{"total":111,"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":"2303.14773","title":"BlackVIP: Black-Box Visual Prompting for Robust Transfer Learning","created":"2023-03-26","cited_by_count":70,"area":null},{"id":"2201.09531","title":"Communication-Efficient Stochastic Zeroth-Order Optimization for Federated Learning","created":"2022-01-24","cited_by_count":59,"area":null},{"id":"2312.06353","title":"Federated Full-Parameter Tuning of Billion-Sized Language Models with Communication Cost under 18 Kilobytes","created":"2023-12-11","cited_by_count":55,"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":"2404.08080","title":"Variance-reduced Zeroth-Order Methods for Fine-Tuning Language Models","created":"2024-04-11","cited_by_count":54,"area":null},{"id":"2410.07698","title":"Enhancing Zeroth-order Fine-tuning for Language Models with Low-rank Structures","created":"2024-10-10","cited_by_count":50,"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":"2401.04343","title":"Private Fine-tuning of Large Language Models with Zeroth-order Optimization","created":"2024-01-09","cited_by_count":41,"area":null},{"id":"2305.16296","title":"A Guide Through the Zoo of Biased SGD","created":"2023-05-25","cited_by_count":40,"area":null},{"id":"2203.14195","title":"How to Robustify Black-Box ML Models? A Zeroth-Order Optimization Perspective","created":"2022-03-27","cited_by_count":39,"area":null},{"id":"2110.07004","title":"On the Convergence Theory for Hessian-Free Bilevel Algorithms","created":"2021-10-13","cited_by_count":35,"area":null},{"id":"2108.09513","title":"A Hard Label Black-box Adversarial Attack Against Graph Neural Networks","created":"2021-08-21","cited_by_count":26,"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":"2410.08989","title":"Zeroth-Order Fine-Tuning of LLMs in Random Subspaces","created":"2024-10-11","cited_by_count":26,"area":null},{"id":"2406.18060","title":"AdaZeta: Adaptive Zeroth-Order Tensor-Train Adaption for Memory-Efficient Large Language Models Fine-Tuning","created":"2024-06-26","cited_by_count":25,"area":null},{"id":"2110.04743","title":"ZARTS: On Zero-order Optimization for Neural Architecture Search","created":"2021-10-10","cited_by_count":18,"area":null},{"id":"2502.03304","title":"Harmony in Divergence: Towards Fast, Accurate, and Memory-efficient Zeroth-order LLM Fine-tuning","created":"2025-02-05","cited_by_count":18,"area":null},{"id":"2104.05245","title":"Distributed Learning Systems with First-order Methods","created":"2021-04-12","cited_by_count":17,"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":"2306.02895","title":"Evading Black-box Classifiers Without Breaking Eggs","created":"2023-06-05","cited_by_count":13,"area":null},{"id":"2405.15861","title":"Achieving Dimension-Free Communication in Federated Learning via Zeroth-Order Optimization","created":"2024-05-24","cited_by_count":13,"area":null},{"id":"2505.05465","title":"ComPO: Preference Alignment via Comparison Oracles","created":"2025-05-08","cited_by_count":13,"area":"alignment"},{"id":"2409.17401","title":"Zeroth-Order Policy Gradient for Reinforcement Learning from Human Feedback without Reward Inference","created":"2024-09-25","cited_by_count":12,"area":"alignment"},{"id":"2502.01014","title":"Refining Adaptive Zeroth-Order Optimization at Ease","created":"2025-02-03","cited_by_count":12,"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":"2202.07201","title":"Holistic Adversarial Robustness of Deep Learning Models","created":"2022-02-15","cited_by_count":11,"area":null},{"id":"2304.06430","title":"Certified Zeroth-order Black-Box Defense with Robust UNet Denoiser","created":"2023-04-13","cited_by_count":11,"area":null},{"id":"2406.14095","title":"Memory-Efficient Gradient Unrolling for Large-Scale Bi-level Optimization","created":"2024-06-20","cited_by_count":11,"area":null},{"id":"2508.02180","title":"Test-Time Model Adaptation for Quantized Neural Networks","created":"2025-08-04","cited_by_count":10,"area":null},{"id":"2203.10329","title":"Desirable Companion for Vertical Federated Learning: New Zeroth-Order Gradient Based Algorithm","created":"2022-03-19","cited_by_count":9,"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":"2501.01045","title":"ZeroFlow: Overcoming Catastrophic Forgetting is Easier than You Think","created":"2025-01-02","cited_by_count":9,"area":null},{"id":"2504.20314","title":"Perturbation-efficient Zeroth-order Optimization for Hardware-friendly On-device Training","created":"2025-04-28","cited_by_count":9,"area":null},{"id":"2206.05124","title":"Stochastic