The code for replicating the experiments from the LFI in SSMs with Unknown Dynamics paper.

Overview

Likelihood-Free Inference in State-Space Models with Unknown Dynamics

This package contains the codes required to run the experiments in the paper. The simulators used for the State-Space Models in the experiments are implemented based on Engine for Likelihood-free Inference (ELFI) models.

Installation

We recommend using an Anaconda environment. To create and activate the conda environment with all dependencies installed, run:

conda create -c conda-forge --name env --file lfi-requirements.txt
conda activate env
pip install -e .
pip install sbi blitz-bayesian-pytorch stable_baselines3

For the GP-SSM and PR-SSM methods, we recommend creating a separate environment, in which one should install tensorflow, and then clone the 'custom_multiouput' branch of the GPflow from https://github.com/ialong/GPflow. Once GPflow is installed, one should clone GPt from https://github.com/ialong/GPt and execute 'experiments/run_gpssms.py', the code will complete 30 repletions of experiments with tractable likelihoods.

Running the experiments

The experiment scripts can be found in the 'experiments/' folder. To run the experiments on one of the considered SSM, one should run the 'run_experiment.py' script with the following arguments (options are in the parentheses): --sim ('lgssm', 'toy', 'sv', 'umap', 'gaze'), --meth ('bnn', 'qehvi', 'blr', 'SNPE', 'SNLE', 'SNRE'), --seed (any seed number), --budget (available simulation budget for each new state), --tasks (number of tasks considered/ moving window size for LMC-BNN, LMC-qEHVI and LMC-BLR methods). For instance:

python3 experiments/run_experiment.py --sim=lgssm --meth=bolfi --seed=0 --budget=2 --tasks=2

The results will be saved in the corresponding folders 'experiments/[sim]/[meth]-w[tasks]-s[budget]/'. To build plots and output the results, one should run 'collect_plots.py' script with specified arguments: --type ('inf' in case of evaluating state inference quality or 'traj' in case of evaluating the generated trajectories), --tasks (the number of tasks used by the methods). For example:

python3 experiments/collect_results.py --type=inf --tasks=2

The plots with experiment results will be stored in 'experiments/plots'.

Implementing custom simulators

The simulators for all experiments can be found in elfi/examples. Example implementations used in the paper are found in gaze_selection.py, umap_tasks.py, LGSSM.py (LG), dynamic_toy_model.py (NN), and stochastic_volatility.py (SV). To create a new SSM, implement a new class that inherits from elfi.DynamicProcess with custom generating function for observations, create_model(), and update_dynamic().

The code for all methods can be found in 'elfi/methods/dynamic_parameter_inference.py' and 'elfi/methods/bo/mogp.py'.

Citation


Owner
Alex Aushev
Alex Aushev
Stereo Hybrid Event-Frame (SHEF) Cameras for 3D Perception, IROS 2021

For academic use only. Stereo Hybrid Event-Frame (SHEF) Cameras for 3D Perception Ziwei Wang, Liyuan Pan, Yonhon Ng, Zheyu Zhuang and Robert Mahony Th

Ziwei Wang 11 Jan 04, 2023
Rule Extraction Methods for Interactive eXplainability

REMIX: Rule Extraction Methods for Interactive eXplainability This repository contains a variety of tools and methods for extracting interpretable rul

Mateo Espinosa Zarlenga 21 Jan 03, 2023
Tensors and neural networks in Haskell

Hasktorch Hasktorch is a library for tensors and neural networks in Haskell. It is an independent open source community project which leverages the co

hasktorch 920 Jan 04, 2023
clustering moroccan stocks time series data using k-means with dtw (dynamic time warping)

Moroccan Stocks Clustering Context Hey! we don't always have to forecast time series am I right ? We use k-means to cluster about 70 moroccan stock pr

Ayman Lafaz 7 Oct 18, 2022
Generative Query Network (GQN) in PyTorch as described in "Neural Scene Representation and Rendering"

Update 2019/06/24: A model trained on 10% of the Shepard-Metzler dataset has been added, the following notebook explains the main features of this mod

