activity
20152026
most citedUsing the Johnson-Lindenstrauss lemma in linear and integer programming

5 citations · 8 across the 9 of their papers we have counts for

collaborators

14 papers

cs.IT2026

The Hellinger Conjecture for Antipodal Boolean Functions

Vu Khac Ky

The balanced Hellinger conjecture compares the overlap of two output laws induced by a Boolean decision under binary symmetric noise. We prove that a single input coordinate minimi…

cs.IT2026

Stability of the Courtade-Kumar inequality

Vu Khac Ky, Tuan Tran

We prove dimension-independent stability for the Courtade-Kumar inequality: a Boolean function whose information is close to the dictator value is close i…

cs.IT2026

Dictators are most informative

Vu Khac Ky, Tuan Tran

We prove the Courtade-Kumar conjecture: among all Boolean functions , a dictator retains the most information about a uniformly random input observed…

cs.LG2026

Loss-Parameterized Fisher Width Along Learning Trajectories

Vu Khac Ky

Fisher width measures the Gaussian width of a probe set after deformation by the local Fisher geometry. We study its evolution along learning trajectories and ask when training los…

math.OC2026

Curvature Residual Geometry in Bregman Regression

Vu Khac Ky

We consider linear regression models fitted by minimizing Bregman losses of the form \[ \frac{1}{n}\sum_{i=1}^n \left[ ϕ(y_i)-ϕ(x_i^\topθ) -ϕ'(x_i^\topθ) \bigl(y_i-x_i^\topθ\bigr)…

cs.LG2026

Fisher Widths: Local Learning Geometry and Anisotropic Recovery

Vu Khac Ky

We study Gaussian-width complexity on statistical manifolds through a pair of functionals: the primal Fisher width , induced by the Fisher metric, and the inv…