Zeroth order Descent with Structured Directions","created":"2022-06-10","cited_by_count":8,"area":null},{"id":"2109.13391","title":"Curvature-Aware Derivative-Free Optimization","created":"2021-09-27","cited_by_count":7,"area":null},{"id":"2506.14460","title":"Zeroth-Order Optimization is Secretly Single-Step Policy Optimization","created":"2025-06-17","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":"2107.06534","title":"Zeroth and First Order Stochastic Frank-Wolfe Algorithms for Constrained Optimization","created":"2021-07-14","cited_by_count":6,"area":null},{"id":"2209.07883","title":"Minibatch Stochastic Three Points Method for Unconstrained Smooth Minimization","created":"2022-09-16","cited_by_count":6,"area":null},{"id":"2506.05454","title":"Zeroth-Order Optimization Finds Flat Minima","created":"2025-06-05","cited_by_count":6,"area":"deeprl"},{"id":"2309.11006","title":"STARNet: Sensor Trustworthiness and Anomaly Recognition via Approximated Likelihood Regret for Robust Edge Autonomy","created":"2023-09-20","cited_by_count":5,"area":null},{"id":"2411.05873","title":"Poor Man's Training on MCUs: A Memory-Efficient Quantized Back-Propagation-Free Approach","created":"2024-11-07","cited_by_count":5,"area":null},{"id":"2501.04287","title":"ElasticZO: A Memory-Efficient On-Device Learning with Combined Zeroth- and First-Order Optimization","created":"2025-01-08","cited_by_count":5,"area":null},{"id":"2505.18886","title":"KerZOO: Kernel Function Informed Zeroth-Order Optimization for Accurate and Accelerated LLM Fine-Tuning","created":"2025-05-24","cited_by_count":5,"area":null},{"id":"2505.19685","title":"Graph Guided Diffusion: Unified Guidance for Conditional Graph Generation","created":"2025-05-26","cited_by_count":5,"area":"diffusion"},{"id":"2109.12213","title":"Adaptive Sampling Quasi-Newton Methods for Zeroth-Order Stochastic Optimization","created":"2021-09-24","cited_by_count":4,"area":null},{"id":"2206.02785","title":"Zeroth-Order SciML: Non-intrusive Integration of Scientific Software with Deep Learning","created":"2022-06-04","cited_by_count":4,"area":null},{"id":"2405.09106","title":"Minimisation of Polyak-\\L{}ojasewicz Functions Using Random Zeroth-Order Oracles","created":"2024-05-15","cited_by_count":4,"area":null},{"id":"2406.00812","title":"Covariance-Adaptive Sequential Black-box Optimization for Diffusion Targeted Generation","created":"2024-06-02","cited_by_count":4,"area":"diffusion"},{"id":"2501.06736","title":"ZOQO: Zero-Order Quantized Optimization","created":"2025-01-12","cited_by_count":4,"area":null},{"id":"2506.03066","title":"Sign-SZPO: Provable Preference-based Reinforcement Learning with an Unknown Link Function","created":"2025-06-03","cited_by_count":4,"area":"deeprl"},{"id":"2510.00761","title":"Downgrade to Upgrade: Optimizer Simplification Enhances Robustness in LLM Unlearning","created":"2025-10-01","cited_by_count":4,"area":"safety"},{"id":"2112.12373","title":"Decentralized Multi-Task Stochastic Optimization With Compressed Communications","created":"2021-12-23","cited_by_count":3,"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":"2407.17491","title":"Robust Adaptation of Foundation Models with Black-Box Visual Prompting","created":"2024-07-04","cited_by_count":3,"area":null},{"id":"2505.02281","title":"Minimisation of Quasar-Convex Functions Using Random Zeroth-Order Oracles","created":"2025-05-04","cited_by_count":3,"area":null},{"id":"2509.00031","title":"End-to-End On-Device Quantization-Aware Training for LLMs at Inference Cost","created":"2025-08-21","cited_by_count":3,"area":null},{"id":"2103.03701","title":"Don't Forget to Sign the Gradients!","created":"2021-03-05","cited_by_count":2,"area":"safety"},{"id":"2206.07126","title":"Lazy Queries Can Reduce Variance in Zeroth-order Optimization","created":"2022-06-14","cited_by_count":2,"area":null},{"id":"2306.16077","title":"Secure and Fast Asynchronous Vertical Federated Learning via Cascaded Hybrid Optimization","created":"2023-06-28","cited_by_count":2,"area":null},{"id":"2309.10679","title":"Oracle Complexity Reduction for Model-free LQR: A Stochastic Variance-Reduced Policy Gradient Approach","created":"2023-09-19","cited_by_count":2,"area":null},{"id":"2405.01731","title":"Dynamic Anisotropic Smoothing for Noisy Derivative-Free Optimization","created":"2024-05-02","cited_by_count":2,"area":null},{"id":"2502.12384","title":"Scalable Back-Propagation-Free Training of Optical Physics-Informed Neural Networks","created":"2025-02-17","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":"2510.19953","title":"On