no code implementations • 7 Aug 2022 • Sally Dong, Haotian Jiang, Yin Tat Lee, Swati Padmanabhan, Guanghao Ye
In this work, we give an algorithm that minimizes the above convex formulation to $\epsilon$-accuracy in $\widetilde{O}(\sum_{i=1}^n d_i \log (1 /\epsilon))$ gradient computations, with no assumptions on the condition number.
