# Robust Generalization against Photon-Limited Corruptions via Worst-Case Sharpness Minimization

arXiv: https://arxiv.org/abs/2303.13087 · HTML: https://mlsanity.com/paper/2303.13087/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- Builds on 56 of its 72 references that are in the map.
- First posted on arXiv 23 Mar 2023.

## Builds on (most cited first, 30 of 56)

- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016)
- [Invariant Risk Minimization](https://mlsanity.com/paper/1907.02893/) (2019)
- [Sharpness-Aware Minimization for Efficiently Improving Generalization](https://mlsanity.com/paper/2010.01412/) (2020)
- [On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima](https://mlsanity.com/paper/1609.04836/) (2016)
- [Moment Matching for Multi-Source Domain Adaptation](https://mlsanity.com/paper/1812.01754/) (2018)
- [Learning Transferable Features with Deep Adaptation Networks](https://mlsanity.com/paper/1502.02791/) (2015)
- [Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks](https://mlsanity.com/paper/1706.02690/) (2017)
- [Adversarial Discriminative Domain Adaptation](https://mlsanity.com/paper/1702.05464/) (2017)
- [Energy-based Out-of-distribution Detection](https://mlsanity.com/paper/2010.03759/) (2020)
- [Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization](https://mlsanity.com/paper/1911.08731/) (2019)
- [Deep Anomaly Detection with Outlier Exposure](https://mlsanity.com/paper/1812.04606/) (2018)
- [Out-of-Distribution Generalization via Risk Extrapolation (REx)](https://mlsanity.com/paper/2003.00688/) (2020)
- [Domain Generalization via Invariant Feature Representation](https://mlsanity.com/paper/1301.2115/) (2013)
- [Just Train Twice: Improving Group Robustness without Training Group Information](https://mlsanity.com/paper/2107.09044/) (2021)
- [Domain Generalization by Solving Jigsaw Puzzles](https://mlsanity.com/paper/1903.06864/) (2019)
- [SWAD: Domain Generalization by Seeking Flat Minima](https://mlsanity.com/paper/2102.08604/) (2021)
- [Fairness Without Demographics in Repeated Loss Minimization](https://mlsanity.com/paper/1806.08010/) (2018)
- [Entropy-SGD: Biasing Gradient Descent Into Wide Valleys](https://mlsanity.com/paper/1611.01838/) (2016)
- [Learning Models with Uniform Performance via Distributionally Robust Optimization](https://mlsanity.com/paper/1810.08750/) (2018)
- [Environment Inference for Invariant Learning](https://mlsanity.com/paper/2010.07249/) (2020)
- [Learning to Learn Single Domain Generalization](https://mlsanity.com/paper/2003.13216/) (2020)
- [Mitigating Neural Network Overconfidence with Logit Normalization](https://mlsanity.com/paper/2205.09310/) (2022)
- [Domain Generalization using Causal Matching](https://mlsanity.com/paper/2006.07500/) (2020)
- [Towards Causal Representation Learning](https://mlsanity.com/paper/2102.11107/) (2021)
- [Are Anchor Points Really Indispensable in Label-Noise Learning?](https://mlsanity.com/paper/1906.00189/) (2019)
- [Solving a Class of Non-Convex Min-Max Games Using Iterative First Order Methods](https://mlsanity.com/paper/1902.08297/) (2019)

