45 citations · 45 across the 5 of their papers we have counts for
5 papers
Uniform Convergence with Square-Root Lipschitz Loss
Lijia Zhou, Zhen Dai, Frederic Koehler +1
We establish generic uniform convergence guarantees for Gaussian data in terms of the Rademacher complexity of the hypothesis class and the Lipschitz constant of the square root of…
Complex matrix inversion via real matrix inversions
Zhen Dai, Lek-Heng Lim, Ke Ye
We study the inversion analog of the well-known Gauss algorithm for multiplying complex matrices. A simple version is $(A + iB)^{-1} = (A + BA^{-1}B)^{-1} - i A^{-1}B(A+BA^{-1} B)^…
Rank-constrained Hyperbolic Programming
Zhen Dai, Lek-Heng Lim
We extend rank-constrained optimization to general hyperbolic programs (HP) using the notion of matroid rank. For LP and SDP respectively, this reduces to sparsity-constrained LP a…
Numerical stability and tensor nuclear norm
Zhen Dai, Lek-Heng Lim
We present a notion of bilinear stability, which is to numerical stability what bilinear complexity is to time complexity. In bilinear complexity, an algorithm for evaluating a bil…
Is Local SGD Better than Minibatch SGD?
Blake Woodworth, Kumar Kshitij Patel, Sebastian U. Stich +5
We study local SGD (also known as parallel SGD and federated averaging), a natural and frequently used stochastic distributed optimization method. Its theoretical foundations are c…