1 code implementation • CVPR 2023 • Chao Ning, Hongping Gan
Recently, some studies introduced multi-head attention (MHA) modules to perform long-range interaction, which have shown significant progress in regressing the depth maps. The main functions of MHA can be loosely summarized to capture long-distance information and report the attention map by the relationship between pixels.
no code implementations • 4 Dec 2022 • Haoran Deng, Bo Yang, Chao Ning, Cailian Chen, Xinping Guan
In order to ensure the individual optimality of the two networks in a unified framework in day-ahead power scheduling, a two-stage distributionally robust centralized optimization model is established to carry out the equilibrium of power-transportation coupled network.
no code implementations • 20 Nov 2020 • Chao Ning, Fengqi You
We propose a novel online learning based risk-averse stochastic MPC framework in which Conditional Value-at-Risk (CVaR) constraints on system states are required to hold for a family of distributions called an ambiguity set.
no code implementations • 3 Apr 2019 • Chao Ning, Fengqi You
This paper reviews recent advances in the field of optimization under uncertainty via a modern data lens, highlights key research challenges and promise of data-driven optimization that organically integrates machine learning and mathematical programming for decision-making under uncertainty, and identifies potential research opportunities.
no code implementations • 28 Jul 2017 • Chao Ning, Fengqi You
A DDSRO framework is further proposed based on the data-driven uncertainty model through a bi-level optimization structure.