Related papers: Variance-Covariance Regularization Improves Repres…
Regularization and transfer learning are two popular techniques to enhance generalization on unseen data, which is a fundamental problem of machine learning. Regularization techniques are versatile, as they are task- and…
Statistical characteristics of deep network representations, such as sparsity and correlation, are known to be relevant to the performance and interpretability of deep learning. When a statistical characteristic is desired, often an…
Over-parameterized neural network models often lead to significant performance discrepancies between training and test sets, a phenomenon known as overfitting. To address this, researchers have proposed numerous regularization techniques…
Continual learning of deep neural networks is a key requirement for scaling them up to more complex applicative scenarios and for achieving real lifelong learning of these architectures. Previous approaches to the problem have considered…
We present a new paradigm for fine-tuning large-scale visionlanguage pre-trained models on downstream task, dubbed Prompt Regularization (ProReg). Different from traditional fine-tuning which easily overfits to the downstream task data,…
We study behavior-regularized reinforcement learning (RL), where regularization toward a reference distribution (the dataset in offline RL or the base model in LLM RL finetuning) is essential to prevent value over-optimization caused by…
Parameter pruning is a promising approach for CNN compression and acceleration by eliminating redundant model parameters with tolerable performance degrade. Despite its effectiveness, existing regularization-based parameter pruning methods…
Deep neural networks produce state-of-the-art results when trained on a large number of labeled examples but tend to overfit when small amounts of labeled examples are used for training. Creating a large number of labeled examples requires…
Self-Supervised Learning (SSL) methods harness the concept of semantic invariance by utilizing data augmentation strategies to produce similar representations for different deformations of the same input. Essentially, the model captures the…
Transfer learning is widely used to adapt large pretrained models to new tasks with only a small amount of new data. However, a challenge persists -- the features from the original task often do not fully cover what is needed for unseen…
Collaborative learning has successfully applied knowledge transfer to guide a pool of small student networks towards robust local minima. However, previous approaches typically struggle with drastically aggravated student homogenization…
Continued advances in self-supervised learning have led to significant progress in video representation learning, offering a scalable alternative to supervised approaches by removing the need for manual annotations. Despite strong…
Dealing with high variance is a significant challenge in model-free reinforcement learning (RL). Existing methods are unreliable, exhibiting high variance in performance from run to run using different initializations/seeds. Focusing on…
This paper investigates a general regularization framework for unsupervised domain adaptation in vector-valued regression under the covariate shift assumption, utilizing vector-valued reproducing kernel Hilbert spaces (vRKHS). Covariate…
Predicting student performance under varying data distributions is a challenging task. This study proposes a method to improve prediction accuracy by employing transfer learning techniques on the dataset with varying distributions. Using…
In general, an experimental environment for deep learning assumes that the training and the test dataset are sampled from the same distribution. However, in real-world situations, a difference in the distribution between two datasets,…
Self-supervised learning methods for computer vision have demonstrated the effectiveness of pre-training feature representations, resulting in well-generalizing Deep Neural Networks, even if the annotated data are limited. However,…
We investigate and improve self-supervision as a drop-in replacement for ImageNet pretraining, focusing on automatic colorization as the proxy task. Self-supervised training has been shown to be more promising for utilizing unlabeled data…
In performative learning, the data distribution reacts to the deployed model - for example, because strategic users adapt their features to game it - which creates a more complex dynamic than in classical supervised learning. One should…
Transfer learning methods address the situation where little labeled training data from the "target" problem exists, but much training data from a related "source" domain is available. However, the overwhelming majority of transfer learning…