Deep Kernel Learning

Deep kernel learning (DKL) combines the representational power of deep neural networks with the uncertainty quantification of Gaussian processes to build powerful and flexible machine learning models. Current research focuses on improving DKL's scalability and efficiency through novel architectures like Kolmogorov-Arnold networks and integrating it with other techniques such as Bayesian optimization and active learning, particularly for high-dimensional data in domains like molecular discovery and process optimization. This approach offers significant advantages in handling complex datasets, providing reliable uncertainty estimates, and enabling efficient exploration of large search spaces, impacting diverse fields from materials science to control systems.

Papers

October 8, 2024

Stochastic Kernel Regularisation Improves Generalisation in Deep Kernel Machines
Edward Milsom, Ben Anson, Laurence Aitchison
Strong Generalization Kernel Method Deep Kernel Learning

October 4, 2024

Rapid optimization in high dimensional space by deep kernel learning augmented genetic algorithms
Mani Valleti, Aditya Raghavan, Sergei V. Kalinin
Bayesian Optimization Genetic Algorithm Deep Kernel Learning Deep Kernel Deep Learning Based Surrogate

October 2, 2024

Deep Kernel Posterior Learning under Infinite Variance Prior Weights
Jorge Loría, Anindya Bhadra
Shallow Neural Network Bayesian Deep Learning Deep Kernel Learning Unbounded Variance Covariance Kernel

August 26, 2024

gWaveNet: Classification of Gravity Waves from Noisy Satellite Data using Custom Kernel Integrated Deep Learning Method
Seraj Al Mahmud Mostafa, Omar Faruque, Chenxi Wang, Jia Yue, Sanjay Purushotham, Jianwu Wang
Classification Code Noisy Data Gravitational Wave Deep Kernel Learning Atmospheric Dynamic

July 30, 2024

DKL-KAN: Scalable Deep Kernel Learning using Kolmogorov-Arnold Networks
Shrenik Zinage, Sudeepta Mondal, Soumalya Sarkar
Gaussian Process Deep Learning Architecture Kolmogorov Arnold Network Deep Kernel Learning Large Scale Kernel

March 2, 2024

Active Deep Kernel Learning of Molecular Functionalities: Realizing Dynamic Structural Embeddings
Ayana Ghosh, Maxim Ziatdinov and, Sergei V. Kalinin
Deep Kernel Learning Dynamic Embeddings Molecular Discovery Molecular Functionality

September 18, 2023

Convolutional Deep Kernel Machines
Edward Milsom, Ben Anson, Laurence Aitchison
Deep Gaussian Process Deep Kernel Learning Neural Network Gaussian Process

September 12, 2023

Promises of Deep Kernel Learning for Control Synthesis
Robert Reed, Luca Laurenti, Morteza Lahijanian
Stochastic Dynamical System Promise Complex Dynamical System Control Synthesis Deep Kernel Learning

August 9, 2023

Efficient Bayesian Optimization with Deep Kernel Learning and Transformer Pre-trained on Multiple Heterogeneous Datasets
Wenlong Lyu, Shoubo Hu, Jie Chuai, Zhitang Chen
Transformer Based Gaussian Process Bayesian Optimization Surrogate Model Black Box Optimization Heterogeneous Datasets Black Box Optimization Problem Deep Kernel Learning

June 6, 2023

DEK-Forecaster: A Novel Deep Learning Model Integrated with EMD-KNN for Traffic Prediction
Sajal Saha, Sudipto Baral, Anwar Haque
Traffic Prediction Deep Kernel Learning Empirical Mode Decomposition

May 23, 2023

Deep Learning with Kernels through RKHM and the Perron-Frobenius Operator
Yuka Hashimoto, Masahiro Ikeda, Hachem Kadri
Deep Learning Kernel Method Kernel Hilbert Space Reproducing Kernel Hilbert Space Small Kernel Non Linear Operator Deep Kernel Learning

March 25, 2023

Deep Kernel Methods Learn Better: From Cards to Process Optimization
Mani Valleti, Rama K. Vasudevan, Maxim A. Ziatdinov, Sergei V. Kalinin
Optimization Purpose Latent Space Latent Manifold Deep Kernel Learning Classical Autoencoders

February 28, 2023

Interactive Segmentation as Gaussian Process Classification
Minghao Zhou, Hong Wang, Qian Zhao, Yuexiang Li, Yawen Huang, Deyu Meng, Yefeng Zheng
Semantic Segmentation Gaussian Process Interactive Segmentation Deep Kernel Learning Poor Segmentation Pixel Wise Classification

February 19, 2023

Guided Deep Kernel Learning
Idan Achituve, Gal Chechik, Ethan Fetaya
Deep Kernel Learning Deep Kernel Neural Network Gaussian Process Infinite Width Neural Network Kernel Optimization

December 5, 2022

High-Dimensional Yield Estimation using Shrinkage Deep Features and Maximization of Integral Entropy Reduction
Shuo Yin, Guohao Dai, Wei W. Xing
Large Scale Circuit Yield Prediction Balancing Efficiency Deep Kernel Learning Feature Reduction

December 1, 2022

Deep Kernel Learning for Mortality Prediction in the Face of Temporal Shift
Miguel Rios, Ameen Abu-Hanna
Human Face Neural Model Prediction Uncertainty Temporal Shift Neural Network Baseline Mortality Prediction Overconfident Prediction Deep Kernel Learning

August 27, 2022

Deep Kernel Learning of Dynamical Models from High-Dimensional Noisy Data
Nicolò Botteghi, Mengwu Guo, Christoph Brune
Latent Dynamic Dynamical Model Dimensional State Space Deep Kernel Learning Low Dimensional High Dimensional Noisy

May 5, 2022

Meta-learning Adaptive Deep Kernel Gaussian Processes for Molecular Property Prediction
Wenlin Chen, Austin Tripp, José Miguel Hernández-Lobato
Gaussian Process Molecular Property Prediction Deep Kernel Learning

March 18, 2022

Active learning in open experimental environments: selecting the right information channel(s) based on predictability in deep kernel learning
Maxim Ziatdinov, Yongtao Liu, Sergei V. Kalinin
Active Learning Predictability Problem Quantitative Structure Activity Relationship Deep Kernel Learning Deep Kernel Structure Property Relationship