arXiv research

This paper improves kernel-based regression using transfer learning.

Framework for transferring discount curve estimates across fixed-income product classes.

SATL adapts to varying smoothness in hypothesis transfer learning.

New method tackles concept shifts in nonparametric regression using robust and adaptive transfer learning.

Proposes CVKT to complete missing kernel matrices across multiple views.

New method transfers emotions in facial images.

The study addresses negative transfer in multi-output Gaussian processes by proposing latent structures.

Paper introduces a new multi-kernel algorithm for better gradient approximation.

Kernel transfer operators, which can be regarded as approximations of transfer operators such as the Perron-Frobenius or Koopman operator in reproducing kernel Hilbert spaces, are defined in terms of covariance and cross-covariance operators and have been shown to be closely related to the conditional mean embedding fr…

A new method estimates generative model mappings using kernel transfer operators, reducing costs and improving performance.

Transfer operators such as the Perron--Frobenius or Koopman operator play an important role in the global analysis of complex dynamical systems. The eigenfunctions of these operators can be used to detect metastable sets, to project the dynamics onto the dominant slow processes, or to separate superimposed signals. We …

Neural networks can learn useful representations that kernels can't.

This work improves knowledge distillation by transferring full kernel matrices efficiently.

The ability of a human being to extrapolate previously gained knowledge to other domains inspired a new family of methods in machine learning called transfer learning. Transfer learning is often based on the assumption that objects in both target and source domains share some common feature and/or data space. In this p…

TAP transfers knowledge from unlabeled data to improve cross-modal learning.

Bayesian meta-learning improves few-shot learning with deep kernels.

Knowledge transfer speeds up neural classifier training.

Method leverages data transfer for estimating CATE with KRR.

MetaNOR learns common nonlocal kernels for efficient metamaterial modeling.

Paper develops methods for analyzing forms with synchronized singularities.

Optimal scheme minimizes deviation in federated transfer learning for kernel regression.

The study analyzes transfer learning in infinite-width neural networks, improving generalization on target tasks.

KM method reduces ConvNet parameters to 9% higher accuracy with minimal additional memory.

New method for efficient personalized learning in mobile health.

We consider the Hypothesis Transfer Learning (HTL) problem where one incorporates a hypothesis trained on the source domain into the learning procedure of the target domain. Existing theoretical analysis either only studies specific algorithms or only presents upper bounds on the generalization error but not on the exc…

Study on neural networks' performance in sequential task learning.

The paper analyzes covariate shift in nonparametric regression with Markovian data.

Improves robust transfer learning with side information.

The present work shows the application of transfer learning for a pre-trained deep neural network (DNN), using a small image dataset ($\approx$ 12,000) on a single workstation with enabled NVIDIA GPU card that takes up to 1 hour to complete the training task and archive an overall average accuracy of $94.7\%$. The DNN …

Efficiently fine-tunes patient-independent seizure detection models with tensor kernel machine.

DeltaBO accelerates Bayesian optimization with theoretical guarantees.

Simplifies transfer learning with deep neural networks using ridge regression.

TransBoost improves financial inclusion by evaluating individual financial risk.

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…

Study improves hypothesis transfer learning for functional linear models.

This paper presents regression models obtained from a process of blind prediction of peptide binding affinity from provided descriptors for several distinct datasets as part of the 2006 Comparative Evaluation of Prediction Algorithms (COEPRA) contest. This paper finds that kernel partial least squares, a nonlinear part…

Sharp bounds derived for test error of finite-rank kernel ridge regression.

Bayesian optimisation is a popular technique for hyperparameter learning but typically requires initial exploration even in cases where similar prior tasks have been solved. We propose to transfer information across tasks using learnt representations of training datasets used in those tasks. This results in a joint Gau…

Learning powerful data embeddings has become a center piece in machine learning, especially in natural language processing and computer vision domains. The crux of these embeddings is that they are pretrained on huge corpus of data in a unsupervised fashion, sometimes aided with transfer learning. However currently in …

A new framework for robust transfer learning that avoids negative transfer in domains with unequal information.

Develops kernels for matchings, overcoming computational challenges.

Kernel embeddings help estimate causal effects from observational data.

New method finds sparse networks without labels, improving performance.

Proposes a curriculum-based scheme to smooth CNN feature embeddings.

The purpose of this paper is to introduce a concept of equivalence between machine learning algorithms. We define two notions of algorithmic equivalence, namely, weak and strong equivalence. These notions are of paramount importance for identifying when learning prop erties from one learning algorithm can be transferre…

Model projection transfers convolutional network properties to feedforward networks.

Study shows how transformers classify symbols without naming them, proving a margin-versus-collision criterion.

We illustrate relationships between classical kernel-based dimensionality reduction techniques and eigendecompositions of empirical estimates of reproducing kernel Hilbert space (RKHS) operators associated with dynamical systems. In particular, we show that kernel canonical correlation analysis (CCA) can be interpreted…