Code for NeurIPS2021 submission "A Surrogate Objective Framework for Prediction+Programming with Soft Constraints"

Overview

This repository is the code for NeurIPS 2021 submission "A Surrogate Objective Framework for Prediction+Programming with Soft Constraints".

Edit 2021/8/30: KKT-based (Decision-focused) baseline is added to the first experiment.

Requirements

pytorch>=1.7.0

scipy

gurobipy (and Gurobi>=9.1 license - you can get Academic license for free at https://www.gurobi.com/downloads/end-user-license-agreement-academic/; download and install Gurobi first.)

Quandl

h5py

bs4

tqdm

sklearn

pandas

lxml

qpth

cvxpy

cvxpylayers

Running Experiments

You should be able to run all experiments by fulfilling the requirements and cloning this repo to your local machine.

Synthetic Linear Programming

The dataset for this problem is generated at runtime. To run a single problem instance, type the following command:

python run_main_synth.py --method=2 --dim_context=40 --dim_hard=40 --dim_soft=20 --seed=2006 --dim_features=80 --loss=l1 --K=0.2

The four methods (L1,L2,SPO+,ours) we used in the experiment are respectively

--method=0 --loss=l1 # L1
--method=0 --loss=l2 # L2
--method=1 --loss=l1 # SPO+
--method=2 --loss=l1 # ours
--method=3 --loss=l1 # decision-focused (KKT-based)

The other parameters can be seen in run_script.py and run_main_synth.py. To get multiple data for a single method, modify with the parameters listed above, and then run run_script.py. The outcome containing prediction error and regret is in the result folder. See dataprocess.py for a reference on how to interpret the data; the data with suffix "...test.txt" is used for evaluation. Also, to change batch size and training set size, alter the default parameters in run_main_synth.py.

Portfolio Optimization

The dataset for this problem will be automatically downloaded when you first run this code, as Wilder et al.'s code does[1]. It is the daily price data of SP500 from 2004 to 2017 downloaded by Quandl API. To run a single problem instance, type the following command:

python main.py --method=3 --n=50 --seed=471298479

The four methods (L1, DF, L2, ours) are labeled as method 0, 1, 2 and 3. To get multiple data for a single method, run run_script.py.

The result is in the res/K100 folder.

Resource Provisioning

The dataset of this problem is attached in the github repository, which are the eight csv file, one for each region. It is the ERCOT dataset taken from (...to be filled...), and is processed by resource_provisioning/data_energy/data_loader.py at runtime. When you first run this code, it will generate several large .npy file as the cached feature, which will accelerate the preprocessing of the following runs. This experiment requires large memory and is recommended to run on a server. To run a single problem instance, type the following command:

python run_main_newnet.py --method=1 --seed=16900000 --loss=l1

The four methods (L1, L2, weighted L1, ours) are respectively

--method=0 --loss=l1 # L1
--method=0 --loss=l2 # L2
--method=0 --loss=l3 # weighted L1
--method=1 --loss=l1 # ours

To run different ratio of alpha1/alpha2, modify line 157-158 in synthesize.py

 alpha1 = torch.ones(dim_context, 1) * 50
 alpha2 = torch.ones(dim_context, 1) * 0.5

to a desired ratio. Furthermore, modify line 174 in main_newnet.py

netname = "50to0.5"

to "5to0.5"/"1to1"/"0.5to5"/"0.5to50", and line 199 in main_newnet.py

self.alpha1, self.alpha2 = 0.5, 50

to (0.5, 5)/(1, 1)/(5, 0.5)/(50, 0.5) respectively.

run run_script.py to get multiple data. The result is in the result/2013to18_+str(netname)+newnet folder. The interpretation of output data is similar to synthetic linear programming.

[1] Automatically Learning Compact Quality-aware Surrogates for Optimization Problems, Wilder et al., 2020 (https://arxiv.org/abs/2006.10815)

Empirical Evaluation of Lambda_max in Theorem 6

run test.py directly to get results (note it takes a long time to finish the whole run, especially for the option of beta distribution). The results for uniform, Gaussian and beta are respectively in test1.txt, test2.txt and test3.txt.

A PyTorch implementation for Unsupervised Domain Adaptation by Backpropagation(DANN), support Office-31 and Office-Home dataset

DANN A PyTorch implementation for Unsupervised Domain Adaptation by Backpropagation Prerequisites Linux or OSX NVIDIA GPU + CUDA (may CuDNN) and corre

8 Apr 16, 2022
pytorch implementation of "Contrastive Multiview Coding", "Momentum Contrast for Unsupervised Visual Representation Learning", and "Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination"

Unofficial implementation: MoCo: Momentum Contrast for Unsupervised Visual Representation Learning (Paper) InsDis: Unsupervised Feature Learning via N

Zhiqiang Shen 16 Nov 04, 2020
Official source code of paper 'IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo'

IterMVS official source code of paper 'IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo' Introduction IterMVS is a novel lear

