A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
ART improves transfer learning performance with robust theory and methods.
AdaTrans adapts to feature and sample transfer in high-dimensional regression.
UDA learns target domain from unlabeled data via source knowledge transfer.
The paper examines Adaptive Lasso and Transfer Lasso, highlighting their differences and proposing a new method.
Interventional domain adaptation improves feature transferability by removing spurious correlations.
SATL adapts to varying smoothness in hypothesis transfer learning.
New method tackles concept shifts in nonparametric regression using robust and adaptive transfer learning.
Adaptive source selection for positive transfer in linear models improves target dataset performance.
New estimator achieves minimax optimal risk in transfer learning.
Proposes a method to improve multi-output Gaussian process for transfer learning.
Adaptive transfer learning model for varying mechanisms across domains.
Transfer learning framework for fragility modeling under domain shift and class imbalance
The paper proposes a uniformity regularization scheme to improve deep neural network transferability.
Domain adaptation is the supervised learning setting in which the training and test data are sampled from different distributions: training data is sampled from a source domain, whilst test data is sampled from a target domain. This paper proposes and studies an approach, called feature-level domain adaptation (FLDA), …
Transfer learning aims to learn robust classifiers for the target domain by leveraging knowledge from a source domain. Since the source and the target domains are usually from different distributions, existing methods mainly focus on adapting the cross-domain marginal or conditional distributions. However, in real appl…
New technique explains convergence in ML models with data modifications.
Proposes TFDF to learn transferable and discriminative features for unsupervised domain adaptation.
Transfer learning has achieved promising results by leveraging knowledge from the source domain to annotate the target domain which has few or none labels. Existing methods often seek to minimize the distribution divergence between domains, such as the marginal distribution, the conditional distribution or both. Howeve…
Cross-domain recommendation has long been one of the major topics in recommender systems. Recently, various deep models have been proposed to transfer the learned knowledge across domains, but most of them focus on extracting abstract transferable features from auxilliary contents, e.g., images and review texts, and th…
This paper proposes a new method to improve domain adaptation by distinguishing between marginal and dependence structure differences.
Transfer Learning (TL) in Deep Neural Networks is gaining importance because in most of the applications, the labeling of data is costly and time-consuming. Additionally, TL also provides an effective weight initialization strategy for Deep Neural Networks . This paper introduces the idea of Adaptive Transfer Learning …
Fine-tuning large pre-trained models is an effective transfer mechanism in NLP. However, in the presence of many downstream tasks, fine-tuning is parameter inefficient: an entire new model is required for every task. As an alternative, we propose transfer with adapter modules. Adapter modules yield a compact and extens…
Paper proposes a unified time series forecasting model with adaptive transfer.
New study reveals surprising adaptive rates in model selection for transfer learning.
Paper proposes SOTL framework for improving transfer learning accuracy and efficiency.
Adapts Neyman-Pearson classification for both source and target distribution shifts.
Recent works reveal that network embedding techniques enable many machine learning models to handle diverse downstream tasks on graph structured data. However, as previous methods usually focus on learning embeddings for a single network, they can not learn representations transferable on multiple networks. Hence, it i…
Studies show that the representations learned by deep neural networks can be transferred to similar prediction tasks in other domains for which we do not have enough labeled data. However, as we transition to higher layers in the model, the representations become more task-specific and less generalizable. Recent resear…
Transfer and adaptation to new unknown environmental dynamics is a key challenge for reinforcement learning (RL). An even greater challenge is performing near-optimally in a single attempt at test time, possibly without access to dense rewards, which is not addressed by current methods that require multiple experience …
(Unsupervised) Domain Adaptation (DA) seeks for classifying target instances when solely provided with source labeled and target unlabeled examples for training. Learning domain-invariant features helps to achieve this goal, whereas it underpins unlabeled samples drawn from a single or multiple explicit target domains …
Deep networks have been successfully applied to learn transferable features for adapting models from a source domain to a different target domain. In this paper, we present joint adaptation networks (JAN), which learn a transfer network by aligning the joint distributions of multiple domain-specific layers across domai…
New findings on representation changes in transfer learning.
Compared with shallow domain adaptation, recent progress in deep domain adaptation has shown that it can achieve higher predictive performance and stronger capacity to tackle structural data (e.g., image and sequential data). The underlying idea of deep domain adaptation is to bridge the gap between source and target d…
Unified framework for clustering with auxiliary data.
The recent advances in deep transfer learning reveal that adversarial learning can be embedded into deep networks to learn more transferable features to reduce the distribution discrepancy between two domains. Existing adversarial domain adaptation methods either learn a single domain discriminator to align the global …
Time Series Classification (TSC) has been an important and challenging task in data mining, especially on multivariate time series and multi-view time series data sets. Meanwhile, transfer learning has been widely applied in computer vision and natural language processing applications to improve deep neural network's g…
The study analyzes transfer learning using information theory.
Transfer learning for causal forest
End-to-end analysis of SGD for STL with adaptive sub-sampling.
Proposes a graph embedding framework for domain adaptation.
Flexible framework for transfer learning with optimal rates.
We study few-shot supervised domain adaptation (DA) for regression problems, where only a few labeled target domain data and many labeled source domain data are available. Many of the current DA methods base their transfer assumptions on either parametrized distribution shift or apparent distribution similarities, e.g.…
Unified approach for sample aggregation in transfer learning across various divergence measures.
This paper introduces localized discrepancy theories for unsupervised domain adaptation.
In recent years, an increasing popularity of deep learning model for intelligent condition monitoring and diagnosis as well as prognostics used for mechanical systems and structures has been observed. In the previous studies, however, a major assumption accepted by default, is that the training and testing data are tak…
FAST improves fast and stable task adaptation in DNNs.
This paper tackles continuous domain adaptation with a new approach.
In this paper, we propose a novel learning framework for the problem of domain transfer learning. We map the data of two domains to one single common space, and learn a classifier in this common space. Then we adapt the common classifier to the two domains by adding two adaptive functions to it respectively. In the com…