Efficient Algorithms for Non-convex Isotonic Regression through Submodular Optimization

07/28/2017
by   Francis Bach, et al.
0

We consider the minimization of submodular functions subject to ordering constraints. We show that this optimization problem can be cast as a convex optimization problem on a space of uni-dimensional measures, with ordering constraints corresponding to first-order stochastic dominance. We propose new discretization schemes that lead to simple and efficient algorithms based on zero-th, first, or higher order oracles; these algorithms also lead to improvements without isotonic constraints. Finally, our experiments show that non-convex loss functions can be much more robust to outliers for isotonic regression, while still leading to an efficient optimization problem.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/26/2013

Structured Convex Optimization under Submodular Constraints

A number of discrete and continuous optimization problems in machine lea...
research
05/16/2020

Tiering as a Stochastic Submodular Optimization Problem

Tiering is an essential technique for building large-scale information r...
research
04/17/2020

First-Order Methods for Optimal Experimental Design Problems with Bound Constraints

We consider a class of convex optimization problems over the simplex of ...
research
09/23/2021

Outlier-Robust Sparse Estimation via Non-Convex Optimization

We explore the connection between outlier-robust high-dimensional statis...
research
01/04/2022

Sparse Non-Convex Optimization For Higher Moment Portfolio Management

One of the reasons that higher order moment portfolio optimization metho...
research
05/31/2022

Evaluating Robustness to Dataset Shift via Parametric Robustness Sets

We give a method for proactively identifying small, plausible shifts in ...
research
01/09/2021

Rate Allocation and Content Placement in Cache Networks

We introduce the problem of optimal congestion control in cache networks...

Please sign up or login with your details

Forgot password? Click here to reset