Roch
  Journal of Mathematical Biology 84 (5), 1-37
- What kinds of functions do deep neural networks learn? Insights from variational spline theory
  R. Parhi, and R. Nowak
  SIAM Journal on Mathematics of Data Science 4 (2), 464-489
- Near Instance Optimal Model Selection for Pure Exploration Linear Bandits
  Y. Zhu, J. Katz-Samuels, and R. Nowak
  AISTATS 2022
- Pareto optimal model selection in linear bandits
  Y. Zhu, and R. Nowak
  AISTATS 2022
- Finding Nearly Everything within Random Binary Networks
  K. Sreenivasan, S. Rajput, J. Sohn, D. Papailiopoulos
  AISTATS 2022
- Learning Preference Distributions From Distance Measurements
  G. Tatli, R. Nowak, and R. K. Vinayak
  Allerton Conference on Communication, Control, and Computing 2022
- Fisher-Pitman permutation tests based on nonparametric Poisson mixtures with application to single cell genomics
  Z. Miao, W. Kong, R. K. Vinayak, W. Sun, and F. Han
  Journal of the American Statistical Association 2022
- Breaking Fair Binary Classification with Optimal Flipping Attacks
  C. Jo, J. Sohn, and K. Lee
  ISIT 2022
- GALAXY: Graph-based Active Learning at the Extreme
  J. Zhang, J. Katz-Samuels, and R. Nowak
  ICML 2022
- Training ood detectors in their natural habitats
  J. Katz-Samuels, J. B. Nakhleh, R. Nowak, Y. Li
  ICML 2022
- GenLabel: Mixup Relabeling using Generative Models
  J. Sohn, L. Shang, H. Chen, J. Moon, D. Papailiopoulos, and K. Lee
  ICML 2022
- Permutation-Based SGD: Is Random Optimal?
  S. Rajput, K. Lee, and D. Papailiopoulos
  ICLR 2022
2021
- Pure exploration in kernel and neural bandits
  Y. Zhu, D. Zhou, R. Jiang, Q. Gu, R. Willett, R. Nowak
  NeurIPS 2021
- Practical, Provably-Correct Interactive Learning in the Realizable Setting: The Power of True Believers
  J. Katz-Samuels, B. Mason, K. Jamieson, R. Nowak
  NeurIPS 2021
- An Exponential Improvement on the Memorization Capacity of Deep Threshold Networks
  S Rajput, K Sreenivasan, D Papailiopoulos, A Karbasi
  NeurIPS 2021
- Sample Selection for Fair and Robust Training
  Y. Roh, K. Lee, S. Whang, and C. Suh
  NeurIPS 2021
- Gradient Inversion with Generative Image Prior
  J. Kim, J. Jeon, K. Lee, S. Oh, and J. Ok
  NeurIPS 2021
- Fisher-Pitman permutation tests based on nonparametric Poisson mixtures with application to single cell genomics
  Z. Miao, W. Kong, R. Korlakai Vinayak, W. Sun, and F. Han
- Coded-InvNet for Resilient Prediction Serving Systems
  T. Dinh and K. Lee
  ICML 2021
- Discrete-Valued Latent Preference Matrix Estimation with Graph Side Information
  C. Jo and K. Lee
  ICML 2021
- Pufferfish: Communication-efficient Models At No Extra Cost
  H. Wang, S. Agarwal, and D. Papailiopoulos
  MLSys 2021
- Tensor Methods for Nonlinear Matrix Completion
  G Ongie, D Pimentel-Alarcón, L Balzano, R Willett, RD Nowak
  
  SIAM Journal on Mathematics of Data Science 3 (1), 253-279
- Accordion: Adaptive Gradient Communication via Critical Learning Regime Identification
  S. Agarwal, H. Wang, K. Lee, S. Venkataraman, and D. Papailiopoulos
  MLSys 2021
- FairBatch: Batch Selection for Model Fairness
  Y. Roh, K. Lee, S. Whang, and C. Suh
  ICLR 2021
- Banach space representer theorems for neural networks and ridge splines
  R Parhi, RD Nowak
  
  Journal of Machine Learning Research 22 (43), 1-40
2020
- Maximin active learning in overparameterized model classes
  M Karzand, RD Nowak
  
