Universal Adaptive Environment Discovery

• URL: http://arxiv.org/abs/2510.12547v1
• Date: Tue, 14 Oct 2025 14:10:16 GMT
• Title: Universal Adaptive Environment Discovery
• Authors: Madi Matymov, Ba-Hien Tran, Maurizio Filippone,
• Abstract summary: We propose a unified framework that learns a distribution over data transformations that instantiate environments.<n>UAED yields adaptive variants of IRM, REx, GroupDRO, and CORAL without predefined groups or manual environment design.<n>Our results indicate that making environments adaptive is a practical route to out-of-distribution generalization.
• Score: 9.289361622607453
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: An open problem in Machine Learning is how to avoid models to exploit spurious correlations in the data; a famous example is the background-label shortcut in the Waterbirds dataset. A common remedy is to train a model across multiple environments; in the Waterbirds dataset, this corresponds to training by randomizing the background. However, selecting the right environments is a challenging problem, given that these are rarely known a priori. We propose Universal Adaptive Environment Discovery (UAED), a unified framework that learns a distribution over data transformations that instantiate environments, and optimizes any robust objective averaged over this learned distribution. UAED yields adaptive variants of IRM, REx, GroupDRO, and CORAL without predefined groups or manual environment design. We provide a theoretical analysis by providing PAC-Bayes bounds and by showing robustness to test environment distributions under standard conditions. Empirically, UAED discovers interpretable environment distributions and improves worst-case accuracy on standard benchmarks, while remaining competitive on mean accuracy. Our results indicate that making environments adaptive is a practical route to out-of-distribution generalization.

Related papers

• Multi-environment Invariance Learning with Missing Data [0.0]
  In this work, we establish non-asymptotic guarantees on variable selection property and $ell$ error convergence rates.<n>We evaluate the performance of the new estimator through extensive simulations and demonstrate its application using the UCI Bike Sharing dataset.
  arXiv  Detail & Related papers  (2026-01-12T06:30:58Z)
• Local Performance vs. Out-of-Distribution Generalization: An Empirical Analysis of Personalized Federated Learning in Heterogeneous Data Environments [3.186130813218338]
  This study involves a thorough evaluation of Federated Learning approaches, encompassing both their local performance and their generalization capabilities.<n>We propose and incorporate a modified approach of FedAvg, designated as Federated Learning with Individualized Updates (FLIU), extending the algorithm by a straightforward individualization step with an adaptive personalization factor.
  arXiv  Detail & Related papers  (2025-10-28T15:15:14Z)
• Group Distributionally Robust Machine Learning under Group Level Distributional Uncertainty [14.693433974739213]
  We propose a novel framework that relies on Wasserstein-based distributionally robust optimization (DRO) to account for the distributional uncertainty within each group.<n>We develop a gradient descent-ascent algorithm to solve the proposed DRO problem and provide convergence results.
  arXiv  Detail & Related papers  (2025-09-10T19:08:17Z)
• Theoretically Guaranteed Distribution Adaptable Learning [23.121014921407898]
  We propose a novel framework called Distribution Adaptable Learning (DAL) DAL enables the model to effectively track the evolving data distributions. It can enhance the reusable and evolvable properties of DAL in accommodating evolving distributions.
  arXiv  Detail & Related papers  (2024-11-05T09:10:39Z)
• Trained Models Tell Us How to Make Them Robust to Spurious Correlation without Group Annotation [3.894771553698554]
  Empirical Risk Minimization (ERM) models tend to rely on attributes that have high spurious correlation with the target. This can degrade the performance on underrepresented (or'minority') groups that lack these attributes. We propose Environment-based Validation and Loss-based Sampling (EVaLS) to enhance robustness to spurious correlation.
  arXiv  Detail & Related papers  (2024-10-07T08:17:44Z)
• Decorr: Environment Partitioning for Invariant Learning and OOD Generalization [10.799855921851332]
  Invariant learning methods are aimed at identifying a consistent predictor across multiple environments. When environments aren't inherent in the data, practitioners must define them manually. This environment partitioning affects invariant learning's efficacy but remains underdiscussed. In this paper, we suggest partitioning the dataset into several environments by isolating low-correlation data subsets.
  arXiv  Detail & Related papers  (2022-11-18T06:49:35Z)
• Divide and Contrast: Source-free Domain Adaptation via Adaptive Contrastive Learning [122.62311703151215]
  Divide and Contrast (DaC) aims to connect the good ends of both worlds while bypassing their limitations. DaC divides the target data into source-like and target-specific samples, where either group of samples is treated with tailored goals. We further align the source-like domain with the target-specific samples using a memory bank-based Maximum Mean Discrepancy (MMD) loss to reduce the distribution mismatch.
  arXiv  Detail & Related papers  (2022-11-12T09:21:49Z)
• Differentiable Invariant Causal Discovery [106.87950048845308]
  Learning causal structure from observational data is a fundamental challenge in machine learning. This paper proposes Differentiable Invariant Causal Discovery (DICD) to avoid learning spurious edges and wrong causal directions. Extensive experiments on synthetic and real-world datasets verify that DICD outperforms state-of-the-art causal discovery methods up to 36% in SHD.
  arXiv  Detail & Related papers  (2022-05-31T09:29:07Z)
• Accuracy on the Line: On the Strong Correlation Between Out-of-Distribution and In-Distribution Generalization [89.73665256847858]
  We show that out-of-distribution performance is strongly correlated with in-distribution performance for a wide range of models and distribution shifts. Specifically, we demonstrate strong correlations between in-distribution and out-of-distribution performance on variants of CIFAR-10 & ImageNet. We also investigate cases where the correlation is weaker, for instance some synthetic distribution shifts from CIFAR-10-C and the tissue classification dataset Camelyon17-WILDS.
  arXiv  Detail & Related papers  (2021-07-09T19:48:23Z)
• Examining and Combating Spurious Features under Distribution Shift [94.31956965507085]
  We define and analyze robust and spurious representations using the information-theoretic concept of minimal sufficient statistics. We prove that even when there is only bias of the input distribution, models can still pick up spurious features from their training data. Inspired by our analysis, we demonstrate that group DRO can fail when groups do not directly account for various spurious correlations.
  arXiv  Detail & Related papers  (2021-06-14T05:39:09Z)
• Predict then Interpolate: A Simple Algorithm to Learn Stable Classifiers [59.06169363181417]
  Predict then Interpolate (PI) is an algorithm for learning correlations that are stable across environments. We prove that by interpolating the distributions of the correct predictions and the wrong predictions, we can uncover an oracle distribution where the unstable correlation vanishes.
  arXiv  Detail & Related papers  (2021-05-26T15:37:48Z)
• Environment Inference for Invariant Learning [9.63004099102596]
  We propose EIIL, a framework for domain-invariant learning that incorporates Environment Inference. We show that EIIL outperforms invariant learning methods on the CMNIST benchmark without using environment labels. We also establish connections between EIIL and algorithmic fairness, which enables EIIL to improve accuracy and calibration in a fair prediction problem.
  arXiv  Detail & Related papers  (2020-10-14T17:11:46Z)
• Unshuffling Data for Improved Generalization [65.57124325257409]
  Generalization beyond the training distribution is a core challenge in machine learning. We show that partitioning the data into well-chosen, non-i.i.d. subsets treated as multiple training environments can guide the learning of models with better out-of-distribution generalization.
  arXiv  Detail & Related papers  (2020-02-27T03:07:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.