Optimal kernel in KR can be data-dependent, improving model performance.
problem Fixed kernel in KR limits model performance.
method Considered data-dependent kernels for KR, using posterior covariance.
result Data-dependent kernel choice leads to optimal performance.
Large amounts of labeled data are typically required to train deep learning models. For many real-world problems, however, acquiring additional data can be expensive or even impossible. We present semi-supervised deep kernel learning (SSDKL), a semi-supervised regression model based on minimizing predictive variance in…
Deep kernel learning provides an elegant and principled framework for combining the structural properties of deep learning algorithms with the flexibility of kernel methods. By means of a deep neural network, we learn a parametrized kernel operator that can be combined with a differentiable kernel algorithm during infe…
Bayes-optimal learning of deep random networks with Gaussian weights is studied.
problem Learning a target function corresponding to a deep, extensive-width, non-linear neural network with random Gaussian weights.
method Closed-form expressions for Bayes-optimal test error, ridge regression, kernel and random features regression are computed.
result Optimally regularized ridge regression and kernel regression achieve Bayes-optimal performances, while logistic loss yields a near-optimal test error for classification.
In this paper, we propose a novel supervised learning method that is called Deep Embedding Kernel (DEK). DEK combines the advantages of deep learning and kernel methods in a unified framework. More specifically, DEK is a learnable kernel represented by a newly designed deep architecture. Compared with pre-defined kerne…
We apply a fast kernel method for mask-based single-channel speech enhancement. Specifically, our method solves a kernel regression problem associated to a non-smooth kernel function (exponential power kernel) with a highly efficient iterative method (EigenPro). Due to the simplicity of this method, its hyper-parameter…
The paper explains generalization in kernel regression and deep neural networks using spectral bias and task-model alignment.
problem Understanding generalization in machine learning models, especially deep neural networks.
method Analytical expression for generalization error derived from statistical mechanics, applied to various kernels and data distributions.
result Spectral bias and task-model alignment explain generalization in kernel regression and deep neural networks.
A new deep neural network tackles nonlinear functional regression with improved dimensionality reduction.
problem Nonlinear functional regression in infinite-dimensional functional data analysis.
method Functional deep neural network with adaptive kernel embedding and projection steps.
result Explicit rates of approximating nonlinear smooth functionals are derived, and the network is shown to be effective in both simulated and real datasets.
HKRR adapts to MIM, overcoming the curse of dimensionality.
problem Understanding when deep networks outperform kernel methods in high dimensions.
method Hyper-kernel ridge regression (HKRR) for multi-index models (MIM).
result HKRR can adaptively learn MIM, overcoming the curse of dimensionality.
Generalizes leverage score sampling for neural networks, accelerating kernel methods and deep learning.
problem Accelerating kernel methods and deep learning training.
method Generalizes leverage score sampling to neural networks and proves equivalence to neural tangent kernel ridge regression.
result Equivalence between regularized neural network and neural tangent kernel ridge regression under leverage score sampling initialization.
DSPPs improve predictive distributions in scalable regression tasks.
problem Improving predictive distributions in scalable regression tasks.
method Inspired by DGPs, DSPPs use mini-batch training and kernel basis functions for uncertainty control.
result DSPPs provide significantly better calibrated predictive distributions than other methods.
A framework and benchmark for deep batch active learning in neural networks.
problem Efficiently acquiring labels for neural network regression.
method Framework of base kernels, transformations, and selection methods; use of sketched finite-width neural tangent kernels and clustering.
result Proposed method outperforms state-of-the-art on benchmark, scales to large data sets.
Meta-learning improves Gaussian process uncertainty estimation.
problem Poor uncertainty estimation in Gaussian processes with deep kernels.
method Meta-learning to calibrate deep kernel GPs using task-specific uncalibrated and calibrated distributions.
result Improves uncertainty estimation performance with high regression performance.
Sharp bounds derived for test error of finite-rank kernel ridge regression.
problem Loose bounds on test error for finite-rank kernels in machine learning.
method Sharp non-asymptotic upper and lower bounds for KRR test error.
result Tighter bounds on finite-rank KRR test error, valid for any regularization parameters.
pGMM kernel outperforms ordinary ridge regression and RBF kernel ridge regression without tuning.
problem Comparing pGMM kernel regression with other ridge regression methods.
method Implemented and compared pGMM kernel regression with ordinary ridge regression and RBF kernel ridge regression.
result pGMM kernel performs well without tuning and can match boosted trees with parameter tuning.
Automates kernel discovery for longitudinal data analysis.
problem Handling irregularly sampled, sparse longitudinal data with multilevel correlation.
method Combines deep neural networks and non-parametric kernel methods to discover complex multilevel correlation structure.
result Significantly outperforms state-of-the-art methods on benchmark data sets.
