mlsanityData to 14 Oct 2026

Global Optimization Networks

arXiv 2202.01277 ↗First posted 2 Feb 2022stat.ML cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

We consider the problem of estimating a good maximizer of a black-box function given noisy examples. To solve such problems, we propose to fit a new type of function which we call a global optimization network (GON), defined as any composition of an invertible function and a unimodal function, whose unique global maximizer can be inferred in O(D) time. In this paper, we show how to construct invertible and unimodal functions by using linear inequality constraints on lattice models. We also extend to conditional GONs that find a global maximizer conditioned on specified inputs of other dimensions. Experiments show the GON maximizers are statistically significantly better predictions than those produced by convex fits, GPR, or DNNs, and are more reasonable predictions for real-world problems.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 14 of its 68 references that are in the map. First posted on arXiv 2 Feb 2022.

Builds on

14 of 68 references.

References · 14

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  3. 2019On the Variance of the Adaptive Learning Rate and Beyondcited by 772
  4. 2016Input Convex Neural Networkscited by 414
  5. 2018Invertible Residual Networkscited by 365
  6. 2019Unconstrained Monotonic Neural Networkscited by 92
  7. 2021Conservative Objective Models for Effective Offline Model-Based Optimizationcited by 88
  8. 2018Optimal Control Via Neural Networks: A Convex Approachcited by 85
  9. 2019Model Inversion Networks for Model-Based Optimizationcited by 83
  10. 2017Deep Lattice Networks and Partial Monotonic Functionscited by 63
  11. 2021RoMA: Robust Model Adaptation for Offline Model-based Optimizationcited by 39
  12. 2015Monotonic Calibrated Interpolated Look-Up Tablescited by 35
2 more
  1. 2020Deontological Ethics By Monotonicity Shape Constraintscited by 16
  2. 2018Prediction Rule Reshapingcited by 3

Built on by

Cited by year

Citing papers per year: 2023: 2.

2 papers.

  1. 2023Asymmetric Certified Robustness via Feature-Convex Neural Networkscited by 8
  2. 2023Physics-Driven ML-Based Modelling for Correcting Inverse Estimationcited by 1