Related papers: An Improved Transfer Model: Randomized Transferabl…
This paper studies "unsupervised finetuning", the symmetrical problem of the well-known "supervised finetuning". Given a pretrained model and small-scale unlabeled target data, unsupervised finetuning is to adapt the representation…
Fine-tuning of self-supervised models is a powerful transfer learning method in a variety of fields, including speech processing, since it can utilize generic feature representations obtained from large amounts of unlabeled data.…
There are many time series in the literature with high dimension yet limited sample sizes, such as macroeconomic variables, and it is almost impossible to obtain efficient estimation and accurate prediction by using the corresponding…
The existence of spurious correlations such as image backgrounds in the training environment can make empirical risk minimization (ERM) perform badly in the test environment. To address this problem, Kirichenko et al. (2022) empirically…
Diffusion-based generative models have achieved remarkable success in various domains. It trains a shared model on denoising tasks that encompass different noise levels simultaneously, representing a form of multi-task learning (MTL).…
The success of machine learning algorithms often relies on a large amount of high-quality data to train well-performed models. However, data is a valuable resource and are always held by different parties in reality. An effective solution…
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…
We present three related ways of using Transfer Learning to improve feature selection. The three methods address different problems, and hence share different kinds of information between tasks or feature classes, but all three are based on…
Object recognition is a key enabler across industry and defense. As technology changes, algorithms must keep pace with new requirements and data. New modalities and higher resolution sensors should allow for increased algorithm robustness.…
Distance metric learning (DML) is a critical factor for image analysis and pattern recognition. To learn a robust distance metric for a target task, we need abundant side information (i.e., the similarity/dissimilarity pairwise constraints…
Computer simulation provides an automatic and safe way for training robotic control policies to achieve complex tasks such as locomotion. However, a policy trained in simulation usually does not transfer directly to the real hardware due to…
While the untargeted black-box transferability of adversarial perturbations has been extensively studied before, changing an unseen model's decisions to a specific `targeted' class remains a challenging feat. In this paper, we propose a new…
Vision Foundation Models (VFMs) pretrained on massive datasets exhibit impressive performance on various downstream tasks, especially with limited labeled target data. However, due to their high inference compute cost, these models cannot…
Transfer learning has become an essential paradigm in artificial intelligence, enabling the transfer of knowledge from a source task to improve performance on a target task. This approach, particularly through techniques such as pretraining…
The goal of machine learning is to develop predictors that generalize well to test data. Ideally, this is achieved by training on an almost infinitely large training data set that captures all variations in the data distribution. In…
Transfer reinforcement learning aims to derive a near-optimal policy for a target environment with limited data by leveraging abundant data from related source domains. However, it faces two key challenges: the lack of performance…
Representation-based multi-task learning (MTL) improves efficiency by learning a shared structure across tasks, but its practical application is often hindered by contamination, outliers, or adversarial tasks. Most existing methods and…
Unsupervised learning has been widely used in many real-world applications. One of the simplest and most important unsupervised learning models is the Gaussian mixture model (GMM). In this work, we study the multi-task learning problem on…
Transfer learning refers to the promising idea of initializing model fits based on pre-training on other data. We particularly consider regression modeling settings where parameter estimates from previous data can be used as anchoring…
Transfer Learning (TL) has shown great potential to accelerate Reinforcement Learning (RL) by leveraging prior knowledge from past learned policies of relevant tasks. Existing transfer approaches either explicitly computes the similarity…