14 citations · 79 across the 38 of their papers we have counts for
8 papers · 1 filter
On the Ergodicity, Bias and Asymptotic Normality of Randomized Midpoint Sampling Method
Ye He, Krishnakumar Balasubramanian, Murat A. Erdogdu
The randomized midpoint method, proposed by [SL19], has emerged as an optimal discretization procedure for simulating the continuous time Langevin diffusions. Focusing on the case…
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…
Fractal Gaussian Networks: A sparse random graph model based on Gaussian Multiplicative Chaos
Subhroshekhar Ghosh, Krishnakumar Balasubramanian, Xiaochuan Yang
We propose a novel stochastic network model, called Fractal Gaussian Network (FGN), that embodies well-defined and analytically tractable fractal structures. Such fractal structure…
An Analysis of Constant Step Size SGD in the Non-convex Regime: Asymptotic Normality and Bias
Lu Yu, Krishnakumar Balasubramanian, Stanislav Volgushev +1
Structured non-convex learning problems, for which critical points have favorable statistical properties, arise frequently in statistical machine learning. Algorithmic convergence…
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…