{"total":56,"rows":[{"id":"2305.17333","title":"Fine-Tuning Language Models with Just Forward Passes","created":"2023-05-27","cited_by_count":345,"area":null},{"id":"2402.11592","title":"Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark","created":"2024-02-18","cited_by_count":114,"area":null},{"id":"2310.02025","title":"DeepZero: Scaling up Zeroth-Order Optimization for Deep Model Training","created":"2023-10-03","cited_by_count":76,"area":null},{"id":"2306.03082","title":"InstructZero: Efficient Instruction Optimization for Black-Box Large Language Models","created":"2023-06-05","cited_by_count":68,"area":null},{"id":"2402.15751","title":"Sparse MeZO: Less Parameters for Better Performance in Zeroth-Order LLM Fine-Tuning","created":"2024-02-24","cited_by_count":54,"area":null},{"id":"2102.10707","title":"A Zeroth-Order Block Coordinate Descent Algorithm for Huge-Scale Black-Box Optimization","created":"2021-02-21","cited_by_count":46,"area":null},{"id":"2209.05045","title":"Gradient-Free Methods for Deterministic and Stochastic Nonsmooth Nonconvex Optimization","created":"2022-09-12","cited_by_count":43,"area":null},{"id":"2304.05818","title":"Gradient-Free Textual Inversion","created":"2023-04-12","cited_by_count":29,"area":null},{"id":"2310.09639","title":"DPZero: Private Fine-Tuning of Language Models without Backpropagation","created":"2023-10-14","cited_by_count":26,"area":null},{"id":"2301.06428","title":"Faster Gradient-Free Algorithms for Nonsmooth Nonconvex Stochastic Optimization","created":"2023-01-16","cited_by_count":17,"area":null},{"id":"2102.03389","title":"Online Statistical Inference for Stochastic Optimization via Kiefer-Wolfowitz Methods","created":"2021-02-05","cited_by_count":14,"area":null},{"id":"2310.03123","title":"Efficient Federated Prompt Tuning for Black-box Large Pre-trained Models","created":"2023-10-04","cited_by_count":12,"area":null},{"id":"2405.16805","title":"Gradient Compressed Sensing: A Query-Efficient Gradient Estimator for High-Dimensional Zeroth-Order Optimization","created":"2024-05-27","cited_by_count":12,"area":null},{"id":"2210.05584","title":"On Adaptivity in Non-stationary Stochastic Optimization With Bandit Feedback","created":"2022-10-11","cited_by_count":11,"area":null},{"id":"2310.05143","title":"ZooPFL: Exploring Black-box Foundation Models for Personalized Federated Learning","created":"2023-10-08","cited_by_count":9,"area":null},{"id":"2410.09823","title":"Simultaneous Computation and Memory Efficient Zeroth-Order Optimizer for Fine-Tuning Large Language Models","created":"2024-10-13","cited_by_count":9,"area":null},{"id":"2109.13391","title":"Curvature-Aware Derivative-Free Optimization","created":"2021-09-27","cited_by_count":7,"area":null},{"id":"2205.14737","title":"Stochastic Zeroth Order Gradient and Hessian Estimators: Variance Reduction and Refined Bias Bounds","created":"2022-05-29","cited_by_count":7,"area":null},{"id":"2102.05198","title":"Statistical Inference for Polyak-Ruppert Averaged Zeroth-order Stochastic Gradient Algorithm","created":"2021-02-10","cited_by_count":6,"area":null},{"id":"2107.12102","title":"Global optimization using random embeddings","created":"2021-07-26","cited_by_count":6,"area":null},{"id":"2503.04181","title":"Boosting Offline Optimizers with Surrogate Sensitivity","created":"2025-03-06","cited_by_count":6,"area":null},{"id":"2106.10166","title":"Problem Dependent View on Structured Thresholding Bandit Problems","created":"2021-06-18","cited_by_count":5,"area":null},{"id":"2602.04761","title":"Improved Dimension Dependence for Bandit Convex Optimization with Gradient Variations","created":"2026-02-04","cited_by_count":5,"area":null},{"id":"2105.11818","title":"SGD with Coordinate Sampling: Theory and Practice","created":"2021-05-25","cited_by_count":4,"area":null},{"id":"2501.06736","title":"ZOQO: Zero-Order Quantized Optimization","created":"2025-01-12","cited_by_count":4,"area":null},{"id":"2502.06168","title":"Dynamic Pricing with Adversarially-Censored Demands","created":"2025-02-10","cited_by_count":4,"area":null},{"id":"2509.15552","title":"The Multi-Query Paradox in Zeroth-Order Optimization","created":"2025-09-19","cited_by_count":4,"area":null},{"id":"2509.16300","title":"ROOT: Rethinking Offline Optimization as Distributional Translation via Probabilistic Bridge","created":"2025-09-19","cited_by_count":4,"area":null},{"id":"2210.05279","title":"Zeroth-Order Hard-Thresholding: Gradient Error