{"total":24,"rows":[{"id":"2307.13304","title":"QuIP: 2-Bit Quantization of Large Language Models With Guarantees","created":"2023-07-25","cited_by_count":414,"area":null},{"id":"2104.09459","title":"A Practical Method for Constructing Equivariant Multilayer Perceptrons for Arbitrary Matrix Groups","created":"2021-04-19","cited_by_count":187,"area":null},{"id":"2110.15343","title":"Scatterbrain: Unifying Sparse and Low-rank Attention Approximation","created":"2021-10-28","cited_by_count":130,"area":null},{"id":"2205.13026","title":"Preference Dynamics Under Personalized Recommendations","created":"2022-05-25","cited_by_count":25,"area":null},{"id":"2102.03646","title":"Streaming k-PCA: Efficient guarantees for Oja's algorithm, beyond rank-one updates","created":"2021-02-06","cited_by_count":21,"area":null},{"id":"2104.00512","title":"On the Optimality of the Oja's Algorithm for Online PCA","created":"2021-03-31","cited_by_count":11,"area":null},{"id":"2106.14857","title":"Bootstrapping the error of Oja's algorithm","created":"2021-06-28","cited_by_count":11,"area":null},{"id":"2306.17378","title":"Global Optimality in Bivariate Gradient-based DAG Learning","created":"2023-06-30","cited_by_count":10,"area":null},{"id":"2410.14802","title":"Implicit Regularization of Sharpness-Aware Minimization for Scale-Invariant Problems","created":"2024-10-18","cited_by_count":10,"area":null},{"id":"2212.04025","title":"A Novel Stochastic Gradient Descent Algorithm for Learning Principal Subspaces","created":"2022-12-08","cited_by_count":7,"area":null},{"id":"2403.03905","title":"Black-Box $k$-to-$1$-PCA Reductions: Theory and Applications","created":"2024-03-06","cited_by_count":7,"area":null},{"id":"2105.12257","title":"Rank-one matrix estimation: analytic time evolution of gradient descent dynamics","created":"2021-05-25","cited_by_count":5,"area":null},{"id":"2210.06705","title":"From Gradient Flow on Population Loss to Learning with Stochastic Gradient Descent","created":"2022-10-13","cited_by_count":5,"area":null},{"id":"2308.03661","title":"Matrix Completion in Almost-Verification Time","created":"2023-08-07","cited_by_count":4,"area":null},{"id":"2102.00937","title":"Riemannian Perspective on Matrix Factorization","created":"2021-02-01","cited_by_count":3,"area":null},{"id":"2106.03780","title":"Learning Stochastic Optimal Policies via Gradient Descent","created":"2021-06-07","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":"2602.05887","title":"Escaping Local Minima Provably in Non-convex Matrix Sensing: A Deterministic Framework via Simulated Lifting","created":"2026-02-05","cited_by_count":3,"area":null},{"id":"2310.12969","title":"Demystifying the Myths and Legends of Nonconvex Convergence of SGD","created":"2023-10-19","cited_by_count":2,"area":null},{"id":"2609.26508","title":"Gap-Free Streaming PCA Beyond Rank-One Updates: Near-Optimal Rates and Applications to Differential Privacy","created":"2026-09-22","cited_by_count":1,"area":null},{"id":"2106.07905","title":"Non-Gradient Manifold Neural Network","created":"2021-06-15","cited_by_count":0,"area":null},{"id":"2110.03273","title":"AgFlow: Fast Model Selection of Penalized PCA via Implicit Regularization Effects of Gradient Flow","created":"2021-10-07","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":"2505.10882","title":"Global Convergence of Adaptive Sensing for Principal Eigenvector Estimation","created":"2025-05-16","cited_by_count":0,"area":null}],"next_cursor":null}