DSoftKI scales GP regression with full derivative observations.
problem Efficiently fitting and predicting full derivative observations in Gaussian Processes.
method Extends SoftKI by using local temperature vectors for interpolation, enabling encoding of local directional sensitivity.
result DSoftKI achieves accurate predictions and scales to larger datasets with full derivative observations.
Deep neural networks for structured prediction using kernel-induced losses.
problem Structured prediction tasks for images and texts.
method Designing a novel family of deep neural architectures that predict in a finite-dimensional subspace derived from the kernel-induced loss.
result Gradient descent algorithms can be used for structured prediction with deep neural networks.
The evolution of a deep neural network trained by the gradient descent can be described by its neural tangent kernel (NTK) as introduced in [20], where it was proven that in the infinite width limit the NTK converges to an explicit limiting kernel and it stays constant during training. The NTK was also implicit in some…
DFIV uses deep features for IV regression, achieving optimal rates.
problem Optimal IV regression with deep features for complex target functions.
method Two-stage approach: deep feature learning followed by IV regression.
result DFIV achieves minimax optimal learning rate under certain conditions.
KITT uses transformers to quickly recommend kernels for GP models.
problem Kernel selection for high-dimensional GP regression models.
method Transformer-based architecture for generating kernel recommendations.
result KITT selects kernels that perform well on various regression benchmarks.
The NNGP kernel's predictions closely match those of the Matern kernel under certain conditions.
problem Comparing NNGP kernels to Matern kernels in practical applications.
method Demonstrated the necessity of normalization for NNGP kernels, explored numerical challenges, and compared predictions and performance.
result NNGP kernel predictions closely match Matern kernel predictions under specific circumstances.
Neural networks generalize well despite overfitting due to high capacity.
problem Understanding why deep neural networks generalize well in overparameterized settings.
method High-dimensional asymptotic analysis of generalization under kernel regression with Neural Tangent Kernel.
result Test error exhibits non-monotonic behavior and can have additional peaks and descents in the overparameterized regime.
Proposes DAK model for improved GP computations.
problem Challenges in high-dimensional GP layers in DKL.
method Additive structure and induced prior approximation for GP units.
result Outperforms state-of-the-art DKL methods in regression and classification.
Conditional DGP learns effective kernels from low-fidelity data.
problem Learning effective kernels for multi-fidelity regression.
method Conditional DGP with moment matching for implicit kernel approximation.
result Effective kernels are learned from lower-fidelity data, improving multi-fidelity regression.
The necessary and sufficient conditions for existence of a generalized representer theorem are presented for learning Hilbert space-valued functions. Representer theorems involving explicit basis functions and Reproducing Kernels are a common occurrence in various machine learning algorithms like generalized least squa…
FFN addresses spectral bias in neural value approximation, improving reinforcement learning performance.
problem Spectral bias in neural value approximation, leading to slow convergence and poor performance.
method Proposes Fourier feature networks (FFN) to overcome spectral bias by using a composite neural tangent kernel.
result FFN achieves state-of-the-art performance on challenging continuous control domains with faster convergence and better stability.
Accelerates GPR with localized kernels for faster performance.
problem Speeding up Gaussian process regression.
method Localization kernels applied at each data point to down-weight distant points, leading to a sparsified Gram matrix.
result Significant speedups with competitive performance compared to other methods.
ResNets and DenseNets converge to NTK with depth and width, offering advantages for kernel regression.
problem Understanding convergence of ResNets and DenseNets to Neural Tangent Kernel (NTK).
method Analysis of finite width and depth corrections for NTK of ResNets and DenseNets.
result ResNets and DenseNets can converge to NTK with depth and width, unlike vanilla networks.
Simplified kernel ridge regression with a conservation law.
problem Understanding the test risk and generalization of kernel ridge regression.
method Identification of a conservation law that limits KRR's learning ability, leading to simplified expressions for test risk.
result Transparency in test risk expressions through the conserved quantity in the kernel eigenbasis.
Paper analyzes SGD in kernel regression, showing it outperforms offline methods.
problem Performance of SGD in kernel regression compared to offline methods.
method Analyzes Stochastic Gradient Descent (SGD) in kernel regression under misspecified models.
result SGD achieves min-max optimal rates up to constants, avoiding saturation.
Survey of SDR methods for high-dimensional regression and embedding.
problem Reducing dimensionality in high-dimensional data.
method Involves both statistical and machine learning approaches, covering inverse and forward regression methods.
result Supervised Kernel Dimension Reduction is equivalent to supervised PCA.
The paper tackles counterfactual inference with multioutput deep kernels in high-dimensional settings.
problem Performing counterfactual inference with observational data in high-dimensional settings with multiple actions and outcomes.
method The paper presents a general class of counterfactual multi-task deep kernels models based on Structural Causal Models (SCM) and Gaussian Processes.
result The models estimate causal effects and learn policies efficiently, scaling well with high dimensions.
