I am grateful for all of the wonderful collaborations that have led to the publications listed here.
Preprints/submissions
- Guanghui Wang, Krishna Acharya, Lokranjan Lakshmikanthan, Vidya Muthukumar and Juba Ziani: “Multi-agent performative prediction beyond the insensitivity assumption: A case study in mortgage competition”.
- Adhyyan Narang, Vidya Muthukumar and Anant Sahai: “Classification and adversarial examples in an overparameterized linear model: A signal-processing perspective”, short version at ICML’21 Workshop on Overparameterization: Pitfalls and Opportunities.
- Yehuda Dar, Vidya Muthukumar and Richard G. Baraniuk: “A farewell to the bias-variance tradeoff? An overview of the theory of overparameterized machine learning”.
Journal papers (under revision)
- Guanghui Wang, Zihao Hu, Claudio Gentile, Vidya Muthukumar and Jacob Abernethy: “Faster margin maximization rates for generic and adversarially robust optimization methods”, minor revision at Mathematical Programming Series B (special issue on Optimization for Machine Learning).
- Kuo-Wei Lai and Vidya Muthukumar: “General Loss Functions Lead to (Approximate) Interpolation in High Dimensions”, major revision at Journal of Machine Learning Research.
Journal papers (accepted)
- Ashwin Pananjady, Vidya Muthukumar and Andrew Thangaraj: “Just Wing It: Optimal Estimation of Missing Mass in a Markovian Sequence”, Journal of Machine Learning Research, 2024 issue.
- Vidya Muthukumar, Soham Phade and Anant Sahai: “On the impossibility of convergence of strategies arising from no-regret learning”, Mathematics of Operations Research, 2024 issue.
- Chiraag Kaushik, Andrew McRae, Mark Davenport and Vidya Muthukumar: “New equivalences between interpolation and SVMs: Kernels and structured features”, SIAM Journal on Mathematics of Data Science, 2024 issue.
- Chi-Heng Lin, Chiraag Kaushik, Eva L. Dyer and Vidya Muthukumar: “The good, bad and ugly sides of data augmentation: An implicit spectral regularization perspective”, Journal of Machine Learning Research, 2024 issue.
- Jonathan N. Lee, Weihao Kong, Aldo Pacchiano, Vidya Muthukumar and Emma Brunskill: “Estimating optimal policy value in general linear contextual bandits”, Transactions of Machine Learning Research, 2024 issue.
- Ke Wang, Vidya Muthukumar and Christos Thrampoulidis: “Benign overfitting in multiclass classification: All roads lead to interpolation”, IEEE Transactions on Information Theory, 2023 issue.
- Daniel Hsu, Vidya Muthukumar and Ji Xu: “On the proliferation of support vectors in high dimensions”, Journal of Statistical Mechanics: Theory and Experiment (special issue, Machine Learning, 2022).
- Vidya Muthukumar, Adhyyan Narang, Vignesh Subramanian, Mikhail Belkin, Daniel Hsu and Anant Sahai: “Classification vs regression in overparameterized regimes: Does the loss function matter?”, Journal of Machine Learning Research, 2021 issue.
- Vidya Muthukumar, Kailas Vodrahalli, Vignesh Subramanian and Anant Sahai: “Harmless interpolation of noisy data in linear regression”, IEEE Journal of Selected Areas in Information Theory, inaugural special issue on “Deep Learning: Mathematical Foundations and Applications to Information Science”, 2020 issue.
- Ashwin Pananjady, Cheng Mao, Vidya Muthukumar, Martin Wainwright and Thomas Courtade: “Worst-case v.s. Average-case Design for Estimation from Fixed Pairwise Comparisons”, Annals of Statistics, 2020 issue.
- Vidya Muhukumar and Anant Sahai: “Fundamental limits on ex-post enforcement and implications for spectrum rights”, IEEE Transactions on Cognitive Communications and Networking, 2017 issue.
Conference papers
- Milind Nakul, Vidya Muthukumar and Ashwin Pananjady: “Estimating stationary mass, frequency by frequency”, to appear in Conference on Learning Theory (COLT), Lyon, 2025.
- Rohan Ghuge, Vidya Muthukumar and Sahil Singla: “Improved and oracle-efficient online $\ell_1$-multicalibration”, to appear in International Conference on Machine Learning (ICML), Vancouver, 2025.
- Tyler LaBonte*, Kuo-Wei Lai* and Vidya Muthukumar: “Task Shift: From Classification to Regression in Overparameterized Linear Models”, International Conference on Artificial Intelligence and Statistics (AISTATS), Phuket, 2025.
- Tyler LaBonte, Jack Hill, Xinchen Zhang, Vidya Muthukumar and Abhishek Kumar: “The Group Robustness is in the Details: Revisiting Finetuning Under Spurious Correlations”, Neural Information Processing Systems (NeurIPS), Vancouver, 2024.
- Chiraag Kaushik, Justin Romberg and Vidya Muthukumar: “Precise asymptotics of reweighted least-squares algorithms for linear diagonal networks”, Neural Information Processing Systems (NeurIPS), Vancouver, 2024.
- Chiraag Kaushik, Ran Liu, Chi-Heng Lin, Amrit Khera, Matthew Y Jin, Wenrui Ma, Vidya Muthukumar and Eva L Dyer: “Balanced Data, Imbalanced Spectra: Unveiling Class Disparities with Spectral Imbalance”, International Conference on Machine Learning (ICML), Vienna, 2024.