vs. Expansivity","created":"2022-10-11","cited_by_count":3,"area":null},{"id":"2302.05120","title":"Step by Step Loss Goes Very Far: Multi-Step Quantization for Adversarial Text Attacks","created":"2023-02-10","cited_by_count":3,"area":null},{"id":"2603.04733","title":"FOZO: Forward-Only Zeroth-Order Prompt Optimization for Test-Time Adaptation","created":"2026-03-05","cited_by_count":3,"area":null},{"id":"2206.07126","title":"Lazy Queries Can Reduce Variance in Zeroth-order Optimization","created":"2022-06-14","cited_by_count":2,"area":null},{"id":"2403.15603","title":"Forward Learning for Gradient-based Black-box Saliency Map Generation","created":"2024-03-22","cited_by_count":2,"area":null},{"id":"2510.18228","title":"Towards Fast LLM Fine-tuning through Zeroth-Order Optimization with Projected Gradient-Aligned Perturbations","created":"2025-10-21","cited_by_count":2,"area":null},{"id":"2104.11283","title":"A Dimension-Insensitive Algorithm for Stochastic Zeroth-Order Optimization","created":"2021-04-22","cited_by_count":1,"area":null},{"id":"2208.04579","title":"Adaptive Zeroth-Order Optimisation of Nonconvex Composite Objectives","created":"2022-08-09","cited_by_count":1,"area":null},{"id":"2402.01621","title":"Stochastic Two Points Method for Deep Model Zeroth-order Optimization","created":"2024-02-02","cited_by_count":1,"area":null},{"id":"2409.00459","title":"Gradient-Free Method for Heavily Constrained Nonconvex Optimization","created":"2024-08-31","cited_by_count":1,"area":null},{"id":"2505.13954","title":"VAMO: Efficient Zeroth-Order Variance Reduction for SGD with Faster Convergence","created":"2025-05-20","cited_by_count":1,"area":null},{"id":"2506.21833","title":"Memory Savings at What Cost? A Study of Alternatives to Backpropagation","created":"2025-06-27","cited_by_count":1,"area":null},{"id":"2105.03527","title":"Scalable Projection-Free Optimization","created":"2021-05-07","cited_by_count":0,"area":null},{"id":"2209.05372","title":"Convergence of Batch Updating Methods with Approximate Gradients and/or Noisy Measurements: Theory and Computational Results","created":"2022-09-12","cited_by_count":0,"area":null},{"id":"2211.11710","title":"Adaptive Stochastic Optimisation of Nonconvex Composite Objectives","created":"2022-11-21","cited_by_count":0,"area":null},{"id":"2407.06325","title":"CONGO: Compressive Online Gradient Optimization","created":"2024-07-08","cited_by_count":0,"area":null},{"id":"2504.09409","title":"Mirror Descent Linearized Augmented Lagrangian Methods for Nonconvex Constrained Stochastic Zeroth-Order Optimization","created":"2025-04-13","cited_by_count":0,"area":null},{"id":"2505.22042","title":"Estimating the Effects of Sample Training Orders for Large Language Models without Retraining","created":"2025-05-28","cited_by_count":0,"area":null},{"id":"2510.25074","title":"BOND: License to Train with Black-Box Functions","created":"2025-10-29","cited_by_count":0,"area":null},{"id":"2511.02757","title":"ConMeZO: Adaptive Descent-Direction Sampling for Gradient-Free Finetuning of Large Language Models","created":"2025-11-04","cited_by_count":0,"area":null},{"id":"2601.20422","title":"Guiding the Recommender: Information-Aware Auto-Bidding for Content Promotion","created":"2026-01-28","cited_by_count":0,"area":null},{"id":"2602.13659","title":"Zero-Order Optimization for LLM Fine-Tuning via Learnable Direction Sampling","created":"2026-02-14","cited_by_count":0,"area":null},{"id":"2603.07389","title":"Feed m Birds with One Scone: Accelerating Multi-task Gradient Balancing via Bi-level Optimization","created":"2026-03-08","cited_by_count":0,"area":null},{"id":"2604.12325","title":"Black-Box Optimization From Small Offline Datasets via Meta Learning with Synthetic Tasks","created":"2026-04-14","cited_by_count":0,"area":null},{"id":"2604.14669","title":"Zeroth-Order Optimization at the Edge of Stability","created":"2026-04-16","cited_by_count":0,"area":null},{"id":"2604.25372","title":"From Cursed to Competitive: Closing the ZO-FO Gap via Input-to-State Stability","created":"2026-04-28","cited_by_count":0,"area":null},{"id":"2605.14373","title":"Turning Stale Gradients into Stable Gradients: Coherent Coordinate Descent with Implicit Landscape Smoothing for Lightweight Zeroth-Order Optimization","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2606.19878","title":"On the Oracle Complexity of Interpolation-Based Gradient Descent","created":"2026-06-18","cited_by_count":0,"area":null}],"next_cursor":null}