Paper converts deep networks to flat, equivalent kernel machines.
problem Capacity control and uniform convergence in deep learning.
method Push-forward transformation from deep networks to indefinite kernel machines.
result Flat network weights are Lp-norm regularized (0<p<1).
Convolutional DKMs improve kernel methods on MNIST, CIFAR-10, and CIFAR-100.
problem Improving kernel methods for image classification.
method Developed a novel inter-domain inducing point approximation and introduced various techniques to extend DKMs to convolutional networks.
result Achieved state-of-the-art performance on image classification benchmarks.
Simplifies transfer learning with deep neural networks using ridge regression.
problem High computational cost of finetuning deep models for transfer learning.
method Leverage the low-rank property of deep neural networks' feature vectors in kernel ridge regression.
result Successful on supervised and semi-supervised transfer learning tasks.
Deep-HGP uses Bayesian nonparametric approach for complex data regression.
problem Complex data regression with compositional structures.
method Deep Gaussian processes with a squared-exponential kernel, data-driven lengthscale parameters.
result Posterior distribution optimally recovers unknown true regression curve in terms of quadratic loss.
DANCE improves prediction set efficiency for deep learning models.
problem Inefficient, overly conservative prediction sets for pre-trained models.
method DANCE combines adaptive kernel regression and nearest-neighbor approach.
result DANCE produces more efficient and robust prediction sets.
DBKs enable scalable GPs with tractable inference for large datasets.
problem Scaling Gaussian processes to large and complex datasets while maintaining tractable inference.
method DBKs constructed from neural-network-parameterized basis functions with explicit low-rank structure, enabling linear-complexity inference.
result DBKs provide a unified perspective and improve predictive accuracy, uncertainty quantification, and computational efficiency.
TNP-KR improves scalability of NPs with Transformer blocks and attention mechanisms.
problem Scalability bottleneck in NPs and GPs, especially for large datasets.
method Introduces TNP-KR with KRBlock, kernel-based attention, and two attention mechanisms.
result TNP-KR with DKA outperforms Performer and achieves state-of-the-art results.
New findings on kernel regression in the quadratic regime, improving understanding of machine learning models.
problem Understanding kernel ridge regression in the quadratic asymptotic regime.
method Extended study of kernel regression to the quadratic regime, establishing approximation bounds and spectral distributions.
result Broad class of inner-product kernels exhibit behavior similar to a quadratic kernel, with precise asymptotic training and test errors characterized.
DGPFM uses deep Gaussian processes to map functions accurately and quantify uncertainty.
problem Learning mappings between functional spaces, especially when data are noisy, sparse, or irregularly sampled.
method Constructs a sequence of GP-based linear and nonlinear transformations directly in function space, leveraging kernel integral transforms, GP conditional means, and nonlinear activations sampled from Gaussian processes.
result Empirical results show DGPFM outperforms existing methods in predictive accuracy and uncertainty calibration.
Novel framework predicts brain biomarker trajectories with superior performance.
problem Challenges in estimating longitudinal brain biomarker trajectories due to variability, inconsistencies, and irregular measurements.
method Personalized deep kernel regression with Adaptive Shrinkage Estimation.
result Superior predictive performance compared to state-of-the-art models.
K-StoNet improves neural networks by avoiding local minima and assessing uncertainty.
problem Local minima and prediction uncertainty in deep neural networks.
method Combines SVR with latent variable model, using RBF kernel for feature space mapping and IRO algorithm for training.
result The model asymptotically converges to the global optimum and assesses prediction uncertainty easily.
Strong inductive biases prevent harmless interpolation in overparameterized models.
problem Understanding the conditions under which overparameterized models can interpolate noise without overfitting.
method Theoretical analysis of high-dimensional kernel regression and deep neural networks, focusing on the role of inductive biases.
result The strength of an estimator's inductive bias determines whether interpolation is harmless or requires fitting noise for good generalization.
Novel neural GP kernels learn stable, flexible covariance structures.
problem Scalable and flexible covariance kernels for Gaussian processes.
method Directly learn kriging coefficients and conditional standard deviations using deep neural architectures exploiting permutation-equivariant structure.
result Improved training stability and data efficiency with expressive, non-stationary kernels.
Deep neural networks enforce non-crossing quantile regression curves.
problem Estimating quantile regression curves without crossing.
method Penalized deep ReQU neural networks with a non-crossing penalty.
result Established non-asymptotic risk and error bounds for the estimated QRP.
Survival kernets scale deep kernel survival analysis to large datasets with interpretability and theoretical guarantees.
problem Scalable and interpretable deep kernel survival analysis for large datasets.
method Survival kernets use kernel netting for training set compression and XGBoost for warm-starting neural architecture search.
result Survival kernets achieve optimal time-dependent concordance index on various survival analysis datasets.