相关论文: How to Mitigate Overfitting in Weak-to-strong Gene…

Robust model fitting is a core algorithm in a large number of computer vision applications. Solving this problem efficiently for datasets highly contaminated with outliers is, however, still challenging due to the underlying computational…

AI model alignment is crucial due to inadvertent biases in training data and the underspecified machine learning pipeline, where models with excellent test metrics may not meet end-user requirements. While post-training alignment via human…

Deep neural networks are learning models with a very high capacity and therefore prone to over-fitting. Many regularization techniques such as Dropout, DropConnect, and weight decay all attempt to solve the problem of over-fitting by…

AI-driven decision-making systems are becoming instrumental in the public sector, with applications spanning areas like criminal justice, social welfare, financial fraud detection, and public health. While these systems offer great…

Data sparsity is an inherent challenge in the recommender systems, where most of the data is collected from the implicit feedbacks of users. This causes two difficulties in designing effective algorithms: first, the majority of users only…

Adversarial examples cause neural networks to produce incorrect outputs with high confidence. Although adversarial training is one of the most effective forms of defense against adversarial examples, unfortunately, a large gap exists…

Recent advancements in large language models (LLMs) have led to their increased application across various tasks, with reinforcement learning from human feedback (RLHF) being a crucial part of their training to align responses with user…

In scientific reasoning tasks, the veracity of the reasoning process is as critical as the final outcome. While Process Reward Models (PRMs) offer a solution to the coarse-grained supervision problems inherent in Outcome Reward Models…

Scalable oversight protocols aim to empower evaluators to accurately verify AI models more capable than themselves. However, human evaluators are subject to biases that can lead to systematic errors. We conduct two studies examining the…

Overfit is a fundamental problem in machine learning in general, and in deep learning in particular. In order to reduce overfit and improve generalization in the classification of images, some employ invariance to a group of…

An overarching goal in machine learning is to build a generalizable model with few samples. To this end, overparameterization has been the subject of immense interest to explain the generalization ability of deep nets even when the size of…

Many binary classification problems minimize misclassification above (or below) a threshold. We show that instances of ranking problems, accuracy at the top or hypothesis testing may be written in this form. We propose a general framework…

Recent advancements in semi-supervised deep learning have introduced effective strategies for leveraging both labeled and unlabeled data to improve classification performance. This work proposes a semi-supervised framework that utilizes a…

Machine learning models often perform poorly on subgroups that are underrepresented in the training data. Yet, little is understood on the variation in mechanisms that cause subpopulation shifts, and how algorithms generalize across such…

Generalization is the ability of a model to predict on unseen domains and is a fundamental task in machine learning. Several generalization bounds, both theoretical and empirical have been proposed but they do not provide tight bounds .In…

The growing capabilities of large language models (LLMs) present a key challenge of maintaining effective human oversight. Weak-to-strong generalization (W2SG) offers a promising framework for supervising increasingly capable LLMs using…

The usage of machine learning models has grown substantially and is spreading into several application domains. A common need in using machine learning models is collecting the data required to train these models. In some cases, labeling a…

It is increasingly common in machine learning to use learned models to label data and then employ such data to train more capable models. The phenomenon of weak-to-strong generalization exemplifies the advantage of this two-stage procedure:…

Meta-learning algorithms aim to learn two components: a model that predicts targets for a task, and a base learner that quickly updates that model when given examples from a new task. This additional level of learning can be powerful, but…

Adversarial training has been empirically shown to be more prone to overfitting than standard training. The exact underlying reasons still need to be fully understood. In this paper, we identify one cause of overfitting related to current…