Alternatives to Deep Neural Networks for Function Approximations in Finance

Related tags

Deep Learningaltnnpub
Overview

Alternatives to Deep Neural Networks for Function Approximations in Finance

Code companion repo

Overview

This is a repository of Python code to go with our paper whose details could be found below

We provide our implementations of the generalized stochastic sampling (gSS) and functional Tensor Train (fTT) algorithms from the paper, and related routines. This is a somewhat simplified version of the code that produced the test results that we reported. Simplifications were made to improve clarity and increase general didactic value, at a (small) expense of cutting out some of the secondary tricks and variations.

The code is released under the MIT License

Installing the code

You do not have to install this package once you have downloaded it -- see the next section on how to use it without any installation. But if you want to call our routines from a different project or directory, execute the following (note you need to run this from altnnpub directory, assuming this is the root of the project directory -- the directory where this file that you are reading is located)

altnnpub>pip install -e .

Then you can call various methods from your code like this

from nnu import gss_kernels
kernel = gss_kernels.global_kernel_dict(1.0)['invquad']
...

to uninstall the package, run (from anywhere)

blah>pip uninstall altnnpub

Running the code

The main entry point to the code is main.py in ./nnu folder. Assuming the project directory is called altnnpub, the code is run via Python module syntax

altnnpub>python -m nnu.main

Various options such as which functions to fit, which models to use, and so on can be set in main.py

Results are reported in the terminal and are also stored in ./results directory

All of our (non-test) Python code is in ./nnu directory

Jupyter notebooks

We provide a number of notebooks that demonstrate, at varying levels of detail, how to build and use certain models

  • ftt_als_01.ipynb: Functional Tensor Train (fTT) approximation using the Alternating Least Squares (ALS) algorithm
  • functional_2D_low_rank_01.ipynb: Low-rank functional approximation of 2D functions done manually. This is an illustrative example of ALS applied to calculate successive rank-1 approximations, as described in the paper
  • gss_example_keras_direct_01.ipynb: Create and test the generalized Stochastic Sampling (gSS) model. In this notebook do it "by hand", ie using granular interfaces such as the Keras functional interface. Here we create a hidim version of the model with the Adam optimizer for the frequency bounds (aka scales) and linear regression for the outer (linear) weights
  • gss_example_model_factory_01.ipynb: Create and test the generalized Stochastic Sampling (gSS) model. This notebook uses gss_model_factory and other higher-level interfaces that the main entry point (./nnu/main.py) eventually calls. We create a onedim version of the model with a one-dim optimizer for the frequency bounds (aka scales) and linear regression for the outer (linear) weights

Test suite

Unit tests are collected in ./test directory and provide useful examples of how different parts of the code can be used. The test suite can be run in the standard Python way using pytest, e.g. from the comamnd line at the project root directory:

altnnpub>pytest

Pytest is installed with pip install pytest command

Individual tests can be run using a pytest -k test_blah type command, which could be useful for debugging. This is all very well explained in pytest documentation

Tests are there predominantly to show how to call certain functions. They mostly test that the code simply runs rather than testing numbers, etc. except for tests in test_gss_report_generator.py where actual fitting results are compared to the expected ones. Tests produce various output that could be interesting to see -- option pytest -s will print out whatever the tests are printing out

Requirements

The code has been tested with Python 3.7 and 3.8. See requirements.txt for required packages

Contacting us

Our contact details are in the SSRN link below

Details of the paper

Antonov, Alexandre and Piterbarg, Vladimir, Alternatives to Deep Neural Networks for Function Approximations in Finance (November 7, 2021). Available at SSRN: https://ssrn.com/abstract=3958331 or http://dx.doi.org/10.2139/ssrn.3958331

Kaggleship: Kaggle Notebooks

Kaggleship: Kaggle Notebooks This repository contains my Kaggle notebooks. They are generally about data science, machine learning, and deep learning.

Erfan Sobhaei 1 Jan 25, 2022
[CVPR'21] MonoRUn: Monocular 3D Object Detection by Reconstruction and Uncertainty Propagation

MonoRUn MonoRUn: Monocular 3D Object Detection by Reconstruction and Uncertainty Propagation. CVPR 2021. [paper] Hansheng Chen, Yuyao Huang, Wei Tian*

同济大学智能汽车研究所综合感知研究组 ( Comprehensive Perception Research Group under Institute of Intelligent Vehicles, School of Automotive Studies, Tongji University) 96 Dec 10, 2022
Binary classification for arrythmia detection with ECG datasets.