  IEEE Journal on Selected Areas in Information Theory 1 (1), 167-177
- Concentration inequalities for the empirical distribution of discrete distributions: beyond the method of types
  J Mardia, J Jiao, E Tánczos, RD Nowak, T Weissman
  
  Information and Inference: A Journal of the IMA 9 (4), 813-850
- Optimal Lottery Tickets via SubsetSum: Logarithmic Over-Parameterization is Sufficient
  A. Pensia, S. Rajput, A. Nagle, H. Vishwakarma, D. Papailiopoulos
  NeurIPS 2020 (spotlight)
- Attack of the Tails: Yes, You Really Can Backdoor Federated Learning
  H. Wang, K. Sreenivasan, S. Rajput, H. Vishwakarma, S. Agarwal, J. Sohn, K. Lee, and D. Papailiopoulos
  NeurIPS 2020
- Bad Global Minima Exist and SGD Can Reach Them
  S. Liu, D. Papailiopoulos, D. Achlioptas
  NeurIPS 2020
- Finding All ϵ -Good Arms in Stochastic Bandits
  B Mason, L Jain, AS Tripathy, R Nowak
  NeuIPS 2020
- Reprogramming GANs via Input Noise Design
  K. Lee, C. Suh, and K. Ramchandran
  ECML PKDD 2020
- Popular Imperceptibility Measures in Visual Adversarial Attacks are Far from Human Perception
  A Sen, X Zhu, E Marshall, R Nowak
  
  International Conference on Decision and Game Theory for Security 2020
- Robust Outlier Arm Identification
  Y Zhu, S Katariya, R Nowak
  
  ICML 2020
- Estimating the number and effect sizes of non-null hypotheses
  J. Brennan, R. Korlakai Vinayak, K. Jamieson
  ICML 2020
- The role of neural network activation functions
  R Parhi, RD Nowak
  
  IEEE Signal Processing Letters 2020
- Federated Learning with Matched Averaging
  H. Wang, M. Yurochkin, Y. Sun, D. Papailiopoulos, Y. Khazaeni
  ICLR 2020 (oral)
- FR-Train: A mutual information-based approach to fair and robust training
  Y. Roh, K. Lee, S. Whang, and C. Suh
  ICML 2020
- Closing the Convergence Gap of SGD without Replacement
  S. Rajput, A. Gupta, D. Papailiopoulos
  ICML 2020
- Linear bandits with feature feedback
  U Oswal, A Bhargava, R Nowak
  
  AAAI 2020
2019
- DETOX: A Redundancy-based Framework for Faster and More Robust Gradient Aggregation?
  S. Rajput, H. Wang, Z. Charles, and D. Papailiopoulos
  NeurIPS 2019
- Maxgap bandit: Adaptive algorithms for approximate ranking
  S Katariya, A Tripathy, R Nowak
  NeurIPS 2019
- Learning nearest neighbor graphs from noisy distance samples
  B Mason, A Tripathy, R Nowak
  NeurIPS 2019
- Maximum Likelihood Estimation for Learning Populations of Parameters
  R. Korlakai Vinayak, W. Kong, G. Valiant, and S. Kakade
  ICML 2019
- Does Data Augmentation Lead to Positive Margin?
  S. Rajput, Z. Feng, Z. Charles, P.-L. Loh, and D. Papailiopoulos
  ICML 2019
- Bilinear bandits with low-rank structure
  KS Jun, R Willett, S Wright, R Nowak
  
  ICML 2019
- The Illusion of Change: Correcting for Bias when Inferring Changes in Sparse, Societal-Scale Data
  G. Cadamuro, R. Korlakai Vinayak, J. Blumenstock, S. Kakade, and J. N. Shapiro
  WWW 2019
- Crash to Not Crash: Learn to Identify Dangerous Vehicles using a Simulator
  H. Kim*, K. Lee*, G. Hwang, and C. Suh
  AAAI 2019 (oral)
<= 2018
- Binary Rating Estimation with Graph Side Information
  K. Ahn, K. Lee, H. Cha, and C. Suh
  NeurIPS 2018
- Simulated+Unsupervised Learning With Adaptive Data Generation and Bidirectional Mappings
  K. Lee*, H. Kim*, and C. Suh
  ICLR 2018