activity
20082019
most citedLaplacian Smoothing Gradient Descent

28 citations · 57 across the 10 of their papers we have counts for

collaborators

10 papers

math.CO2019

Design Theory and some Forbidden Configurations

R. P. Anstee, Farzin Barekat, Zachary Pellegrin

In this paper we relate t-designs to a forbidden configuration problem in extremal set theory. Let 1_t 0_l denote a column of t 1's on top of l 0's. We assume t>l. Let q. (1_t 0_l)…

math.CO2019★ 1 cited

Design Theory and Some Non-simple Forbidden Configurations

R. P. Anstee, Farzin Barekat

Let 1_k 0_l denote the (k+l)\times 1 column of k 1's above l 0's. Let q. (1_k 0_l) $ denote the (k+l)xq matrix with q copies of the column 1_k0_l. A 2-design S_λ(2,3,v) can be defi…

cs.LG2019★ 18 cited

DP-LSSGD: A Stochastic Optimization Method to Lift the Utility in Privacy-Preserving ERM

Bao Wang, Quanquan Gu, March Boedihardjo +2

Machine learning (ML) models trained by differentially private stochastic gradient descent (DP-SGD) have much lower utility than the non-private ones. To mitigate this degradation,…

cs.LG2018★ 28 cited

Laplacian Smoothing Gradient Descent

Stanley Osher, Bao Wang, Penghang Yin +4

We propose a class of very simple modifications of gradient descent and stochastic gradient descent. We show that when applied to a large variety of machine learning problems, rang…

cond-mat.mtrl-sci2014★ 3 cited

Compressed Wannier modes found from an regularized energy functional

Farzin Barekat, Ke Yin, Russel E. Caflisch +3

We propose a method for calculating Wannier functions of periodic solids directly from a modified variational principle for the energy, subject to the requirement that the Wannier…

math.NA2014★ 2 cited

Projection to the Set of Shift Orthogonal Functions

Farzin Barekat, Rongjie Lai, Ke Yin +3

This paper presents a fast algorithm for projecting a given function to the set of shift orthogonal functions (i.e. set containing functions with unit norm that are orthogona…