Publications
Preprints/Under Preparation
RI. Sultan, C. Li, H. Zhu, P. Khanduri, M. Brocanelli, and D. Zhu, "GeoSAM: Fine-Tuning SAM with Sparse and Dense Visual Prompting for Automated Segmentation of Mobility Infrastructure," arXiv, Nov 2023.
P. Khanduri, C. Li, RI. Sultan, Y. Qiang, J. Kliewer, and D. Zhu, "FedDRO: Federated Compositional Optimization for Distributionally Robust Learning," arXiv, Nov 2023.
Y. Qiang, C. Li, P. Khanduri, and D. Zhu, "Interpretability-Aware Vision Transformer," arXiv, Sep 2023.
C. Li, P. Khanduri, Y. Qiang, R. Sultan, I. Chetty, and D. Zhu, "Auto-Prompting SAM for Mobile Friendly 3D Medical Image Segmentation," arXiv, Aug 2023.
P. Khanduri, S. Zeng, M. Hong, H-T Wai, Z. Wang, and Z. Yang, “A Momentum-Assisted Single-Timescale Stochastic Approximation Algorithm for Bilevel Optimization,” arXiv, Feb 2021.
P. Sharma, S. Kafle, P. Khanduri, S. Bulusu, K. Rajawat, and P. K. Varshney, "Parallel Restarted SPIDER - Communication Efficient Distributed Nonconvex Optimization with Optimal Computation Complexity," arXiv, Nov 2020.
P. Khanduri, P. Sharma, S. Kafle, S. Bulusu, K. Rajawat, and P. K. Varshney, “Distributed Stochastic Non-Convex Optimization: Momentum-Based Variance Reduction,” arXiv, May 2020.
Journals
Y. Zhang, P. Khanduri, I. Tsaknakis, Y. Yao, M. Hong, and S. Liu, "An Introduction to Bi-Level Optimization: Foundations and Applications in Signal Processing and Machine Learning," vol: 41, no. 1, pp. 38 - 59 IEEE Signal Process. Magazine, 2024.
S. Bulusu, P. Khanduri, S. Kafle, P. Sharma, and P. K. Varshney, "Byzantine Resilient Non-Convex SCSG with Distributed Batch Gradient Computations," vol. 7, pp. 754 - 766 IEEE Trans. Signal Inf. Process. Netw., 2021.
X. Cheng, P. Khanduri, B. Chen, and P. K. Varshney, "Joint Collaboration and Compression Design for Distributed Sequential Estimation in a Wireless Sensor Network," vol. 69, pp. 5448 - 5462 IEEE Trans. Signal Process., 2021.
X. Cheng, B. Chen, P. Khanduri, B. Chen, and P. K. Varshney, "Joint Collaboration and Compression Design for Random Signal Detection in a Wireless Sensor Network," vol. 28, pp. 1630 - 1634, IEEE Signal Process. Lett., 2021.
S. Zhang, P. Khanduri, and P. K. Varshney, "Distributed Sequential Detection: Dependent Observations and Imperfect Communication," vol. 68, pp. 830 - 842, IEEE Trans. Signal Process., 2020.
P. Khanduri, D. Pastor, V. Sharma, and P. K. Varshney, "Sequential Random Distortion Testing of Non-Stationary Processes," vol. 67, no. 21, pp. 5450 - 5462, IEEE Trans. Signal Process., 2019.
P. Khanduri, L. N. Theagarajan, and P. K. Varshney, "Online Design of Optimal Precoders for High Dimensional Signal Detection," vol. 67, no. 15, pp. 4122 - 4135, IEEE Trans. Signal Process., 2019.
P. Khanduri, D. Pastor, V. Sharma, and P. K. Varshney, "Truncated Sequential Non-Parametric Hypothesis Testing Based on Random Distortion Testing," vol. 67, no. 15, pp. 4027 - 4042, IEEE Trans. Signal Process., 2019.
P. Khanduri, B. Kailkhura, J. J. Thiagarajan, and P. K. Varshney, “Universal Collaboration Strategies for Signal Detection: A Sparse Learning Approach,” vol. 23, no. 10, pp. 1484 - 1488, IEEE Signal Process. Lett., 2016.
Conferences/Workshops
Machine Learning Conferences/Workshops
Y. Qiang, C. Li, P. Khanduri, and D. Zhu, "Fairness-aware Vision Transformer via Debiased Self-Attention," ECCV, 2024.
H. Yang, P. Qiu, P. Khanduri, M. Fang, and J. Liu, "Understanding Server-Assisted Federated Learning in the Presence of Incomplete Client Participation," ICML, 2024.
M. Fang, Z. Zhang, Hairi, P. Khanduri, J. Liu, S. Lu, Y. Liu, and N. Gong, "Toward Byzantine-robust Decentralized Federated Learning," ACM CCS, 2024.
C. Li, Yao Qiang, R. Sultan, H Bagher-Ebadian, P. Khanduri, I. Chetty, and D. Zhu, "FocalUNETR: A Focal Transformer for Boundary-aware Segmentation of CT Images" MICCAI, 2023.
P. Khanduri, C. Li, R. Sultan, Y. Qiang, J. Kliewer, and D. Zhu, "Proximal Compositional Optimization for Distributionally Robust Learning" AdvML-Frontiers, ICML Workshop, 2023.
B. Song, P. Khanduri*, X. Zhang*, J. Yi, and M. Hong, "FedAvg Converges to Zero Training Loss Linearly for Overparameterized Multi-Layer Neural Networks," ICML, 2023.
