Patrick Kidger
8 papers · 2019–2021 · 4 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
🌉 Interdisciplinary Bridge · Bronze 🌍 Conference Polyglot · Bronze 🗺️ Taxonomy Completionist (16) 🐣 Hot Topic Early Bird 👑 Triple Crown
🏆
Keyword Champion
(2)
⚡
Prolific Year · Productive
Venues
Top co-authors
Research topics
Machine Learning
(8)
Deep Learning
(6)
Core Methods
(6)
Architectures
(5)
Optimization & Theory · Machine Learning
(4)
Optimization & Theory · Deep Learning
(3)
Computer Science
(1)
Data Science & Analytics
(1)
Mathematics & Optimization
(1)
Applications
(1)
Learning Types
(1)
Mathematics
(1)
Methods
(1)
Models
(1)
Keywords
neural differential equation
(3)
neural network
(3)
time series
(3)
controlled differential equation
(2)
stochastic differential equation
(2)
adjoint method
(2)
brownian motion
(2)
variational autoencoder
(1)
deep learning
(1)
function approximation
(1)
data stream
(1)
recurrent neural network
(1)
gpu computing
(1)
continuous time
(1)
deep learning theory
(1)
activation function
(1)
approximation theory
(1)
multivariate time series
(1)
rough path theory
(1)
adaptive step size
(1)
Papers
Efficient and Accurate Gradients for Neural SDEs
NeurIPS 2021
"Hey, that’s not an ODE": Faster ODE Adjoints via Seminorms
ICML 2021
Neural Rough Differential Equations for Long Time Series
ICML 2021
Neural SDEs as Infinite-Dimensional GANs
ICML 2021
Signatory: differentiable computations of the signature and logsignature transforms, on both CPU and GPU
ICLR 2021
Neural Controlled Differential Equations for Irregular Time Series
NeurIPS 2020
Universal Approximation with Deep Narrow Networks
COLT 2020
Deep Signature Transforms
NeurIPS 2019