Transfer learning for nonparametric classification: minimax rate and adaptive classifier
From MaRDI portal
Publication:2656589
Abstract: Human learners have the natural ability to use knowledge gained in one setting for learning in a different but related setting. This ability to transfer knowledge from one task to another is essential for effective learning. In this paper, we study transfer learning in the context of nonparametric classification based on observations from different distributions under the posterior drift model, which is a general framework and arises in many practical problems. We first establish the minimax rate of convergence and construct a rate-optimal two-sample weighted -NN classifier. The results characterize precisely the contribution of the observations from the source distribution to the classification task under the target distribution. A data-driven adaptive classifier is then proposed and is shown to simultaneously attain within a logarithmic factor of the optimal rate over a large collection of parameter spaces. Simulation studies and real data applications are carried out where the numerical results further illustrate the theoretical analysis. Extensions to the case of multiple source distributions are also considered.
Recommendations
Cites work
- A survey on concept drift adaptation
- A theory of learning with corrupted labels
- Asymptotically Minimax Adaptive Estimation. I: Upper Bounds. Optimally Adaptive Estimates
- Asymptotically Minimax Adaptive Estimation. II. Schemes without Optimal Adaptation: Adaptive Estimators
- Classification in general finite dimensional spaces with the \(k\)-nearest neighbor rule
- Fast learning rates for plug-in classifiers
- Improving predictive inference under covariate shift by weighting the log-likelihood function
- Nearest neighbor pattern classification
- On a Problem of Adaptive Estimation in Gaussian White Noise
- On the rate of convergence of nearest neighbor rules (Corresp.)
- Optimal aggregation of classifiers in statistical learning.
- Optimal pointwise adaptive methods in nonparametric estimation
- Optimal weighted nearest neighbour classifiers
- Spectral methods meet EM: a provably optimal algorithm for crowdsourcing
Cited in
(45)- Transfer Learning under High-dimensional Generalized Linear Models
- Marginal singularity and the benefits of labels in covariate-shift
- Adaptive transfer learning
- TNN: a transfer learning classifier based on weighted nearest neighbors
- Statistical learning from biased training samples
- A no-free-lunch theorem for multitask learning
- Transfer of semiparametric single index model in binary classification
- Robust transfer learning of high-dimensional generalized linear model
- Transfer Learning in Large-Scale Gaussian Graphical Models with False Discovery Rate Control
- Targeting underrepresented populations in precision medicine: a federated transfer learning approach
- Deep neural network classifier for multidimensional functional data
- Distributed adaptive nearest neighbor classifier: algorithm and theory
- Optimally tackling covariate shift in RKHS-based nonparametric regression
- Accommodating Time-Varying Heterogeneity in Risk Estimation under the Cox Model: A Transfer Learning Approach
- Transfer learning for contextual multi-armed bandits
- The art of transfer learning: an adaptive and robust pipeline
- Transfer learning for functional mean estimation: phase transition and adaptive algorithms
- Local convergence rates of the nonparametric least squares estimator with applications to transfer learning
- Estimation and Inference for High-Dimensional Generalized Linear Models with Knowledge Transfer
- Turning the information-sharing dial: efficient inference from different data sources
- Nonparametric classification with missing data
- Weighted likelihood transfer learning for high-dimensional generalized linear models
- Efficient and multiply robust risk estimation under general forms of dataset shift
- Transfer learning via random forests: a one-shot federated approach
- Double debiased transfer learning for adaptive Huber regression
- Pseudo-labeling for kernel ridge regression under covariate shift
- Transfer learning for high-dimensional transelliptical graphical models
- Transfer Q-learning for finite-horizon Markov decision processes
- Transfer learning for high-dimensional data with heavy-tailed noise: a sparse convoluted rank regression method
- On the Comparative Analysis of Average Treatment Effects Estimation via Data Combination
- Learning from similar linear representations: adaptivity, minimaxity, and robustness
- Robust transfer learning for high-dimensional GLM using -divergence with applications to cancer genomics
- An adaptive transfer learning perspective on classification in nonstationary environments
- Editorial: Special issue on ``Learning across distribution shifts
- Robust transfer learning with unreliable source data
- Federated learning of robust individualized decision rules with application to heterogeneous multihospital sepsis population
- Testing sufficiency for transfer learning
- Efficient distributed transfer learning for large-scale Gaussian graphic models
- An Adaptive Transfer Learning Framework for Functional Classification
- A joint estimation approach for monotonic regression functions in general dimensions
- Debiased transfer learning estimation and inference for multinomial regression
- Transfer learning for high-dimensional quantile regression via convolution smoothing
- Efficient risk assessment of time-to-event targets with adaptive information transfer
- Data-Driven Knowledge Transfer in Batch Q * Learning
- Transfer learning for high dimensional data with discrete responses
This page was built for publication: Transfer learning for nonparametric classification: minimax rate and adaptive classifier
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2656589)
