Related papers: Paradise of Forking Paths: Revisiting the Adaptive…
Adaptive data analysis (ADA) involves a dynamic interaction between an analyst and a dataset owner, where the analyst submits queries sequentially, adapting them based on previous answers. This process can become adversarial, as the analyst…
Modern data workflows are inherently adaptive, repeatedly querying the same dataset to refine and validate sequential decisions, but such adaptivity can lead to overfitting and invalid statistical inference. Adaptive Data Analysis (ADA)…
The composition of pretraining data is a key determinant of foundation models' performance, but there is no standard guideline for allocating a limited computational budget across different data sources. Most current approaches either rely…
A fundamental challenge in science and engineering is the simulation-to-experiment gap. While we often possess prior knowledge of physical laws, these physical laws can be too difficult to solve exactly for complex systems. Such systems are…
Transfer learning across domains with distribution shift remains a fundamental challenge in building robust and adaptable machine learning systems. While adversarial perturbations are traditionally viewed as threats that expose model…
Aspect sentiment quad prediction (ASQP) aims to predict the quad sentiment elements for a given sentence, which is a critical task in the field of aspect-based sentiment analysis. However, the data imbalance issue has not received…
We propose a novel algorithm for data augmentation in nonlinear over-parametrized regression. Our data augmentation algorithm borrows from the literature on causality and extends the recently proposed Anchor regression (AR) method for data…
This work proposes a robust Partial Domain Adaptation (PDA) framework that mitigates the negative transfer problem by incorporating a robust target-supervision strategy. It leverages ensemble learning and includes diverse, complementary…
Local differential privacy (LDP) is a strong privacy standard that has been adopted by popular software systems. The main idea is that each individual perturbs their own data locally, and only submits the resulting noisy version to a data…
Deep neural networks demonstrate strong performance under aligned training-test distributions. However, real-world test data often exhibit domain shifts. Test-Time Adaptation (TTA) addresses this challenge by adapting the model to test data…
Global data association is an essential prerequisite for robot operation in environments seen at different times or by different robots. Repetitive or symmetric data creates significant challenges for existing methods, which typically rely…
Test-time adaptation (TTA) enhances the zero-shot robustness under distribution shifts by leveraging unlabeled test data during inference. Despite notable advances, several challenges still limit its broader applicability. First, most…
Active Domain Adaptation (ADA) adapts models to target domains by selectively labeling a few target samples. Existing ADA methods prioritize uncertain samples but overlook confident ones, which often match ground-truth. We find that…
We consider the problem of active domain adaptation (ADA) to unlabeled target data, of which subset is actively selected and labeled given a budget constraint. Inspired by recent analysis on a critical issue from label distribution mismatch…
Traditional statistical analysis requires that the analysis process and data are independent. By contrast, the new field of adaptive data analysis hopes to understand and provide algorithms and accuracy guarantees for research as it is…
In this paper, we study the problem of legal domain adaptation problem from an imbalanced source domain to a partial target domain. The task aims to improve legal judgment predictions for non-professional fact descriptions. We formulate…
Making sense of a dataset in an automatic and unsupervised fashion is a challenging problem in statistics and AI. Classical approaches for {exploratory data analysis} are usually not flexible enough to deal with the uncertainty inherent to…
Partial Adaptation (PDA) addresses a practical scenario in which the target domain contains only a subset of classes in the source domain. While PDA should take into account both class-level and sample-level to mitigate negative transfer,…
The adoption of the distributed paradigm has allowed applications to increase their scalability, robustness and fault tolerance, but it has also complicated their structure, leading to an exponential growth of the applications'…
Reuse of data in adaptive workflows poses challenges regarding overfitting and the statistical validity of results. Previous work has demonstrated that interacting with data via differentially private algorithms can mitigate overfitting,…