Related papers: Universal Adaptive Environment Discovery
Empirical risk minimization often performs poorly when the distribution of the target domain differs from those of source domains. To address such potential distribution shifts, we develop an unsupervised domain adaptation approach that…
Recent work on designing an appropriate distribution of environments has shown promise for training effective generally capable agents. Its success is partly because of a form of adaptive curriculum learning that generates environment…
Domain generalization is the problem of machine learning when the training data and the test data come from different data domains. We present a simple theoretical model of learning to generalize across domains in which there is a…
The inaccuracy of neural network models on inputs that do not stem from the training data distribution is both problematic and at times unrecognized. Model uncertainty estimation can address this issue, where uncertainty estimates are often…
Unsupervised domain adaptation (UDA) is a challenging open problem in land cover mapping. Previous studies show encouraging progress in addressing cross-domain distribution shifts on remote sensing benchmarks for land cover mapping. The…
The aim of unsupervised domain adaptation is to leverage the knowledge in a labeled (source) domain to improve a model's learning performance with an unlabeled (target) domain -- the basic strategy being to mitigate the effects of…
Out-of-distribution (OOD) detection empowers the model trained on the closed image set to identify unknown data in the open world. Though many prior techniques have yielded considerable improvements in this research direction, two crucial…
Out-of-distribution (OOD) detection is vital to safety-critical machine learning applications and has thus been extensively studied, with a plethora of methods developed in the literature. However, the field currently lacks a unified,…
Unsupervised domain adaptation is effective in leveraging rich information from a labeled source domain to an unlabeled target domain. Though deep learning and adversarial strategy made a significant breakthrough in the adaptability of…
Autonomous agents trained using deep reinforcement learning (RL) often lack the ability to successfully generalise to new environments, even when these environments share characteristics with the ones they have encountered during training.…
We study the generalization error of randomized learning algorithms -- focusing on stochastic gradient descent (SGD) -- using a novel combination of PAC-Bayes and algorithmic stability. Importantly, our generalization bounds hold for all…
Machine learning is now used in many areas of astrophysics, from detecting exoplanets in Kepler transit signals to removing telescope systematics. Recent work demonstrated the potential of using machine learning algorithms for atmospheric…
Natural science datasets frequently violate assumptions of independence. Samples may be clustered (e.g. by study site, subject, or experimental batch), leading to spurious associations, poor model fitting, and confounded analyses. While…
When deploying machine learning systems to the wild, it is highly desirable for them to effectively leverage prior knowledge to the unfamiliar domain while also firing alarms to anomalous inputs. In order to address these requirements,…
Trajectory data, capturing human actions and environmental states across various modalities, holds significant potential for enhancing AI agent capabilities, particularly in GUI environments. However, how to model the representation of…
In this work we explore Unsupervised Domain Adaptation (UDA) of pretrained language models for downstream tasks. We introduce UDALM, a fine-tuning procedure, using a mixed classification and Masked Language Model loss, that can adapt to the…
Imitation learning has emerged as a promising approach towards building generalist robots. However, scaling imitation learning for large robot foundation models remains challenging due to its reliance on high-quality expert demonstrations.…
With recent advancements in artificial intelligence, its applications can be seen in every aspect of humans' daily life. From voice assistants to mobile healthcare and autonomous driving, we rely on the performance of AI methods for many…
Finding an interpretable non-redundant representation of real-world data is one of the key problems in Machine Learning. Biological neural networks are known to solve this problem quite well in unsupervised manner, yet unsupervised…
Uncertainty quantification is essential in safety-critical settings--from autonomous driving to aviation, finance, and health--where decisions must rely on conservative bounds rather than point estimates. Predictor-level intervals (e.g.,…