L
Li Zhang
Researcher at Google
Publications - 158
Citations - 13353
Li Zhang is an academic researcher from Google. The author has contributed to research in topics: Computer science & Differential privacy. The author has an hindex of 44, co-authored 136 publications receiving 9699 citations. Previous affiliations of Li Zhang include Microsoft & Stony Brook University.
Papers
More filters
Journal ArticleDOI
Proportional response dynamics in the Fisher market
TL;DR: It is shown that the proportional response dynamics, a utility based distributed dynamics, converges to the market equilibrium in the Fisher market with constant elasticity of substitution (CES) utility functions.
Posted Content
Private Empirical Risk Minimization Beyond the Worst Case: The Effect of the Constraint Set Geometry.
TL;DR: It is shown that the geometric properties of the constraint set can be used to derive significantly better results in ERM, and when the loss function is Lipschitz with respect to the $\ell_1$ norm, a differentially private version of the Frank-Wolfe algorithm gives error bounds of the form $\tilde{O}(n^{-2/3})$.
Book ChapterDOI
Proportional Response Dynamics in the Fisher Market
TL;DR: It is shown that the proportional response dynamics, a utility based distributed dynamics, converges to the market equilibrium in the Fisher market with constant elasticity of substitution (CES) utility functions.
Proceedings Article
Separation-sensitive collision detection for convex objects
TL;DR: A class of new kinetic data structures for collision detection between moving convex polytopes are developed that exhibit hysteresis—after a separation certificate fails, the new certificate cannot fail again until the objects have moved by some constant fraction of their current separation.
Journal ArticleDOI
PolarFormer: Multi-camera 3D Object Detection with Polar Transformers
TL;DR: This paper advocates the exploitation of the Polar coordinate system and proposes a new Polar Transformer ( PolarFormer) for more accurate 3D object detection in the bird’s-eye-view (BEV) taking as input only multi-camera 2D images.