arXiv research

Localized transfer learning improves nonparametric regression performance.

Connections between nodes of fully connected neural networks are usually represented by weight matrices. In this article, functional transfer matrices are introduced as alternatives to the weight matrices: Instead of using real weights, a functional transfer matrix uses real functions with trainable parameters to repre…

Study improves hypothesis transfer learning for functional linear models.

Q-learning is one of the most popular methods in Reinforcement Learning (RL). Transfer Learning aims to utilize the learned knowledge from source tasks to help new tasks to improve the sample complexity of the new tasks. Considering that data collection in RL is both more time and cost consuming and Q-learning converge…

Transfer learning borrows knowledge from a source domain to facilitate learning in a target domain. Two primary issues to be addressed in transfer learning are what and how to transfer. For a pair of domains, adopting different transfer learning algorithms results in different knowledge transferred between them. To dis…

MPHD transfers knowledge across different domains for Bayesian optimization.

Time-variant value function transfer method for RL.

This research evaluates learning models for bionic robots, focusing on transfer function identification.

We develop differential algebraic K-theory for rings of integers in number fields and we construct a cycle map from geometrized bundles of modules over such a ring to the differential algebraic K-theory. We also treat some of the foundational aspects of differential cohomology, including differential function spectra a…

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

This paper tackles negative transfer in multi-task learning by introducing class-wise weights.

New algorithm improves knowledge transfer in dynamic decision-making.

The paper explores transferring functions from one data space to another.

Unified view on GP transfer learning for Bayesian optimization.

Paper presents a robust transfer learning method for active level set estimation.

Kähler information manifolds for signal filters in weighted Hardy spaces are explored.

Paper introduces a new method for improving reinforcement learning performance using transfer learning.

Develops hyperparameter transfer methods for Dense Associative Memories.

Improves functional linear regression with shape transfer learning.

Researchers in functional neuroimaging mostly use activation coordinates to formulate their hypotheses. Instead, we propose to use the full statistical images to define regions of interest (ROIs). This paper presents two machine learning approaches, transfer learning and selection transfer, that are compared upon their…

The objective of transfer reinforcement learning is to generalize from a set of previous tasks to unseen new tasks. In this work, we focus on the transfer scenario where the dynamics among tasks are the same, but their goals differ. Although general value function (Sutton et al., 2011) has been shown to be useful for k…

SF-DQN improves RL transfer by learning successor features.

A new method learns priors for Bayesian optimisation to improve performance.

Proposes a transfer learning framework for sparse SIMs without raw source data.

Training a source model optimally for its own task is suboptimal for downstream transfer.

Paper tackles robust transfer learning with unreliable source data.

A number of approaches to solving the well-known transfer pricing problem are known. However, few models satisfactorily resolve the core problem of allowing both the source and receiving divisions to earn a profit on transfers during a period in such a way that sub-optimal output levels are avoided. In 1969, Samuel pro…

Study shows benefits of transfer learning with neural networks.

New methods avoid spectral pollution in transfer operators for accurate analysis.

Paper proposes operator deep Q-learning for quick reward adaptation.

DeltaBO accelerates Bayesian optimization with theoretical guarantees.

SATL adapts to varying smoothness in hypothesis transfer learning.

We consider the problem of knowledge transfer when an agent is facing a series of Reinforcement Learning (RL) tasks. We introduce a novel metric between Markov Decision Processes (MDPs) and establish that close MDPs have close optimal value functions. Formally, the optimal value functions are Lipschitz continuous with …

Transferring knowledge across tasks to improve data-efficiency is one of the open key challenges in the field of global black-box optimization. Readily available algorithms are typically designed to be universal optimizers and, therefore, often suboptimal for specific tasks. We propose a novel transfer learning method …

Paper tackles transfer RL under unobserved context, developing methods to reduce bias.

Method uses random forest with distance covariance for transfer learning in healthcare.

Study on neural networks' performance in sequential task learning.

New analysis shows transfer learning can significantly reduce sample size for complex models.

Transfer learning across different reinforcement learning (RL) tasks is becoming an increasingly valuable area of research. We consider a goal-based multi-task RL framework and mechanisms by which previously solved tasks can reduce sample complexity and regret when the agent is faced with a new task. Specifically, we i…

Study improves Bayesian optimisation with ensemble transfer learning.

A key question in Reinforcement Learning is which representation an agent can learn to efficiently reuse knowledge between different tasks. Recently the Successor Representation was shown to have empirical benefits for transferring knowledge between tasks with shared transition dynamics. This paper presents Model Featu…

Previous transfer learning methods based on deep network assume the knowledge should be transferred between the same hidden layers of the source domain and the target domains. This assumption doesn't always hold true, especially when the data from the two domains are heterogeneous with different resolutions. In such ca…

Brain imaging data are important in brain sciences yet expensive to obtain, with big volume (i.e., large p) but small sample size (i.e., small n). To tackle this problem, transfer learning is a promising direction that leverages source data to improve performance on related, target data. Most transfer learning methods …

Transfer learning has recently attracted significant research attention, as it simultaneously learns from different source domains, which have plenty of labeled data, and transfers the relevant knowledge to the target domain with limited labeled data to improve the prediction performance. We propose a Bayesian transfer…

New statistical guarantees for transfer learning with diverse tasks.

Study shows how pretraining robustness transfers to downstream tasks.

Adversarially-trained models transfer better in limited data scenarios.

The transfer learning toolkit wraps the codes of 17 transfer learning models and provides integrated interfaces, allowing users to use those models by calling a simple function. It is easy for primary researchers to use this toolkit and to choose proper models for real-world applications. The toolkit is written in Pyth…