Jesper Wohlert 313 Dec 27, 2022
Code for the paper: "On the Bottleneck of Graph Neural Networks and Its Practical Implications"

On the Bottleneck of Graph Neural Networks and its Practical Implications This is the official implementation of the paper: On the Bottleneck of Graph

75 Dec 22, 2022
Implementation of EMNLP 2017 Paper "Natural Language Does Not Emerge 'Naturally' in Multi-Agent Dialog" using PyTorch and ParlAI

Language Emergence in Multi Agent Dialog Code for the Paper Natural Language Does Not Emerge 'Naturally' in Multi-Agent Dialog Satwik Kottur, José M.

Karan Desai 105 Nov 25, 2022
ViSER: Video-Specific Surface Embeddings for Articulated 3D Shape Reconstruction

ViSER: Video-Specific Surface Embeddings for Articulated 3D Shape Reconstruction. NeurIPS 2021.

Gengshan Yang 59 Nov 25, 2022
tmm_fast is a lightweight package to speed up optical planar multilayer thin-film device computation.

tmm_fast tmm_fast or transfer-matrix-method_fast is a lightweight package to speed up optical planar multilayer thin-film device computation. It is es

26 Dec 11, 2022
PyTorch implementation of Federated Learning with Non-IID Data, and federated learning algorithms, including FedAvg, FedProx.

Federated Learning with Non-IID Data This is an implementation of the following paper: Yue Zhao, Meng Li, Liangzhen Lai, Naveen Suda, Damon Civin, Vik

Youngjoon Lee 48 Dec 29, 2022
Codes for "Solving Long-tailed Recognition with Deep Realistic Taxonomic Classifier"

Deep-RTC [project page] This repository contains the source code accompanying our ECCV 2020 paper. Solving Long-tailed Recognition with Deep Realistic

Gina Wu 16 May 26, 2022
Deep Learning & 3D Convolutional Neural Networks for Speaker Verification

TensorFlow implementation of 3D Convolutional Neural Networks for Speaker Verification - Official Project Page - Pytorch Implementation This repositor

Amirsina Torfi 753 Dec 17, 2022
Text-to-SQL in the Wild: A Naturally-Occurring Dataset Based on Stack Exchange Data

SEDE SEDE (Stack Exchange Data Explorer) is new dataset for Text-to-SQL tasks with more than 12,000 SQL queries and their natural language description

Rupert. 83 Nov 11, 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
Equivariant CNNs for the sphere and SO(3) implemented in PyTorch

Equivariant CNNs for the sphere and SO(3) implemented in PyTorch

Jonas Köhler 893 Dec 28, 2022
A Small and Easy approach to the BraTS2020 dataset (2D Segmentation)

BraTS2020 A Light & Scalable Solution to BraTS2020 | Medical Brain Tumor Segmentation (2D Segmentation) Developed the segmentation models for segregat

Gunjan Haldar 0 Jan 19, 2022
Author's PyTorch implementation of Randomized Ensembled Double Q-Learning (REDQ) algorithm.

REDQ source code Author's PyTorch implementation of Randomized Ensembled Double Q-Learning (REDQ) algorithm. Paper link: https://arxiv.org/abs/2101.05

109 Dec 16, 2022
Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue System

Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue System Authors: Yixuan Su, Lei Shu, Elman Mansimov, Arshit Gupta, Deng Cai, Yi-An Lai

Amazon Web Services - Labs 123 Dec 23, 2022
A Tensorfflow implementation of Attend, Infer, Repeat

Attend, Infer, Repeat: Fast Scene Understanding with Generative Models This is an unofficial Tensorflow implementation of Attend, Infear, Repeat (AIR)

Adam Kosiorek 82 May 27, 2022
PRIME: A Few Primitives Can Boost Robustness to Common Corruptions

PRIME: A Few Primitives Can Boost Robustness to Common Corruptions This is the official repository of PRIME, the data agumentation method introduced i

Apostolos Modas 34 Oct 30, 2022