73 citations · 347 across the 51 of their papers we have counts for
5 papers · 1 filter
Resolving Matrix Spencer Conjecture Up to Poly-logarithmic Rank
Nikhil Bansal, Haotian Jiang, Raghu Meka
We give a simple proof of the matrix Spencer conjecture up to poly-logarithmic rank: given symmetric matrices each with …
Smoothed Analysis of the Komlós Conjecture
Nikhil Bansal, Haotian Jiang, Raghu Meka +2
The well-known Komlós conjecture states that given vectors in with Euclidean norm at most one, there always exists a coloring such that the $\ell_{\infty…
Distributional Hardness Against Preconditioned Lasso via Erasure-Robust Designs
Jonathan A. Kelner, Frederic Koehler, Raghu Meka +1
Sparse linear regression with ill-conditioned Gaussian random designs is widely believed to exhibit a statistical/computational gap, but there is surprisingly little formal evidenc…
Hardness of Noise-Free Learning for Two-Hidden-Layer Neural Networks
Sitan Chen, Aravind Gollakota, Adam R. Klivans +1
We give superpolynomial statistical query (SQ) lower bounds for learning two-hidden-layer ReLU networks with respect to Gaussian inputs in the standard (noise-free) model. No gener…
Minimax Optimality (Probably) Doesn't Imply Distribution Learning for GANs
Sitan Chen, Jerry Li, Yuanzhi Li +1
Arguably the most fundamental question in the theory of generative adversarial networks (GANs) is to understand to what extent GANs can actually learn the underlying distribution.…