distribution shifts - Robuta Search

https://jmlr.org/papers/v25/22-1197.html Monotonic Risk Relationships under Distribution Shifts for Regularized Risk Minimization distribution shifts monotonic risk relationships minimization https://openreview.net/forum?id=r8juz2t749J Surgical Fine-Tuning Improves Adaptation to Distribution Shifts | OpenReview Selectively fine-tuning a subset of layers outperforms full fine-tuning when transferring to tasks with various distribution shifts. fine tuning distribution shifts surgical improves adaptation https://neurips.cc/virtual/2020/protected/poster_d8330f857a17c53d217014ee776bfd50.html NeurIPS 2020 : Measuring Robustness to Natural Distribution Shifts in Image Classification distribution shifts neurips 2020 measuring robustness https://openreview.net/forum?id=hVAK0cgiWrU Toward Certified Robustness Against Real-World Distribution Shifts | OpenReview We design algorithms for certifying the robustness of deep neural networks against real-world distribution shifts in data. real world distribution shifts toward certified robustness https://openreview.net/forum?id=kc4dZYJlJG FedRC: Tackling Diverse Distribution Shifts Challenge in Federated Learning by Robust Clustering |... Federated Learning (FL) is a machine learning paradigm that safeguards privacy by retaining client data on edge devices. However, optimizing FL in practice can... distribution shifts https://openreview.net/forum?id=1SCptTFtmV&referrer=%5Bthe%20profile%20of%20Vaishaal%20Shankar%5D(%2Fprofile%3Fid%3D~Vaishaal_Shankar1) Interpreting CLIP: Insights on the Robustness to ImageNet Distribution Shifts | OpenReview What distinguishes robust models from non-robust ones? While for ImageNet distribution shifts it has been shown that such differences in robustness can be... on the distribution shifts interpreting clip insights https://www.utwente.nl/en/eemcs/dmb/assignments/open/master/Computer%20Vision%20and%20Biometrics/20260203-Detecting%20medical%20distribution%20shifts%20in%20hyperbolic%20spaces/ Detecting medical distribution shifts in hyperbolic spaces | Computer Vision and Biometrics | EEMCS... medical distribution hyperbolic spaces https://openreview.net/forum?id=thoPskdIcE Federated Learning with Profile Mapping under Distribution Shifts and Drifts | OpenReview Federated Learning (FL) enables decentralized model training across clients without sharing raw data, but its performance degrades under real-world data... federated learning distribution shifts profile mapping https://openreview.net/forum?id=-440wKL2oJV Detecting and Adapting to Irregular Distribution Shifts in Bayesian Online Learning | OpenReview A Bayesian online learning framework for supervised and unsupervised learning, simultaneously detecting irregular changes in data distributions over time and... distribution shifts https://openreview.net/forum?id=FQOC5u-1egI Handling Distribution Shifts on Graphs: An Invariance Perspective | OpenReview There is increasing evidence suggesting neural networks' sensitivity to distribution shifts, so that research on out-of-distribution (OOD) generalization comes... distribution shifts handling graphs invariance perspective https://openreview.net/forum?id=vqRzLv6POg If your data distribution shifts, use self-learning | OpenReview We demonstrate that self-learning techniques like entropy minimization and pseudo-labeling are simple and effective at improving performance of a deployed... your data distribution shifts self learning use openreview https://openreview.net/forum?id=HHgd65xDov Mixed-Feature Logistic Regression Robust to Distribution Shifts | OpenReview Logistic regression models are widely used in the social and behavioral sciences and in high-stakes domains, due to their simplicity and interpretability... logistic regression distribution shifts mixed feature robust https://openreview.net/forum?id=y_s0M6OtyH_ Identifying the Instances Associated with Distribution Shifts using the Max-Sliced Bures Divergence... A method to find the two slices of the feature space where differences between the distributions is most evident. associated with distribution shifts https://openreview.net/forum?id=GrZmKDYCp6H An Information-theoretic Approach to Distribution Shifts | OpenReview We analyze the problem of distribution shift from an information-theoretical perspective and describe different strategies in literature to correct for... an information distribution shifts theoretic approach openreview https://www.amazon.science/publications/wakeword-detection-under-distribution-shifts Wakeword detection under distribution shifts - Amazon Science We propose a novel approach for semi-supervised learning (SSL) designed to overcome distribution shifts between training and real-world data arising in the... distribution shifts detection amazon science https://openreview.net/forum?id=lu4oAq55iK Mitigating Real-World Distribution Shifts in the Fourier Domain | OpenReview While machine learning systems can be highly accurate in their training environments, their performance in real-world deployments can suffer significantly due... real world distribution shifts in the fourier domain mitigating https://openreview.net/forum?id=ksph9pkEDc Selective Mixup Helps with Distribution Shifts, But Not (Only) because of Mixup | OpenReview Mixup is a highly successful technique to improve generalization by augmenting training data with combinations of random pairs. Selective mixup is a family of... but not only helps with distribution shifts https://openreview.net/forum?id=XNFo3dQiCJ Generalizability of Adversarial Robustness Under Distribution Shifts | OpenReview Recent progress in empirical and certified robustness promises to deliver reliable and deployable Deep Neural Networks (DNNs). Despite that success, most... adversarial robustness distribution shifts generalizability openreview https://www.ornl.gov/publication/assessing-membership-inference-attacks-under-distribution-shifts Assessing Membership Inference Attacks under Distribution Shifts | ORNL Membership inference attacks (MIAs) exploit machine learning models to infer whether a data point was in the training set, posing significant privacy risks... distribution shifts assessing membership inference attacks https://deepai.org/publication/how-robust-is-your-fairness-evaluating-and-sustaining-fairness-under-unseen-distribution-shifts How Robust is Your Fairness? Evaluating and Sustaining Fairness under Unseen Distribution Shifts |... Jul 4, 2022 - 07/04/22 - Increasing concerns have been raised on deep learning fairness in recent years. Existing fairness-aware machine learning methods m... https://deepai.org/publication/can-autonomous-vehicles-identify-recover-from-and-adapt-to-distribution-shifts Can Autonomous Vehicles Identify, Recover From, and Adapt to Distribution Shifts? | DeepAI Jun 26, 2020 - 06/26/20 - Out-of-training-distribution (OOD) scenarios are a common challenge of learning agents at deployment, typically leading to arbitra... autonomous vehicles https://openreview.net/forum?id=VbmqcoHpGT Drift-Resilient TabPFN: In-Context Learning Temporal Distribution Shifts on Tabular Data |... While most ML models expect independent and identically distributed data, this assumption is often violated in real-world scenarios due to distribution shifts,... in context learning