Fangjinhua Wang 127 Jan 04, 2023
This is a package for LiDARTag, described in paper: LiDARTag: A Real-Time Fiducial Tag System for Point Clouds

LiDARTag Overview This is a package for LiDARTag, described in paper: LiDARTag: A Real-Time Fiducial Tag System for Point Clouds (PDF)(arXiv). This wo

University of Michigan Dynamic Legged Locomotion Robotics Lab 159 Dec 21, 2022
This repository is for Contrastive Embedding Distribution Refinement and Entropy-Aware Attention Network (CEDR)

CEDR This repository is for Contrastive Embedding Distribution Refinement and Entropy-Aware Attention Network (CEDR) introduced in the following paper

phoenix 3 Feb 27, 2022
Using PyTorch Perform intent classification using three different models to see which one is better for this task

Using PyTorch Perform intent classification using three different models to see which one is better for this task

Yoel Graumann 1 Feb 14, 2022
Poisson Surface Reconstruction for LiDAR Odometry and Mapping

Poisson Surface Reconstruction for LiDAR Odometry and Mapping Surfels TSDF Our Approach Table: Qualitative comparison between the different mapping te

Photogrammetry & Robotics Bonn 305 Dec 21, 2022
The first machine learning framework that encourages learning ML concepts instead of memorizing class functions.

SeaLion is designed to teach today's aspiring ml-engineers the popular machine learning concepts of today in a way that gives both intuition and ways of application. We do this through concise algori

Anish 324 Dec 27, 2022
Deploy optimized transformer based models on Nvidia Triton server

🤗 Hugging Face Transformer submillisecond inference 🤯 and deployment on Nvidia Triton server Yes, you can perfom inference with transformer based mo

Lefebvre Sarrut Services 1.2k Jan 05, 2023
A simple configurable bot for sending arXiv article alert by mail

arXiv-newsletter A simple configurable bot for sending arXiv article alert by mail. Prerequisites PyYAML=5.3.1 arxiv=1.4.0 Configuration All config

SXKDZ 21 Nov 09, 2022
Implementation of paper "DeepTag: A General Framework for Fiducial Marker Design and Detection"

Implementation of paper DeepTag: A General Framework for Fiducial Marker Design and Detection. Project page: https://herohuyongtao.github.io/research/

Yongtao Hu 46 Dec 12, 2022
Generative Adversarial Text-to-Image Synthesis

###Generative Adversarial Text-to-Image Synthesis Scott Reed, Zeynep Akata, Xinchen Yan, Lajanugen Logeswaran, Bernt Schiele, Honglak Lee This is the

Scott Ellison Reed 883 Dec 31, 2022
[NeurIPS 2021]: Are Transformers More Robust Than CNNs? (Pytorch implementation & checkpoints)

Are Transformers More Robust Than CNNs? Pytorch implementation for NeurIPS 2021 Paper: Are Transformers More Robust Than CNNs? Our implementation is b

Yutong Bai 145 Dec 01, 2022
It's like Shape Editor in Maya but works with skeletons (transforms).

Skeleposer What is Skeleposer? Briefly, it's like Shape Editor in Maya, but works with transforms and joints. It can be used to make complex facial ri

Alexander Zagoruyko 1 Nov 11, 2022
[BMVC2021] The official implementation of "DomainMix: Learning Generalizable Person Re-Identification Without Human Annotations"

DomainMix [BMVC2021] The official implementation of "DomainMix: Learning Generalizable Person Re-Identification Without Human Annotations" [paper] [de

Wenhao Wang 17 Dec 20, 2022
PyTorch implementation of "Image-to-Image Translation Using Conditional Adversarial Networks".

pix2pix-pytorch PyTorch implementation of Image-to-Image Translation Using Conditional Adversarial Networks. Based on pix2pix by Phillip Isola et al.

mrzhu 383 Dec 17, 2022
Hooks for VCOCO

Verbs in COCO (V-COCO) Dataset This repository hosts the Verbs in COCO (V-COCO) dataset and associated code to evaluate models for the Visual Semantic

Saurabh Gupta 131 Nov 24, 2022
Official PyTorch implementation of Data-free Knowledge Distillation for Object Detection, WACV 2021.

Introduction This repository is the official PyTorch implementation of Data-free Knowledge Distillation for Object Detection, WACV 2021. Data-free Kno

NVIDIA Research Projects 50 Jan 05, 2023
PyTorch implementation of the method described in the paper VoiceLoop: Voice Fitting and Synthesis via a Phonological Loop.

VoiceLoop PyTorch implementation of the method described in the paper VoiceLoop: Voice Fitting and Synthesis via a Phonological Loop. VoiceLoop is a n

Meta Archive 873 Dec 15, 2022
PyTorch implementation of Weak-shot Fine-grained Classification via Similarity Transfer

SimTrans-Weak-Shot-Classification This repository contains the official PyTorch implementation of the following paper: Weak-shot Fine-grained Classifi

BCMI 60 Dec 02, 2022