HEART DISEASE AI DATATHON 2021 [Eng] / [Kor] #English This is an AI diagnosis modeling contest that uses the heart disease echocardiography and electr

HY_Kim 3 Jul 14, 2022
Deep Neural Networks Improve Radiologists' Performance in Breast Cancer Screening

Deep Neural Networks Improve Radiologists' Performance in Breast Cancer Screening Introduction This is an implementation of the model used for breast

757 Dec 30, 2022
A TensorFlow implementation of SOFA, the Simulator for OFfline LeArning and evaluation.

SOFA This repository is the implementation of SOFA, the Simulator for OFfline leArning and evaluation. Keeping Dataset Biases out of the Simulation: A

22 Nov 23, 2022
Deep Text Search is an AI-powered multilingual text search and recommendation engine with state-of-the-art transformer-based multilingual text embedding (50+ languages).

Deep Text Search - AI Based Text Search & Recommendation System Deep Text Search is an AI-powered multilingual text search and recommendation engine w

19 Sep 29, 2022
Air Quality Prediction Using LSTM

AirQualityPredictionUsingLSTM In this Repo, i present to you the winning solution of smart gujarat hackathon 2019 where the task was to predict the qu

Deepak Nandwani 2 Dec 13, 2022
Poplar implementation of "Bundle Adjustment on a Graph Processor" (CVPR 2020)

Poplar Implementation of Bundle Adjustment using Gaussian Belief Propagation on Graphcore's IPU Implementation of CVPR 2020 paper: Bundle Adjustment o

Joe Ortiz 34 Dec 05, 2022
SegTransVAE: Hybrid CNN - Transformer with Regularization for medical image segmentation

SegTransVAE: Hybrid CNN - Transformer with Regularization for medical image segmentation This repo is the official implementation for SegTransVAE. Seg

Nguyen Truong Hai 4 Aug 04, 2022
The repository offers the official implementation of our paper in PyTorch.

Cloth Interactive Transformer (CIT) Cloth Interactive Transformer for Virtual Try-On Bin Ren1, Hao Tang1, Fanyang Meng2, Runwei Ding3, Ling Shao4, Phi

Bingoren 49 Dec 01, 2022
ConE: Cone Embeddings for Multi-Hop Reasoning over Knowledge Graphs

ConE: Cone Embeddings for Multi-Hop Reasoning over Knowledge Graphs This is the code of paper ConE: Cone Embeddings for Multi-Hop Reasoning over Knowl

MIRA Lab 33 Dec 07, 2022
FedMM: Saddle Point Optimization for Federated Adversarial Domain Adaptation

This repository contains the code accompanying the paper " FedMM: Saddle Point Optimization for Federated Adversarial Domain Adaptation" Paper link: R

20 Jun 29, 2022
When in Doubt: Improving Classification Performance with Alternating Normalization

When in Doubt: Improving Classification Performance with Alternating Normalization Findings of EMNLP 2021 Menglin Jia, Austin Reiter, Ser-Nam Lim, Yoa

Menglin Jia 13 Nov 06, 2022
Graph-Refined Convolutional Network for Multimedia Recommendation with Implicit Feedback

Graph-Refined Convolutional Network for Multimedia Recommendation with Implicit Feedback This is our Pytorch implementation for the paper: Yinwei Wei,

17 Jun 10, 2022
Public Implementation of ChIRo from "Learning 3D Representations of Molecular Chirality with Invariance to Bond Rotations"

Learning 3D Representations of Molecular Chirality with Invariance to Bond Rotations This directory contains the model architectures and experimental

35 Dec 05, 2022
The official PyTorch code implementation of "Human Trajectory Prediction via Counterfactual Analysis" in ICCV 2021.

Human Trajectory Prediction via Counterfactual Analysis (CausalHTP) The official PyTorch code implementation of "Human Trajectory Prediction via Count

46 Dec 03, 2022
LERP : Label-dependent and event-guided interpretable disease risk prediction using EHRs

LERP : Label-dependent and event-guided interpretable disease risk prediction using EHRs This is the code for the LERP. Dataset The dataset used is MI

5 Jun 18, 2022
A Nim frontend for pytorch, aiming to be mostly auto-generated and internally using ATen.

Master Release Pytorch - Py + Nim A Nim frontend for pytorch, aiming to be mostly auto-generated and internally using ATen. Because Nim compiles to C+

Giovanni Petrantoni 425 Dec 22, 2022
This example implements the end-to-end MLOps process using Vertex AI platform and Smart Analytics technology capabilities

MLOps with Vertex AI This example implements the end-to-end MLOps process using Vertex AI platform and Smart Analytics technology capabilities. The ex

Google Cloud Platform 238 Dec 21, 2022
Wileless-PDGNet Implementation

Wileless-PDGNet Implementation This repo is related to the following paper: Boning Li, Ananthram Swami, and Santiago Segarra, "Power allocation for wi

6 Oct 04, 2022