Cover Image

Revisiting Generalization Measures Beyond IID: An Empirical Study under Distributional Shift

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Nakai, Sora, Fadhloun, Youssef, Mathlouthi, Kacem, Yoshida, Kotaro, Talluri, Ganesh, Mitliagkas, Ioannis, Naganuma, Hiroki
Format:	Preprint
Published:	2026
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

An Empirical Study of Pre-trained Model Selection for Out-of-Distribution Generalization and Calibration
by: Naganuma, Hiroki, et al.
Published: (2023)

Orth-Dion: Eliminating Geometric Mismatch in Distributed Low-Rank Spectral Optimization
by: Nakamori, Tatsuhiro, et al.
Published: (2026)

Towards Understanding Variants of Invariant Risk Minimization through the Lens of Calibration
by: Yoshida, Kotaro, et al.
Published: (2024)

Adaptive Batch Sizes Using Non-Euclidean Gradient Noise Scales for Stochastic Sign and Spectral Descent
by: Naganuma, Hiroki, et al.
Published: (2026)

DisTaC: Conditioning Task Vectors via Distillation for Robust Model Merging
by: Yoshida, Kotaro, et al.
Published: (2025)

Empirical Analysis of Model Selection for Heterogeneous Causal Effect Estimation
by: Mahajan, Divyat, et al.
Published: (2022)

A Derandomization Framework for Structure Discovery: Applications in Neural Networks and Beyond
by: Tsikouras, Nikos, et al.
Published: (2025)

On Fairness of Task Arithmetic: The Role of Task Vectors
by: Naganuma, Hiroki, et al.
Published: (2025)

Pseudo-Asynchronous Local SGD: Robust and Efficient Data-Parallel Training
by: Naganuma, Hiroki, et al.
Published: (2025)

Generating Tabular Data Using Heterogeneous Sequential Feature Forest Flow Matching
by: Akazan, Ange-Clément, et al.
Published: (2024)

Robust Invariant Representation Learning by Distribution Extrapolation
by: Yoshida, Kotaro, et al.
Published: (2025)

Augmenting NER Datasets with LLMs: Towards Automated and Refined Annotation
by: Naraki, Yuji, et al.
Published: (2024)

Feature learning as alignment: a structural property of gradient descent in non-linear neural networks
by: Beaglehole, Daniel, et al.
Published: (2024)

Performative Prediction with Neural Networks
by: Mofakhami, Mehrnaz, et al.
Published: (2023)

A Study of Condition Numbers for First-Order Optimization
by: Guille-Escuret, Charles, et al.
Published: (2020)

Generalizing to unseen domains via distribution matching
by: Albuquerque, Isabela, et al.
Published: (2019)

Optimal Empirical Risk Minimization under Temporal Distribution Shifts
by: Jeong, Yujin, et al.
Published: (2025)

CADet: Fully Self-Supervised Out-Of-Distribution Detection With Contrastive Learning
by: Guille-Escuret, Charles, et al.
Published: (2022)

Takeuchi's Information Criteria as Generalization Measures for DNNs Close to NTK Regime
by: Naganuma, Hiroki, et al.
Published: (2026)

Towards efficient representation identification in supervised learning
by: Ahuja, Kartik, et al.
Published: (2022)

Geometric Insights into Focal Loss: Reducing Curvature for Enhanced Model Calibration
by: Kimura, Masanari, et al.
Published: (2024)

Uncertainty-Aware Subset Selection for Robust Visual Explainability under Distribution Shifts
by: Gupta, Madhav, et al.
Published: (2025)

Expecting The Unexpected: Towards Broad Out-Of-Distribution Detection
by: Guille-Escuret, Charles, et al.
Published: (2023)

Graphs Generalization under Distribution Shifts
by: Tian, Qin, et al.
Published: (2024)

Beyond Multi-Token Prediction: Pretraining LLMs with Future Summaries
by: Mahajan, Divyat, et al.
Published: (2025)

How Does Preconditioning Guide Feature Learning in Deep Neural Networks?
by: Yoshida, Kotaro, et al.
Published: (2025)

Auto-ART: Structured Literature Synthesis and Automated Adversarial Robustness Testing
by: Talluri, Abhijit
Published: (2026)

Weak-to-Strong Generalization under Distribution Shifts
by: Jeon, Myeongho, et al.
Published: (2025)

Convergence Bound and Critical Batch Size of Muon Optimizer
by: Sato, Naoki, et al.
Published: (2025)

Conformal Prediction under Levy-Prokhorov Distribution Shifts: Robustness to Local and Global Perturbations
by: Aolaritei, Liviu, et al.
Published: (2025)

Unlearning with Asymmetric Sources: Improved Unlearning-Utility Trade-off with Public Data
by: Inane, Ahmed Mehdi, et al.
Published: (2026)

Performance Control in Early Exiting to Deploy Large Models at the Same Cost of Smaller Ones
by: Mofakhami, Mehrnaz, et al.
Published: (2024)

Generalization Analysis for Supervised Contrastive Representation Learning under Non-IID Settings
by: Hieu, Nong Minh, et al.
Published: (2025)

Understanding Federated Learning from IID to Non-IID dataset: An Experimental Study
by: Seo, Jungwon, et al.
Published: (2025)

Wasserstein-regularized Conformal Prediction under General Distribution Shift
by: Xu, Rui, et al.
Published: (2025)

Beyond IID: data-driven decision-making in heterogeneous environments
by: Besbes, Omar, et al.
Published: (2022)

DP-RTFL: Differentially Private Resilient Temporal Federated Learning for Trustworthy AI in Regulated Industries
by: Talluri, Abhijit
Published: (2025)

FedLECC: Cluster- and Loss-Guided Client Selection for Federated Learning under Non-IID Data
by: Jimenez-Gutierrez, Daniel M., et al.
Published: (2026)

FederatedFactory: Generative One-Shot Learning for Extremely Non-IID Distributed Scenarios
by: Moleri, Andrea, et al.
Published: (2026)

ShiftKD: Benchmarking Knowledge Distillation under Distribution Shift
by: Zhang, Songming, et al.
Published: (2023)