- Etash Guha, Jim James, Krishna Acharya, Vidya Muthukumar and Ashwin Pananjady: “One shot inverse reinforcement learning for stochastic linear bandits”, Uncertainty in Artificial Intelligence (UAI), Barcelona, 2024.
- Kuo-Wei Lai and Vidya Muthukumar: “Sharp analysis of out-of-distribution error for “importance-weighted” estimators in the overparameterized regime”, IEEE International Symposium on Information Theory (ISIT), Athens, 2024.
- Tyler LaBonte, Vidya Muthukumar and Abhishek Kumar: “Towards last-layer retraining for group robustness with fewer annotations”, Neural Information Processing Systems (NeurIPS), New Orleans, 2023.
- Guanghui Wang, Zihao Hu, Vidya Muthukumar and Jacob Abernethy: “Faster margin maximization rates for generic optimization methods”, Neural Information Processing Systems (NeurIPS), New Orleans, 2023 (spotlight).
- Yujia Jin, Vidya Muthukumar and Aaron Sidford: “The complexity of infinite-horizon general-sum stochastic games”, Innovations in Theoretical Computer Science (ITCS) 2023.
- Guanghui Wang, Zihao Hu, Vidya Muthukumar and Jacob Abernethy: “Adaptive oracle-efficient online learning”, Neural Information Processing Systems (NeurIPS), New Orleans, 2022.
- Vidya Muthukumar and Akshay Krishnamurthy: “Universal and data-adaptive algorithms for model selection in linear contextual bandits”, International Conference on Machine Learning (ICML), Baltimore, 2022.
- Andrew D. McRae, Santhosh Karnik, Mark A. Davenport and Vidya Muthukumar: “Harmless interpolation in regression and classification with structured features”, International Conference on Artificial Intelligence and Statistics (AISTATS), 2022 (virtual).
- Wenshuo Guo, Kumar Krishna Agarwal, Aditya Grover, Vidya Muthukumar and Ashwin Pananjady: “Learning from an exploring demonstrator: Optimal reward estimation for bandits”., International Conference on Artificial Intelligence and Statistics (AISTATS), 2022 (virtual), short versions at ICML’21 Workshop on Human-AI Collaboration in Sequential Decision-Making (spotlight talk) and ICML’21 Workshop on Reinforcement Learning Theory.
- Ke Wang, Vidya Muthukumar and Christos Thrampoulidis: “Benign overfitting in multiclass classification: All roads lead to interpolation”, Neural Information Processing Systems (NeurIPS), 2021 (virtual), short version at ICML’21 Workshop on Overparameterization: Pitfalls and Opportunities.
- Jonathan N. Lee, Aldo Pacchiano, Vidya Muthukumar, Weihao Kong and Emma Brunskill, “Online model selection for reinforcement learning with function approximation”, International Conference on Artificial Intelligence and Statistics (AISTATS), 2021 (virtual).
- Daniel Hsu, Vidya Muthukumar and Ji Xu: “On the proliferation of support vectors in high dimensions”, International Conference on Artificial Intelligence and Statistics (AISTATS), 2021 (virtual).
- Niladri S. Chatterji, Vidya Muthukumar and Peter L. Bartlett: “OSOM: A Simultaneously Optimal Algorithm for the Multi-Armed and the Linear Contextual Bandit Problems”, International Conference on Artificial Intelligence and Statistics (AISTATS), 2020 (virtual).
- Vidya Muthukumar, Kailas Vodrahalli and Anant Sahai: “Harmless interpolation in noisy linear regression”, IEEE International Symposium on Information Theory, Paris, 2019.
- Vidya Muthukumar: “Color-theoretic Explanations for Understanding Unequal Gender Classification Accuracy from Face Images”, IEEE CVPR Workshop on Bias Estimation in Face Analytics, Los Angeles, 2019.
- Vidya Muthukumar, Mitas Ray, Anant Sahai and Peter L. Bartlett: “Best of many worlds: Robust model selection for online supervised learning”, International Conference on Artificial Intelligence and Statistics (AISTATS), 2019, Naha, Okinawa.
- Vidya Muthukumar and Anant Sahai: “Robust commitments and partial reputation”, ACM Economics and Computation, Phoenix, 2019; shorter version presented at Neural Information Processing Systems Workshop on Learning in the Presence of Strategic Behavior, Los Angeles, 2017
- Vidya Muthukumar and Anant Sahai: “Commitment in regulatory spectrum games: Examining the first-player advantage”, IEEE International Symposium on Information Theory, Aachen, 2017.
- Vidya Muthukumar and Anant Sahai: “Fundamental limits on ex-post enforcement and implications for spectrum rights”, IEEE Symposium on Dynamic Spectrum Access Networks, Baltimore, 2017.
- Kate Harrison, Vidya Muthukumar and Anant Sahai: “Whitespace Evaluation SofTware (WEST) and its applications to whitespace in Canada and Australia”, IEEE Symposium on Dynamic Spectrum Access Networks, Stockholm, 2015.
- Vidya Muthukumar, Angel Daruna, Vijay Kamble, Kate Harrison and Anant Sahai: “Whitespaces after the USA’s TV incentive auction: a spectrum reallocation case study”, IEEE International Conference on Communications, London, 2015.
- Matthew Thill, Vidya Muthukumar and Babak Hassibi: “Frames from Generalized Group Fourier Transforms and SL2(Fq)”, IEEE International Conference on Acoustics, Speech and Signal Processing, Florence, 2014.
Unpublished manuscripts
- Vidya Muthukumar: “Understanding Unequal Gender Classification Accuracy From Face Images”.