activity
20202023
most citedAutomatic Gradient Descent: Deep Learning without Hyperparameters

6 citations · 11 across the 5 of their papers we have counts for

collaborators

5 papers

cs.LG20236 cited

Automatic Gradient Descent: Deep Learning without Hyperparameters

Jeremy Bernstein, Chris Mingard, Kevin Huang +2

The architecture of a deep neural network is defined explicitly in terms of the number of layers, the width of each layer and the general network topology. Existing optimisation fr…

math.OC20232 cited

Beyond Monotone Variational Inequalities: Solution Methods and Iteration Complexities

Kevin Huang, Shuzhong Zhang

In this paper, we discuss variational inequality (VI) problems without monotonicity from the perspective of convergence of projection-type algorithms. In particular, we identify ex…

physics.flu-dyn2023

Thrust Enhancement and Degradation Mechanisms due to Self-Induced Vibrations in Bio-inspired Flying Robots

Dipan Deb, Kevin Huang, Aakash Verma +2

Whenever a flapping robot moves along a trajectory it experiences some vibration about its mean path. Even for a hovering case, a flier experiences such vibration due to the oscill…

math.OC20221 cited

An Approximation-Based Regularized Extra-Gradient Method for Monotone Variational Inequalities

Kevin Huang, Shuzhong Zhang

In this paper, we propose a general extra-gradient scheme for solving monotone variational inequalities (VI), referred to here as Approximation-based Regularized Extra-gradient met…

math.OC20202 cited

Cubic Regularized Newton Method for Saddle Point Models: a Global and Local Convergence Analysis

Kevin Huang, Junyu Zhang, Shuzhong Zhang

In this paper, we propose a cubic regularized Newton (CRN) method for solving convex-concave saddle point problems (SPP). At each iteration, a cubic regularized saddle point subpro…