P. Khanduri*, I. Tsaknakis*, Y. Zhang, J. Liu, S. Liu, J. Zhang, and M. Hong, "Linearly Constrained Bilevel Optimization: A Smoothed Implicit Gradient Approach," ICML, 2023.
Z. Liu, X. Zhang, P. Khanduri, S. Lu, and J. Liu, "Prometheus: Taming Sample and Communication Complexities in Constrained Decentralized Stochastic Bilevel Learning," ICML, 2023.
H. Yang, P. Qiu, P. Khanduri, and J. Liu, "With a Little Help from My Friend: Server-Aided Federated Learning with Partial Client Participation," FL-NeurIPS, 2022.
Y. Zhang, G. Zhang, P. Khanduri, M. Hong, S. Chang, and S. Liu, "Revisiting and Advancing Fast Adversarial Training Through The Lens of Bi-Level Optimization," ICML, 2022.
H. Yang, X. Zhang, P. Khanduri, and J. Liu, "Anarchic Federated Learning," ICML, 2022. (Long Presentation)
P. Khanduri, H. Yang, M. Hong, J. Liu, H-T Wai, and S. Liu, "Decentralized Learning for Overparameterized Problems: A Multi-Agent Kernel Approximation Approach," ICLR, 2022.
P. Khanduri, S. Zeng, M. Hong, H-T Wai, Z. Wang, and Z. Yang, “A Near-Optimal Algorithm for Stochastic Bilevel Optimization via Double-Momentum,” NeurIPS, 2021.
P. Khanduri, P. Sharma, H. Yang, M. Hong, J. Liu, K. Rajawat, and P. K. Varshney, "STEM: A Stochastic Two-Sided Momentum Algorithm Achieving Near-Optimal Sample and Communication Complexities for Federated Learning," NeurIPS, 2021.
P. Khanduri, P. Sharma, H. Yang, M. Hong, J. Liu, K. Rajawat, and P. K. Varshney, "Achieving Optimal Sample and Communication Complexities for Non-IID Federated Learning," FL-ICML'21, 2021.
P. Khanduri, S. Bulusu, P. Sharma, and P. K. Varshney, "Byzantine Resilient Non-Convex SVRG with Distributed Batch Gradient Computations," OPT2019, 2019.
K. R. Varshney, P. Khanduri, P. Sharma, S. Zhang, and P. K. Varshney, "Why Interpretability in Machine Learning? An Answer Using Distributed Detection and Data Fusion Theory," WHI, ICML, 2018.
Signal Processing Conferences
W. Ye, P. Khanduri, J. Peng, F. Tian, J. Gao, J. Ding, ZL Zhang, and M. Hong, "SHARE: A Distributed Learning Framework For Multivariate Time-Series Forecasting," SPAWC, 2024.
S. Maralappanavar, P. Khanduri, and B. N. Bharath, "FedAvg for Minimizing Polyak-Lojasiewicz Objectives: The Interpolation Regime," Asilomar, 2023.
I. Tsaknakis, P. Khanduri, and M. Hong, "An Implicit Gradient Method for Constrained Bilevel Problems using Barrier Approximation," ICASSP, 2023.
P. Qiu, Y. Li, Z. Liu, P. Khanduri, J. Liu, N. Shroff, E. S. Bentley, and K. Turck, "DIAMOND: Taming Sample and Communication Complexities in Decentralized Bilevel Optimization," IEEE INFOCOM, 2023.
Z. Liu, X. Zhang, P. Khanduri, S. Lu, and J. Liu, "INTERACT: Achieving Low Sample and Communication Complexities in Decentralized Bilevel Learning over Networks," MobiHoc, 2022.
I. Tsaknakis, P. Khanduri, and M. Hong, "An Implicit Gradient-Type Method for Linearly Constrained Bilevel Problems," ICASSP, 2022.
P. Sharma, P. Khanduri, L. Shen, D. J. Bucci Jr., and P. K. Varshney, “On Distributed Online Convex Optimization with Sublinear Dynamic Regret and Fit,” Asilomar, 2021.
S. Bulusu, P. Khanduri, P. Sharma, and P. K. Varshney, “On Distributed Stochastic Gradient Descent for Nonconvex Functions in the Presence of Byzantines,” ICASSP, 2020.
P. Khanduri, L. N. Theagarajan, and P. K. Varshney, "Online Linear Compression with Side Information for Distributed Detection of High Dimensional Signals," SPAWC, 2019. (Best Student Paper Award)
S. Zhang, P. Khanduri, and P. K. Varshney, "Distributed Sequential Hypothesis Testing with Dependent Sensor Observations," Asilomar, 2019.
P. Khanduri, D. Pastor, V. Sharma, and P. K. Varshney, "On Random Distortion Testing Based Sequential Non-parametric Hypothesis Testing," Allerton, 2018.
P. Khanduri, L. N. Theagarajan, and P. K. Varshney, "Online Design of Precoders for High Dimensional Signal Detection in Wireless Sensor Networks," FUSION, 2018.
P. Khanduri, D. Pastor, V. Sharma, and P. K. Varshney, "On Sequential Random Distortion Testing of Non-Stationary Processes," ICASSP, 2018.
P. Khanduri, A. Vempaty, and P. K. Varshney, "A Unified Diversity Measure for Distributed Inference,” ICASSP, 2017.
P. Khanduri, V. Sharma, and P. K. Varshney, "Detection Diversity of Spatio-Temporal Data using Pitman’s Efficiency for low SNR Regimes,” IEEE GlobalSIP, 2016.
P. Khanduri, B. N. Bharath, and C. R. Murthy, "Coverage Analysis and Training Optimization for Uplink Cellular Networks with Practical Channel Estimation,” IEEE Globecom, 2014.