the Optimal Construction of Unbiased Gradient Estimators for Zeroth-Order Optimization","created":"2025-10-22","cited_by_count":2,"area":null},{"id":"2601.09076","title":"Lean Clients, Full Accuracy: Hybrid Zeroth- and First-Order Split Federated Learning","created":"2026-01-14","cited_by_count":2,"area":null},{"id":"2603.14254","title":"ZOTTA: Test-Time Adaptation with Gradient-Free Zeroth-Order Optimization","created":"2026-03-15","cited_by_count":2,"area":null},{"id":"2604.15609","title":"Adapting in the Dark: Efficient and Stable Test-Time Adaptation for Black-Box Models","created":"2026-04-17","cited_by_count":2,"area":null},{"id":"2604.19024","title":"Policy Gradient Primal-Dual Method for Safe Reinforcement Learning from Human Feedback","created":"2026-04-21","cited_by_count":2,"area":"alignment"},{"id":"2103.12954","title":"Convergence Analysis of Nonconvex Distributed Stochastic Zeroth-order Coordinate Method","created":"2021-03-24","cited_by_count":1,"area":null},{"id":"2109.08858","title":"An Accelerated Variance-Reduced Conditional Gradient Sliding Algorithm for First-order and Zeroth-order Optimization","created":"2021-09-18","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":"2404.11766","title":"End-to-End Mesh Optimization of a Hybrid Deep Learning Black-Box PDE Solver","created":"2024-04-17","cited_by_count":1,"area":null},{"id":"2405.17761","title":"Double Variance Reduction: A Smoothing Trick for Composite Optimization Problems without First-Order Gradient","created":"2024-05-28","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":"2503.06028","title":"Data-Free Black-Box Federated Learning via Zeroth-Order Gradient Estimation","created":"2025-03-08","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":"2509.15113","title":"Low-rank surrogate modeling and stochastic zero-order optimization for training of neural networks with black-box layers","created":"2025-09-18","cited_by_count":1,"area":null},{"id":"2510.15610","title":"Stochastic Optimization with Random Search","created":"2025-10-17","cited_by_count":1,"area":null},{"id":"2510.21019","title":"More Than Memory Savings: Zeroth-Order Optimization Mitigates Forgetting in Continual Learning","created":"2025-10-23","cited_by_count":1,"area":null},{"id":"2602.18181","title":"SeedFlood: A Step Toward Scalable Decentralized Fine-Tuning of LLMs","created":"2026-02-20","cited_by_count":1,"area":null},{"id":"2605.03373","title":"Learning Dynamics of Zeroth-Order Optimization: A Kernel Perspective","created":"2026-05-05","cited_by_count":1,"area":null},{"id":"2605.15622","title":"Position: Zeroth-Order Optimization in Deep Learning Is Underexplored, Not Underpowered","created":"2026-05-15","cited_by_count":1,"area":null},{"id":"2104.04405","title":"Learning Sampling Policy for Faster Derivative Free Optimization","created":"2021-04-09","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":"2410.02559","title":"Obtaining Lower Query Complexities through Lightweight Zeroth-Order Proximal Gradient Algorithms","created":"2024-10-03","cited_by_count":0,"area":null},{"id":"2501.07201","title":"An Enhanced Zeroth-Order Stochastic Frank-Wolfe Framework for Constrained Finite-Sum Optimization","created":"2025-01-13","cited_by_count":0,"area":null},{"id":"2505.19720","title":"A Structured Tour of Optimization with Finite Differences","created":"2025-05-26","cited_by_count":0,"area":null},{"id":"2506.17264","title":"OAT-Rephrase: Optimization-Aware Training Data Rephrasing for Zeroth-Order LLM Fine-Tuning","created":"2025-06-10","cited_by_count":0,"area":null},{"id":"2510.03648","title":"SAFA-SNN: Sparsity-Aware On-Device Few-Shot Class-Incremental Learning with Fast-Adaptive Structure of Spiking Neural Network","created":"2025-10-04","cited_by_count":0,"area":null},{"id":"2510.16157","title":"Zeroth-Order Sharpness-Aware Learning with Exponential Tilting","created":"2025-10-17","cited_by_count":0,"area":null},{"id":"2510.18812","title":"A Unified Perspective on Optimization in Machine Learning and Neuroscience: From Gradient Descent to Neural Adaptation","created":"2025-10-21","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":"2601.01160","title":"Gradient-Free Approaches is a Key to an Efficient Interaction with Markovian Stochasticity","created":"2026-01-03","cited_by_count":0,"area":null},{"id":"2601.12917","title":"CooperLLM: Cloud-Edge-End Cooperative Federated Fine-tuning for LLMs via ZOO-based Gradient Correction","created":"2026-01-19","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}],"next_cursor":"100"}