相关论文: Position: Understanding LLMs Requires More Than St…

We study goal-conditioned RL through the lens of generalization, but not in the traditional sense of random augmentations and domain randomization. Rather, we aim to learn goal-directed policies that generalize with respect to the horizon:…

The transformer's remarkable ability to perform in-context learning (ICL) has sparked a wide range of studies designed to understand its strengths and limitations. However, a theoretical understanding of when ICL can and cannot generalize…

This dissertation studies a fundamental open challenge in deep learning theory: why do deep networks generalize well even while being overparameterized, unregularized and fitting the training data to zero error? In the first part of the…

In this paper, we analyse the generalization ability of binary classifiers for the task of deepfake detection. We find that the stumbling block to their generalization is caused by the unexpected learned identity representation on images.…

Deep Learning (DL) can diagnose faults and assess machine health from raw condition monitoring data without manually designed statistical features. However, practical manufacturing applications remain extremely difficult for existing DL…

Via an overparameterized linear model with Gaussian features, we provide conditions for good generalization for multiclass classification of minimum-norm interpolating solutions in an asymptotic setting where both the number of underlying…

To quantitatively and intuitively explore the generalization ability of pre-trained language models (PLMs), we have designed several tasks of arithmetic and logical reasoning. We both analyse how well PLMs generalize when the test data is…

The rapid advancement of Large Language Models (LLMs) has led to the development of benchmarks that consider temporal dynamics, however, there remains a gap in understanding how well these models can generalize across temporal contexts due…

Unsupervised approaches for learning representations invariant to common transformations are used quite often for object recognition. Learning invariances makes models more robust and practical to use in real-world scenarios. Since data…

Normalization techniques have proved to be a crucial ingredient of successful training in a traditional supervised learning regime. However, in the zero-shot learning (ZSL) world, these ideas have received only marginal attention. This work…

Machine unlearning has emerged as an important component in developing safe and trustworthy models. Prior work on fact unlearning in LLMs has mostly focused on removing a specified target fact robustly, but often overlooks its deductive…

We propose a novel framework for the analysis of learning algorithms that allows us to say when such algorithms can and cannot generalize certain patterns from training data to test data. In particular we focus on situations where the rule…

Learning the ability to generalize knowledge between similar contexts is particularly important in medical imaging as data distributions can shift substantially from one hospital to another, or even from one machine to another. To…

Aimed at explaining the surprisingly good generalization behavior of overparameterized deep networks, recent works have developed a variety of generalization bounds for deep learning, all based on the fundamental learning-theoretic…

Large Language Models (LLMs) often generate responses that are factually incorrect yet expressed with high confidence, which can pose serious risks for end users. To address this, it is essential for LLMs not only to produce answers but…

Classical learning theory suggests that the optimal generalization performance of a machine learning model should occur at an intermediate model complexity, with simpler models exhibiting high bias and more complex models exhibiting high…

Meta reinforcement learning (RL) attempts to discover new RL algorithms automatically from environment interaction. In so-called black-box approaches, the policy and the learning algorithm are jointly represented by a single neural network.…

Reinforcement learning (RL) has achieved remarkable success in LLM reasoning, but whether it can also improve direct recall of parametric knowledge remains an open question. We study this question in a controlled zero-shot, one-hop,…

We assess how the code reasoning abilities of large language models (LLMs) generalize to different kinds of programs. We present techniques for obtaining in- and out-of-distribution programs with different characteristics: code sampled from…

The ability to accurately identify authorship is crucial for verifying content authenticity and mitigating misinformation. Large Language Models (LLMs) have demonstrated an exceptional capacity for reasoning and problem-solving. However,…