60 citations · 203 across the 23 of their papers we have counts for
4 papers · 1 filter
Escaping Saddle-Points Faster under Interpolation-like Conditions
Abhishek Roy, Krishnakumar Balasubramanian, Saeed Ghadimi +1
In this paper, we show that under over-parametrization several standard stochastic optimization algorithms escape saddle-points and converge to local-minimizers much faster. One of…
Stochastic Multi-level Composition Optimization Algorithms with Level-Independent Convergence Rates
Krishnakumar Balasubramanian, Saeed Ghadimi, Anthony Nguyen
In this paper, we study smooth stochastic multi-level composition optimization problems, where the objective function is a nested composition of functions. We assume access to…
Improved Complexities for Stochastic Conditional Gradient Methods under Interpolation-like Conditions
Tesi Xiao, Krishnakumar Balasubramanian, Saeed Ghadimi
We analyze stochastic conditional gradient methods for constrained optimization problems arising in over-parametrized machine learning. We show that one could leverage the interpol…
Reinforcement Learning via Parametric Cost Function Approximation for Multistage Stochastic Programming
Saeed Ghadimi, Raymond T. Perkins, Warren B. Powell
The most common approaches for solving stochastic resource allocation problems in the research literature is to either use value functions ("dynamic programming") or scenario trees…