Published Articles
Journal Publications
Bollapragada, R., Bramwell, J., Karamanli,C., Keith, B., Lazarov, B., &Petrides, S. Adaptive Sampling Augmented Lagrangian Methods for Stochastic Optimization. Computers & Mathematics with Applications, 2023. [arxiv]
Bollapragada, R. & Wild, S.M. Adaptive Sampling Quasi-Newton Methods for Derivative-Free Stochastic Optimization. Mathematical Programming Computation,, 2023 [Springer]
Bollapragada, R., Scieur, D., & D’Aspremont. A. Nonlinear Acceleration of Momentum and Primal-Dual Methods. Mathematical Programming, 2023. [Springer]
Xie, Y., Bollapragada, R., Byrd R., & Nocedal, J. Constrained and Composite Optimization via Adaptive Sampling Methods. IMA Journal of Numerical Analysis, 2023. [Download PDF]
Berahas, A. S., Bollapragada, R., & Wei, E. On the Convergence of Nested Decentralized Gradient Methods with Multiple Consensus and Gradient Steps. IEEE Transactions on Signal Processing, 2021. [IEEE]
Bollapragada, R., Menickelly, M., Nazarewicz W., O’Neal J., Reinhard P.G., & Wild, S.M. Optimization and Machine Learning Training Algorithms for Fitting Numerical Physics Models. Journal of Physics G: Nuclear and Particle Physics, 48(2), 2020. DOI:10.1088/1361-6471/abd009 [researchgate]
Berahas, A. S., Bollapragada, R., & Nocedal, J. An Investigation of Newton-Sketch and Subsampled Newton Methods. Optimization Methods and Software, 35(4):661–680, 2020. DOI: 10.1080/10556788.2020.1725751 [Download PDF]
Bollapragada, R., Byrd, R., & Nocedal, J. Adaptive Sampling Strategies for Stochastic Optimization. SIAM Journal on Optimization, 28(4): 3312 - 3343, 2019. DOI: 10.1137/17M1154679 [SIAMS]
Bollapragada, R., Byrd, R., & Nocedal, J. Exact and Inexact Subsampled Newton Methods for Optimization. IMA Journal of Numerical Analysis, 39(2): 545 - 578, 2019. DOI: 10.1093/imanum/dry009 [Download PDF]
Berahas, A. S., Bollapragada, R., Keskar, N. S., & Wei, E. Balancing Communication and Computation in Distributed Optimization. IEEE Transactions on Automatic Control, 64(8): 3141 - 3155, 2019. DOI: 10.1109/TAC.2018.2880407 [IEEE]
Vairamuthu, R., Vijaya Raghavendra, B., & Ramesh Babu, N. Kinematical Design of a Precision Cylindrical Grinder with Volumetric Error Modelling and Sensitivity Analysis. International Journal of Precision Technology, 6:193-215, 2016. DOI: 10.1504/IJPTECH.2016.079999
Conference Publications
Gupta, S., Singh, G., Bollapragada, R., & Lease, M. Learning a Neural Pareto Manifold Extractor with Constraints. In The 38th Conference on Uncertainty in Artificial Intelligence, Eindhoven, Netherlands, 2022. [MLR press]
Bollapragada, R., Scieur, D., & D’Aspremont, A. Nonlinear Acceleration of Primal-Dual Algorithms. In proceedings of the 22nd International Conference on Artificial Intelligence and Statistics (AISTATS), Okinawa, Japan, PMLR 89: 739 - 747, 2019. [MLR press]
Bollapragada, R., Mudigere, D., Nocedal, J., Shi, H.J.M., & Tang, P.T.P. A Progressive Batching L-BFGS Method for Machine Learning. In proceedings of the 35th International Conference on Machine Learning (ICML), Stockholm, Sweden, PMLR 80: 620 - 629, 2018. [MLR press]
Articles Under Review
Newton, D., Bollapragada, R., Pasupathy, R, & Yip, N., K. Retrospective Approximation for Smooth Stochastic Optimization. arXiv:2103.04392. (Status: First Revision, Mathematics of Operations Research)
Berahas, A. S., Bollapragada, R., & Zhou, B. An Adaptive Sampling Sequential Quadratic Programming Method for Equality Constrained Stochastic Optimization. arXiv:2206.00712. (Status: Submitted, Mathematics of Operations Research)
Bollapragada, R., Chen, T., &Ward, R. On the fast convergence of minibatch heavy ball momentum. arXiv:2206.07553. (Status: Submitted, IMA Journal of Numerical Analysis)
Berahas, A. S., Bollapragada, R., & Gupta, S. Balancing Communication and Computation in Gradient Tracking Algorithms for Decentralized Optimization. arXiv:2303.14289. (Status: Submitted, Journal of Optimization, Theory and Application)
Berahas, A. S., Bollapragada, R., & Gupta, S. A Flexible Gradient Tracking Algorithmic Framework for Decentralized Optimization. (Status: Submitted, Computational Optimization and Applications)
Shah, S., & Bollapragada, R. A stochastic gradient tracking algorithm for decentralized optimization with inexact communication. arXiv:2307.14942. (Status: Submitted, IEEE Transactions on Automatic Control)
Shah, S., Berahas, A. S., & Bollapragada, R. Adaptive Consensus: A network pruning approach for decentralized optimization. (Status: Submitted, SIAM Journal on Optimization)
Working Papers
Bollapragada, R., Karamanli,C., & Wild, S.M. Derivative-Free Optimization via Adaptive Sampling Strategies.
Bollapragada, R., Pasupathy, R, Gupta, A. & Yip, N., K. Adaptive Fixed-Step Stochastic Gradient Method.
Berahas, A. S., Bollapragada, R., & Dong, W. Exploiting Negative Curvature in Conjunction with Adaptive Sampling: Theoretical Results and a Practical Algorithm.
Berahas, A. S., Bollapragada, R., & Shi, J. Exact and Inexact Subsampled Line Search Newton Methods for Equality Constrained Stochastic Optimization.
Berahas, A. S., Bollapragada, R., & Gupta, S. Retrospective Approximation for Sequential Quadratic Programming.
Berahas, A. S., Bollapragada, R., Karamanli,C., & Shah, S. Adaptive Asynchronous Gradient Tracking Algorihtms for Decentralized Optimization.
Bollapragada, R., & O'Leary-Roseberry, T. Second-Order Stochastic Optimization via Hessian Averaging and Adaptive Gradient Sampling.
Berahas, A. S., Bollapragada, R. & Karamanli,C. Adaptive Sampling Strategies for Stochastic Decentralized Optimization with Inexact Communication.
Thesis
Bollapragada, V. R. Methods for Deterministic and Stochastic Optimization. PhD Thesis, Department of Industrial Engineering and Management Sciences, Northwestern University, Evanston, IL, USA.
Bollapragada, V. R. An Approach for Volumetric Accuracy Analysis of Cylindrical Grinding Machine Based on Geometric Error Model. Masters Thesis, Department of Mechanical Engineering, I.I.T Madras, India.