## Built on by (most cited first, 29 of 29)

- [Exploring Criteria of Loss Reweighting to Enhance LLM Unlearning](https://mlsanity.com/paper/2505.11953/) (2025)
- [Learning to Augment Distributions for Out-of-Distribution Detection](https://mlsanity.com/paper/2311.01796/) (2023)
- [Out-of-distribution Detection Learning with Unreliable Out-of-distribution Sources](https://mlsanity.com/paper/2311.03236/) (2023)
- [IDEAL: Influence-Driven Selective Annotations Empower In-Context Learners in Large Language Models](https://mlsanity.com/paper/2310.10873/) (2023)
- [FlatMatch: Bridging Labeled Data and Unlabeled Data with Cross-Sharpness for Semi-Supervised Learning](https://mlsanity.com/paper/2310.16412/) (2023)
- [HYPO: Hyperspherical Out-of-Distribution Generalization](https://mlsanity.com/paper/2402.07785/) (2024)
- [Winning Prize Comes from Losing Tickets: Improve Invariant Learning by Exploring Variant Parameters for Out-of-Distribution Generalization](https://mlsanity.com/paper/2310.16391/) (2023)
- [Eliminating Catastrophic Overfitting Via Abnormal Adversarial Examples Regularization](https://mlsanity.com/paper/2404.08154/) (2024)
- [GRU: Mitigating the Trade-off between Unlearning and Retention for LLMs](https://mlsanity.com/paper/2503.09117/) (2025)
- [Layer-Aware Analysis of Catastrophic Overfitting: Revealing the Pseudo-Robust Shortcut Dependency](https://mlsanity.com/paper/2405.16262/) (2024)
- [Stability and Generalization of the Decentralized Stochastic Gradient Descent Ascent Algorithm](https://mlsanity.com/paper/2310.20369/) (2023)
- [Jailbreaking the Non-Transferable Barrier via Test-Time Data Disguising](https://mlsanity.com/paper/2503.17198/) (2025)
- [AHA: Human-Assisted Out-of-Distribution Generalization and Detection](https://mlsanity.com/paper/2410.08000/) (2024)
- [Toward Robust Non-Transferable Learning: A Survey and Benchmark](https://mlsanity.com/paper/2502.13593/) (2025)
- [Mitigating Label Noise on Graph via Topological Sample Selection](https://mlsanity.com/paper/2403.01942/) (2024)
- [Out-of-Distribution Learning with Human Feedback](https://mlsanity.com/paper/2408.07772/) (2024)
- [Is Gradient Ascent Really Necessary? Memorize to Forget for Machine Unlearning](https://mlsanity.com/paper/2602.06441/) (2026)
- [From Optimization to Generalization: Fair Federated Learning against Quality Shift via Inter-Client Sharpness Matching](https://mlsanity.com/paper/2404.17805/) (2024)
- [When Data-Free Knowledge Distillation Meets Non-Transferable Teacher: Escaping Out-of-Distribution Trap is All You Need](https://mlsanity.com/paper/2507.04119/) (2025)
- [OODRobustBench: a Benchmark and Large-Scale Analysis of Adversarial Robustness under Distribution Shift](https://mlsanity.com/paper/2310.12793/) (2023)
- [Critical Influence of Overparameterization on Sharpness-aware Minimization](https://mlsanity.com/paper/2311.17539/) (2023)
- [Bridging OOD Detection and Generalization: A Graph-Theoretic View](https://mlsanity.com/paper/2409.18205/) (2024)
- [i-PhysGaussian: Implicit Physical Simulation for 3D Gaussian Splatting](https://mlsanity.com/paper/2602.17117/) (2026)
- [FedPCA: Noise-Robust Fair Federated Learning via Performance-Capacity Analysis](https://mlsanity.com/paper/2503.10567/) (2025)
- [Intellectual Property Protection for 3D Gaussian Splatting Assets: A Survey](https://mlsanity.com/paper/2602.03878/) (2026)
- [Distributionally Robust Optimization with Adversarial Data Contamination](https://mlsanity.com/paper/2507.10718/) (2025)
- [Making Robust Generalizers Less Rigid with Loss Concentration](https://mlsanity.com/paper/2408.03619/) (2024)
- [Fair Federated Medical Image Classification Against Quality Shift via Inter-Client Progressive State Matching](https://mlsanity.com/paper/2503.09587/) (2025)
- [BrokenBind: Universal Modality Exploration beyond Dataset Boundaries](https://mlsanity.com/paper/2602.06451/) (2026)

## Abstract (arXiv)

Robust generalization aims to tackle the most challenging data distributions which are rare in the training set and contain severe noises, i.e., photon-limited corruptions. Common solutions such as distributionally robust optimization (DRO) focus on the worst-case empirical risk to ensure low training error on the uncommon noisy distributions. However, due to the over-parameterized model being optimized on scarce worst-case data, DRO fails to produce a smooth loss landscape, thus struggling on generalizing well to the test set. Therefore, instead of focusing on the worst-case risk minimization, we propose SharpDRO by penalizing the sharpness of the worst-case distribution, which measures the loss changes around the neighbor of learning parameters. Through worst-case sharpness minimization, the proposed method successfully produces a flat loss curve on the corrupted distributions, thus achieving robust generalization. Moreover, by considering whether the distribution annotation is available, we apply SharpDRO to two problem settings and design a worst-case selection process for robust generalization. Theoretically, we show that SharpDRO has a great convergence guarantee. Experimentally, we simulate photon-limited corruptions using CIFAR10/100 and ImageNet30 datasets and show that SharpDRO exhibits a strong generalization ability against severe corruptions and exceeds well-known baseline methods with large performance gains.