{"total":34,"rows":[{"id":"2412.05270","title":"APOLLO: SGD-like Memory, AdamW-level Performance","created":"2024-12-06","cited_by_count":54,"area":null},{"id":"2502.01586","title":"SubTrack++ : Gradient Subspace Tracking for Scalable LLM Training","created":"2025-02-03","cited_by_count":16,"area":null},{"id":"2602.17155","title":"Powering Up Zeroth-Order Training via Subspace Gradient Orthogonalization","created":"2026-02-19","cited_by_count":12,"area":null},{"id":"2507.08784","title":"Greedy Low-Rank Gradient Compression for Distributed Learning with Convergence Guarantees","created":"2025-07-11","cited_by_count":11,"area":null},{"id":"2512.18248","title":"On the Convergence Rate of LoRA Gradient Descent","created":"2025-12-20","cited_by_count":10,"area":null},{"id":"2505.12455","title":"AltLoRA: Towards Better Gradient Approximation in Low-Rank Adaptation with Alternating Projections","created":"2025-05-18","cited_by_count":9,"area":null},{"id":"2502.05790","title":"Breaking the Frozen Subspace: Importance Sampling for Low-Rank Optimization in LLM Pretraining","created":"2025-02-09","cited_by_count":7,"area":null},{"id":"2509.18993","title":"CR-Net: Scaling Parameter-Efficient Training with Cross-Layer Low-Rank Structure","created":"2025-09-23","cited_by_count":7,"area":null},{"id":"2510.17802","title":"Unbiased Gradient Low-Rank Projection","created":"2025-10-20","cited_by_count":7,"area":null},{"id":"2502.01378","title":"CE-LoRA: Computation-Efficient LoRA Fine-Tuning for Language Models","created":"2025-02-03","cited_by_count":6,"area":null},{"id":"2505.22922","title":"Scalable Parameter and Memory Efficient Pretraining for LLM: Recent Algorithmic Advances and Benchmarking","created":"2025-05-28","cited_by_count":5,"area":null},{"id":"2509.05213","title":"An Efficient Subspace Algorithm for Federated Learning on Heterogeneous Data","created":"2025-09-05","cited_by_count":4,"area":null},{"id":"2510.09103","title":"AdaPM: a Partial Momentum Algorithm for LLM Training","created":"2025-10-10","cited_by_count":3,"area":null},{"id":"2506.15588","title":"Memory-Efficient Differentially Private Training with Gradient Random Projection","created":"2025-06-18","cited_by_count":2,"area":null},{"id":"2602.01746","title":"Rethinking LoRA for Data Heterogeneous Federated Learning: Subspace and State Alignment","created":"2026-02-02","cited_by_count":2,"area":null},{"id":"2602.03019","title":"FedKRSO: Communication and Memory Efficient Federated Fine-Tuning of Large Language Models","created":"2026-02-03","cited_by_count":2,"area":null},{"id":"2501.07237","title":"GWT: Scalable Optimizer State Compression for Large Language Model Training","created":"2025-01-13","cited_by_count":1,"area":null},{"id":"2506.01897","title":"MLorc: Momentum Low-rank Compression for Memory Efficient Large Language Model Adaptation","created":"2025-06-02","cited_by_count":1,"area":null},{"id":"2510.00192","title":"Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation","created":"2025-09-30","cited_by_count":1,"area":null},{"id":"2510.01878","title":"Geometrically Principled Randomized Optimization for Efficient LLM Training","created":"2025-10-02","cited_by_count":1,"area":null},{"id":"2601.20399","title":"Convergence Analysis of Randomized Subspace Normalized SGD under Heavy-Tailed Noise","created":"2026-01-28","cited_by_count":1,"area":null},{"id":"2602.23111","title":"PRAC: Principal-Random Subspace for LLM Activation Compression and Memory-Efficient Training","created":"2026-02-26","cited_by_count":1,"area":null},{"id":"2603.05960","title":"Omni-Masked Gradient Descent: Memory-Efficient Optimization via Mask Traversal with Improved Convergence","created":"2026-03-06","cited_by_count":1,"area":null},{"id":"2603.20632","title":"Optimal low-rank stochastic gradient estimation for LLM training","created":"2026-03-21","cited_by_count":1,"area":null},{"id":"2604.24012","title":"FedSLoP: Memory-Efficient Federated Learning with Low-Rank Gradient Projection","created":"2026-04-27","cited_by_count":1,"area":null},{"id":"2605.06316","title":"Pro-KLShampoo: Projected KL-Shampoo with Whitening Recovered by Orthogonalization","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2509.11254","title":"From PowerSGD to PowerSGD+: Low-Rank Gradient Compression for Distributed Optimization with Convergence Guarantees","created":"2025-09-14","cited_by_count":0,"area":null},{"id":"2510.26709","title":"An All-Reduce Compatible Top-K Compressor for Communication-Efficient Distributed Learning","created":"2025-10-30","cited_by_count":0,"area":null},{"id":"2602.08007","title":"From $O(mn)$ to $O(r^2)$: Two-Sided Low-Rank Communication for Adam in Distributed Training with Memory Efficiency","created":"2026-02-08","cited_by_count":0,"area":null},{"id":"2605.10288","title":"BROS: Bias-Corrected Randomized Subspaces for Memory-Efficient Single-Loop Bilevel Optimization","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2607.05872","title":"No Subspace to Track: Non-Identifiability and Optimizer State in Low-Rank Training","created":"2026-07-07","cited_by_count":0,"area":null},{"id":"2610.04204","title":"Clean: Second-order LLM Training at Linear Memory Cost via Nystr{\\\"o}m Sketching","created":"2026-10-03","cited_by_count":0,"area":null},{"id":"2610.16451","title":"StructZO: Structured Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning","created":"2026-10-12","cited_by_count":0,"area":null},{"id":"2610.19844","title":"Memory-Efficient Subspace Optimization with Residual Correction: From Momentum SGD to Muon","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}