{"total":22,"rows":[{"id":"2106.06607","title":"Invariance Principle Meets Information Bottleneck for Out-of-Distribution Generalization","created":"2021-06-11","cited_by_count":220,"area":null},{"id":"2203.11834","title":"Improving Generalization in Federated Learning by Seeking Flat Minima","created":"2022-03-22","cited_by_count":98,"area":null},{"id":"2402.11337","title":"Learning by Reconstruction Produces Uninformative Features For Perception","created":"2024-02-17","cited_by_count":55,"area":null},{"id":"2412.03752","title":"Beyond Local Sharpness: Communication-Efficient Global Sharpness-aware Minimization for Federated Learning","created":"2024-12-04","cited_by_count":8,"area":null},{"id":"2309.03060","title":"CoLA: Exploiting Compositional Structure for Automatic and Efficient Numerical Linear Algebra","created":"2023-09-06","cited_by_count":7,"area":null},{"id":"2104.07006","title":"Fast quantum state reconstruction via accelerated non-convex programming","created":"2021-04-14","cited_by_count":5,"area":null},{"id":"2110.13265","title":"On the Second-order Convergence Properties of Random Search Methods","created":"2021-10-25","cited_by_count":5,"area":null},{"id":"2103.00704","title":"FedPower: Privacy-Preserving Distributed Eigenspace Estimation","created":"2021-03-01","cited_by_count":4,"area":null},{"id":"2505.22602","title":"One Rank at a Time: Cascading Error Dynamics in Sequential Learning","created":"2025-05-28","cited_by_count":3,"area":null},{"id":"2510.22440","title":"Low-Precision Streaming PCA","created":"2025-10-25","cited_by_count":3,"area":null},{"id":"2108.09264","title":"Practical and Fast Momentum-Based Power Methods","created":"2021-08-20","cited_by_count":1,"area":null},{"id":"2110.12065","title":"Multiplication-Avoiding Variant of Power Iteration with Applications","created":"2021-10-22","cited_by_count":1,"area":null},{"id":"2310.04283","title":"On the Error-Propagation of Inexact Hotelling's Deflation for Principal Component Analysis","created":"2023-10-06","cited_by_count":1,"area":null},{"id":"2502.17615","title":"Provable Model-Parallel Distributed Principal Component Analysis with Parallel Deflation","created":"2025-02-24","cited_by_count":1,"area":null},{"id":"2202.07992","title":"Improved analysis of randomized SVD for top-eigenvector approximation","created":"2022-02-16","cited_by_count":0,"area":null},{"id":"2211.00866","title":"Gradient Descent and the Power Method: Exploiting their connection to find the leftmost eigen-pair and escape saddle points","created":"2022-11-02","cited_by_count":0,"area":null},{"id":"2310.01165","title":"Towards guarantees for parameter isolation in continual learning","created":"2023-10-02","cited_by_count":0,"area":null},{"id":"2407.16611","title":"Local vs Global continual learning","created":"2024-07-23","cited_by_count":0,"area":null},{"id":"2501.15131","title":"Split-Merge: A Difference-based Approach for Dominant Eigenvalue Problem","created":"2025-01-25","cited_by_count":0,"area":null},{"id":"2502.00320","title":"$k$-SVD with Gradient Descent","created":"2025-02-01","cited_by_count":0,"area":null},{"id":"2602.03682","title":"Improved Analysis of the Accelerated Noisy Power Method with Applications to Decentralized PCA","created":"2026-02-03","cited_by_count":0,"area":null},{"id":"2608.04406","title":"Incremental Aggregation on the Grassmannian for Asynchronous Eigenspace Computation","created":"2026-08-05","cited_by_count":0,"area":null}],"next_cursor":null}