Related papers: Temporal Generalization: A Reality Check
The basic underlying assumption of machine learning (ML) models is that the training and test data are sampled from the same distribution. However, in daily practice, this assumption is often broken, i.e. the distribution of the test data…
Multiple studies have now demonstrated that machine learning (ML) can give improved skill for predicting or simulating fairly typical weather events, for tasks such as short-term and seasonal weather forecasting, downscaling simulations to…
Machine-learning-based parameterizations (i.e. representation of sub-grid processes) of global climate models or turbulent simulations have recently been proposed as a powerful alternative to physical, but empirical, representations,…
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…
We aim to determine some physical properties of distant galaxies (for example, stellar mass, star formation history, or chemical enrichment history) from their observed spectra, using supervised machine learning methods. We know that…
Statistical machine learning theory often tries to give generalization guarantees of machine learning models. Those models naturally underlie some fluctuation, as they are based on a data sample. If we were unlucky, and gathered a sample…
Machine learning (ML) has emerged as a powerful tool for tackling complex regression and classification tasks, yet its success often hinges on the quality of training data. This study introduces an ML paradigm inspired by domain knowledge…
Clinical machine learning models experience significantly degraded performance in datasets not seen during training, e.g., new hospitals or populations. Recent developments in domain generalization offer a promising solution to this problem…
Large language models (LLMs) are often trained on extensive, temporally indiscriminate text corpora, reflecting the lack of datasets with temporal metadata. This approach is not aligned with the evolving nature of language. Conventional…
Predictive skill of complex models is often not uniform in model-state space; in weather forecasting models, for example, the skill of the model can be greater in populated regions of interest than in "remote" regions of the globe. Given a…
Experimental studies are a cornerstone of Machine Learning (ML) research. A common and often implicit assumption is that the study's results will generalize beyond the study itself, e.g., to new data. That is, repeating the same study under…
An important component for generalization in machine learning is to uncover underlying latent factors of variation as well as the mechanism through which each factor acts in the world. In this paper, we test whether 17 unsupervised, weakly…
Real-world deployment of machine learning models is challenging because data evolves over time. While no model can work when data evolves in an arbitrary fashion, if there is some pattern to these changes, we might be able to design methods…
Pre-trained language models (LMs) perform well in In-Topic setups, where training and testing data come from the same topics. However, they face challenges in Cross-Topic scenarios where testing data is derived from distinct topics -- such…
Multi-task learning (MTL) is a methodology that aims to improve the general performance of estimation and prediction by sharing common information among related tasks. In the MTL, there are several assumptions for the relationships and…
We show that pooling countries across a panel dimension to macroeconomic data can improve by a statistically significant margin the generalization ability of structural, reduced form, and machine learning (ML) methods to produce…
Humans can easily infer the underlying 3D geometry and texture of an object only from a single 2D image. Current computer vision methods can do this, too, but suffer from view generalization problems - the models inferred tend to make poor…
Transformer language models have demonstrated impressive generalization capabilities in natural language domains, yet we lack a fine-grained understanding of how such generalization arises. In this paper, we investigate length…
A large language model's (LLM's) out-of-distribution (OOD) generalisation ability is crucial to its deployment. Previous work assessing LLMs' generalisation performance, however, typically focuses on a single out-of-distribution dataset.…
We investigate the generalization boundaries of current Multimodal Large Language Models (MLLMs) via comprehensive evaluation under out-of-distribution scenarios and domain-specific tasks. We evaluate their zero-shot generalization across…