6 papers
Statistical Learning from Attribution Sets
Lorne Applebaum, Robert Busa-Fekete, August Y. Chen +3
We address the problem of training conversion prediction models in advertising domains under privacy constraints, where direct links between ad clicks and conversions are unavailab…
How abundant are good interpolators?
August Y. Chen, Ahmed El Alaoui
Let be the set of unit norm linear classifiers which correctly classify every point of a labeled dataset , , $y_i…
On the Robustness of Langevin Dynamics to Score Function Error
Daniel Yiming Cao, August Y. Chen, Karthik Sridharan +1
We consider the robustness of score-based generative modeling to errors in the estimate of the score function. In particular, we show that Langevin dynamics is not robust to the $L…
Efficiently Escaping Saddle Points under Generalized Smoothness via Self-Bounding Regularity
Daniel Yiming Cao, August Y. Chen, Karthik Sridharan +1
We study the optimization of non-convex functions that are not necessarily smooth (gradient and/or Hessian are Lipschitz) using first order methods. Smoothness is a restrictive ass…
Optimization, Isoperimetric Inequalities, and Sampling via Lyapunov Potentials
August Y. Chen, Karthik Sridharan
In this paper, we prove that optimizability of any function F using Gradient Flow from all initializations implies a Poincaré Inequality for Gibbs measures mu_{beta} = e^{-beta F}…
Beyond the broken tetrahedron
August Y. Chen, Bjarne Schülke
Here we consider the hypergraph Turán problem in uniformly dense hypergraphs as was suggested by ErdÅs and Sós. Given a -graph , the uniform Turán density of $F…