Abhishek Roy, Krishnakumar Balasubramanian, and Saeed Ghadimi, "Projection-free Constrained Stochastic Nonconvex Optimization with State-dependent Markov Data", NeurIPS (2022).
Tesi Xiao, Krishnakumar Balasubramanian, Saeed Ghadimi, "A Projection-free Algorithm for Constrained Multi-level Stochastic Composition Optimization", NeurIPS (2022).
Krishnakumar Balasubramanian, Saeed Ghadimi, and Anthony Nguyen, "Stochastic Multi-level Composition Optimization Algorithms with Level-Independent Convergence Rates", SIAM Journal on Optimization 32 (2022), 519-544.
Abhishek Roy, Krishnakumar Balasubramanian, Saeed Ghadimi, and Prasant Mohapatra, “ Stochastic Zeroth-Order Optimization under Nonstationary and Nonconvexity”, Journal of Machine Learning Research 23 (2022), 1-47.
Tesi Xiao, Krishnakumar Balasubramanian, and Saeed Ghadimi , "Improved Complexities for Stochastic Conditional Gradient Methods under Interpolation-like Conditions", Operations Research Letters, 50 (2022), 184-189.
Abhishek Roy, Lingqing Shen, Krishna Balasubramanian, and Saeed Ghadimi, “Stochastic Zeroth-order Discretizations of Langevin Diffusions for Bayesian Inference”, Bernoulli 28 (2022), 1810-1834.
Krishna Balasubramanian and Saeed Ghadimi, “Zeroth-order Nonconvex Stochastic Optimization: Handling Constraints, High-Dimensionality, and Saddle-Points”, Foundations of Computational Mathematics 22 (2022), 35-76.
Abhishek Roy, Krishnakumar Balasubramanian, Saeed Ghadimi, and Prasant Mohapatra, ``Escaping Saddle-Points Faster under Interpolation-like Conditions'', NeurIPS (2020).
Saeed Ghadimi, Andrzej Ruszczynski, and Mengdi Wang, “A Single Time-Scale Stochastic Approximation Method for Nested Stochastic Optimization”. SIAM Journal on Optimization (2020): 30(1), 960–979 .
Saeed Ghadimi, Guanghui Lan, and Hongchao Zhang, “Generalized Uniformly Optimal Methods for Nonlinear Programming”. Journal of Scientific Computing (2019): 79, 1854–1881.
Krishna Balasubramanian, and Saeed Ghadimi, “Zeroth-order (Non)-Convex Stochastic Optimization via Conditional Gradient and Gradient Updates”. NeurIPS (2018).
Saeed Ghadimi, “Conditional Gradient Type Methods for Composite Nonlinear and Stochastic Optimization”. Mathematical Programming (2019): 173, 431–464.
Saeed Ghadimi, Hongchao Zhang, and Guanghui Lan, “Mini-batch Stochastic Approximation Methods for Nonconvex Stochastic Composite Optimization”. Mathematical Programming (2016):155, 267-305.
Saeed Ghadimi and Guanghui Lan, “Accelerated Gradient Methods for Nonconvex Nonlinear and Stochastic Programming”. Mathematical Programming (2016): 156, 59-99.
Reza Zanjirani Farahani, W Y Szeto, and Saeed Ghadimi, “The Single Facility Location Problem with Time-dependent Weights and Relocation Cost Over a Continuous Time Horizon”. Journal of the Operational Research Society (2014): 66(2), 1-13.
Saeed Ghadimi, Ferenc Szidarovszky, Reza Zanjirani Farahani, and Alireza yousefzadeh Khiabani, “Coordination of Advertising in Supply Management with Cooperating Manufacturer and Retailers”. IMA Journal of Management Mathematics (2013): 24(1), 1-19.
Saeed Ghadimi and Guanghui Lan, “Optimal Stochastic Approximation Algorithms for Strongly Convex Stochastic Composite Optimization, II: Shrinking Procedures and Optimal Algorithms”. SIAM Journal on Optimization (2013): 23(4), 2061-2089.
Saeed Ghadimi and Guanghui Lan, “Stochastic First- and Zeroth-order Methods for NonconvexStochastic Programming”. SIAM Journal on Optimization (2013): 23(4), 2341-2368.
Saeed Ghadimi and Guanghui Lan, “Optimal Stochastic Approximation Algorithms for Strongly Convex Stochastic Composite Optimization, I: a Generic Algorithmic Framework”. SIAM Journal on Optimization (2012): 22(4), 1469-1492.
"A One-Sample Decentralized Proximal Algorithm for Non-Convex Stochastic Composite Optimization", (with Tesi Xiao, Xuxing Chen, and Krishna Balasubramanian)
"RIGID: Robust Linear Regression with Missing Data", (with Alireza Aghasi and Mohammad Javad Feizollahi)
“Stochastic Search for a Parametric Cost Function Approximation: Energy storage with rolling forecasts”, (with Warren Powell)
“The Parametric Cost Function Approximation: A new approach for multistage stochastic programming”, (with Warren Powell)
“Robust and efficient algorithms for high-dimensionalblack-box quantum optimization”, (with Zhaoqi Leng, Pranav Mundada, and Andrew Houck)
“Approximation Methods for Bilevel Programming”, (with Mengdi Wang)
“Second-Order Methods with Cubic Regularization Under Inexact Information”, (with Han Liu, and Tong Zhang)