Derivative Process

Derivative processes, encompassing the study and application of derivatives of functions and data, are central to numerous fields, aiming to improve model accuracy, efficiency, and interpretability. Current research focuses on leveraging derivative information within various machine learning models, including Gaussian processes, neural networks (both convolutional and fully connected), and tree-based ensembles, to enhance prediction accuracy and efficiency in tasks such as classification, regression, and change-point detection. This work has significant implications across diverse domains, from financial risk prediction and high-energy physics to materials science and signal processing, by enabling more robust and informative models.

Papers

October 29, 2024

FreeGaussian: Guidance-free Controllable 3D Gaussian Splats with Flow Derivatives
Qizhi Chen, Delin Qu, Yiwen Tang, Haoming Song, Yiting Zhang, Dong Wang, Bin Zhao, Xuelong Li
3D Gaussian Flow Mood Object Trajectory 3D Gaussian Splat Derivative Process

September 26, 2024

Enriched Functional Tree-Based Classifiers: A Novel Approach Leveraging Derivatives and Geometric Features
Fabrizio Maturo, Annamaria Porreca
Random Forest Novel Approach Geometric Feature Tree Based Functional Data Analysis Classification Tree Derivative Process

August 27, 2024

Evaluating Credit VIX (CDS IV) Prediction Methods with Incremental Batch Learning
Robert Taylor
Class Incremental Learning Risk Prediction Prediction Method Credit Risk Derivative Process Volatility Index

August 3, 2024

Batch Active Learning in Gaussian Process Regression using Derivatives
Hon Sum Alec Yu, Christoph Zimmer, Duy Nguyen-Tuong
Gaussian Process Gaussian Process Regression Total Correlation Derivative Process Batch Active Learning

May 24, 2024

Derivatives of Stochastic Gradient Descent
Franck Iutzeler, Edouard Pauwels, Samuel Vaiter
Stochastic Gradient Descent Hyperparameter Optimization Stochastic Optimization Problem Derivative Process Stochastic Recursive Gradient Exponential Convergence

May 16, 2024

Estimating a Function and Its Derivatives Under a Smoothness Condition
Eunji Lim
Simple Function Linear Estimator Quadratic Program Derivative Process Generalized Smoothness

December 5, 2023

Active Learning for Abrupt Shifts Change-point Detection via Derivative-Aware Gaussian Processes
Hao Zhao, Rong Pan
Active Learning Gaussian Process Change Detection Change Point Detection Derivative Process

October 2, 2023

Cryptocurrency Portfolio Optimization by Neural Networks
Quoc Minh Nguyen, Dat Thanh Tran, Juho Kanniainen, Alexandros Iosifidis, Moncef Gabbouj
Neural Network Deep Neural Network Derivative Process Variance Portfolio Novel Loss

August 31, 2023

Branches of a Tree: Taking Derivatives of Programs with Discrete and Branching Randomness in High Energy Physics
Michael Kagan, Lukas Heinrich
Optimization Purpose High Energy Physic Gradient Estimation Discrete Environment Inherent Randomness Past Present Temporal Program Derivative Process Detector Design Optimization

July 14, 2023

CeRF: Convolutional Neural Radiance Fields for New View Synthesis with Derivatives of Ray Modeling
Xiaoyan Yang, Dingbo Lu, Yang Li, Chenhui Li, Changbo Wang
Novel View Synthesis View Generation Derivative Process Ray Based Neural Ray

January 7, 2023

Investigations on convergence behaviour of Physics Informed Neural Networks across spectral ranges and derivative orders
Mayank Deshpande, Siddharth Agarwal, Vukka Snigdha, Arya Kumar Bhattacharya
Loss Function Physic Informed Neural Network Neural Tangent Kernel Comprehensive Investigation Spectral Bias Convergence Behavior Derivative Process Spectral Band

August 23, 2022

Naive Penalized Spline Estimators of Derivatives Achieve Optimal Rates of Convergence
Bright Antwi Boasiako, John Staudenmayer
Early Stage Convergence Optimal Rate Derivative Process

May 31, 2022

Molecular Dipole Moment Learning via Rotationally Equivariant Gaussian Process Regression with Derivatives in Molecular-orbital-based Machine Learning
Jiace Sun, Lixue Cheng, Thomas F. Miller
Derivative Process Dipole Moment

May 12, 2022

Vision Transformer: Vit and its Derivatives
Zujun Fu
Convolutional Neural Network Vision Transformer Transformer Based Attention Based Encoder Decoder Derivative Process Deeper ViT S 54

February 24, 2022

Phase Continuity: Learning Derivatives of Phase Spectrum for Speech Enhancement
Doyeon Kim, Hyewon Han, Hyeon-Kyeong Shin, Soo-Whan Chung, Hong-Goo Kang
Speech Enhancement Neural Speech Enhancement Enhanced Speech Derivative Process Phase Spectrum Phase Perturbation

January 15, 2022

Physical Derivatives: Computing policy gradients by physical forward-propagation
Arash Mehrjou, Ashkan Soleymani, Stefan Bauer, Bernhard Schölkopf
Policy Gradient Model Based Reinforcement Learning Model Free Dynamic Model Physical System Backward Propagation Derivative Process Custom Robot

Derivative Process

Papers

FreeGaussian: Guidance-free Controllable 3D Gaussian Splats with Flow Derivatives

Enriched Functional Tree-Based Classifiers: A Novel Approach Leveraging Derivatives and Geometric Features

Evaluating Credit VIX (CDS IV) Prediction Methods with Incremental Batch Learning

Batch Active Learning in Gaussian Process Regression using Derivatives

Derivatives of Stochastic Gradient Descent

Estimating a Function and Its Derivatives Under a Smoothness Condition

Active Learning for Abrupt Shifts Change-point Detection via Derivative-Aware Gaussian Processes

Cryptocurrency Portfolio Optimization by Neural Networks

Branches of a Tree: Taking Derivatives of Programs with Discrete and Branching Randomness in High Energy Physics

CeRF: Convolutional Neural Radiance Fields for New View Synthesis with Derivatives of Ray Modeling

Investigations on convergence behaviour of Physics Informed Neural Networks across spectral ranges and derivative orders

Naive Penalized Spline Estimators of Derivatives Achieve Optimal Rates of Convergence

Molecular Dipole Moment Learning via Rotationally Equivariant Gaussian Process Regression with Derivatives in Molecular-orbital-based Machine Learning

Vision Transformer: Vit and its Derivatives

Phase Continuity: Learning Derivatives of Phase Spectrum for Speech Enhancement

Physical Derivatives: Computing policy gradients by physical forward-propagation