{"total":198,"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":"2202.00817","title":"Do Differentiable Simulators Give Better Policy Gradients?","created":"2022-02-02","cited_by_count":89,"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":"2404.01650","title":"Test-Time Model Adaptation with Only Forward Passes","created":"2024-04-02","cited_by_count":74,"area":null},{"id":"2102.07698","title":"How to Learn when Data Reacts to Your Model: Performative Gradient Descent","created":"2021-02-15","cited_by_count":71,"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":"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":"2203.00263","title":"Private Convex Optimization via Exponential Mechanism","created":"2022-03-01","cited_by_count":49,"area":null},{"id":"2104.11470","title":"Random Noise Defense Against Query-Based Black-Box Attacks","created":"2021-04-23","cited_by_count":47,"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":"2203.06560","title":"Query-Efficient Black-box Adversarial Attacks Guided by a Transfer-based Prior","created":"2022-03-13","cited_by_count":38,"area":null},{"id":"2303.03751","title":"Zeroth-Order Optimization Meets Human Feedback: Provable Learning via Ranking Oracles","created":"2023-03-07","cited_by_count":35,"area":"alignment"},{"id":"2102.04168","title":"Provable Model-based Nonlinear Bandit and Reinforcement Learning: Shelve Optimism, Embrace Virtual Curvature","created":"2021-02-08","cited_by_count":32,"area":null},{"id":"2102.01583","title":"The Min-Max Complexity of Distributed Stochastic Convex Optimization with Intermittent Communication","created":"2021-02-02","cited_by_count":31,"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":"2307.04504","title":"An Algorithm with Optimal Dimension-Dependence for Zero-Order Nonsmooth Nonconvex Stochastic Optimization","created":"2023-07-10","cited_by_count":23,"area":null},{"id":"2402.06734","title":"Corruption Robust Offline Reinforcement Learning with Human Feedback","created":"2024-02-09","cited_by_count":20,"area":"alignment"},{"id":"2501.06773","title":"Pareto Set Learning for Multi-Objective Reinforcement Learning","created":"2025-01-12","cited_by_count":20,"area":"deeprl"},{"id":"2402.05926","title":"On the Convergence of Zeroth-Order Federated Tuning for Large Language Models","created":"2024-02-08","cited_by_count":19,"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":"2306.14853","title":"Near-Optimal Nonconvex-Strongly-Convex Bilevel Optimization with Fully First-Order Oracles","created":"2023-06-26","cited_by_count":17,"area":null},{"id":"2410.09591","title":"Unlearn and Burn: Adversarial Machine Unlearning Requests Destroy Model Accuracy","created":"2024-10-12","cited_by_count":17,"area":"safety"},{"id":"2307.08352","title":"Zero-th Order Algorithm for Softmax Attention Optimization","created":"2023-07-17","cited_by_count":16,"area":null},{"id":"2102.05710","title":"Derivative-Free Reinforcement Learning: A Review","created":"2021-02-10","cited_by_count":15,"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":"2306.08553","title":"Noise Stability Optimization for Finding Flat Minima: A Hessian-based Regularization Approach","created":"2023-06-14","cited_by_count":14,"area":null},{"id":"2406.12844","title":"Synergizing Foundation Models and Federated Learning: A Survey","created":"2024-06-18","cited_by_count":14,"area":null},{"id":"2103.11102","title":"Projection-free Distributed Online Learning with Sublinear Communication Complexity","created":"2021-03-20","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":"2306.02159","title":"Gradient-free optimization of highly smooth functions: improved analysis and a new algorithm","created":"2023-06-03","cited_by_count":12,"area":null},{"id":"2307.12551","title":"Continuation Path Learning for Homotopy Optimization","created":"2023-07-24","cited_by_count":12,"area":null},{"id":"2308.09858","title":"Tensor-Compressed Back-Propagation-Free Training for (Physics-Informed) Neural Networks","created":"2023-08-18","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":"2602.17155","title":"Powering Up Zeroth-Order Training via Subspace Gradient Orthogonalization","created":"2026-02-19","cited_by_count":12,"area":null},{"id":"2207.10415","title":"Log Barriers for Safe Black-box Optimization with Application to Safe Reinforcement Learning","created":"2022-07-21","cited_by_count":11,"area":null},{"id":"2405.19098","title":"Efficient Black-box Adversarial Attacks via Bayesian Optimization Guided by a Function Prior","created":"2024-05-29","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":"2510.19975","title":"Revisiting Zeroth-Order Optimization: Minimum-Variance Two-Point Estimators and Directionally Aligned Perturbations","created":"2025-10-22","cited_by_count":11,"area":null},{"id":"2302.06085","title":"Algorithmic Aspects of the Log-Laplace Transform and a Non-Euclidean Proximal Sampler","created":"2023-02-13","cited_by_count":10,"area":null},{"id":"2302.13144","title":"Revisiting LQR Control from the Perspective of Receding-Horizon Policy Gradient","created":"2023-02-25","cited_by_count":10,"area":null},{"id":"2602.00170","title":"The Blessing of Dimensionality in LLM Fine-tuning: A Variance-Curvature Perspective","created":"2026-01-30","cited_by_count":10,"area":null},{"id":"2105.01850","title":"Preference learning along multiple criteria: A game-theoretic perspective","created":"2021-05-05","cited_by_count":9,"area":null},{"id":"2301.12624","title":"Learning the Kalman Filter with Fine-Grained Sample Complexity","created":"2023-01-30","cited_by_count":9,"area":null},{"id":"2506.04430","title":"Leveraging Coordinate Momentum in SignSGD and Muon: Memory-Optimized Zero-Order","created":"2025-06-04","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":"2402.09152","title":"Improved Regret for Bandit Convex Optimization with Delayed Feedback","created":"2024-02-14","cited_by_count":8,"area":null},{"id":"2406.19579","title":"Private Zeroth-Order Nonsmooth Nonconvex Optimization","created":"2024-06-27","cited_by_count":8,"area":null},{"id":"2503.24322","title":"NoProp: Training Neural Networks without Full Back-propagation or Full Forward-propagation","created":"2025-03-31","cited_by_count":8,"area":null},{"id":"2205.13910","title":"A gradient estimator via L1-randomization for online zero-order optimization with two point feedback","created":"2022-05-27","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":"2311.17586","title":"Federated Online and Bandit Convex Optimization","created":"2023-11-29","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":"2511.07971","title":"Low-Rank Curvature for Zeroth-Order Optimization in LLM Fine-Tuning","created":"2025-11-11","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":"2106.09215","title":"Optimum-statistical Collaboration Towards General and Efficient Black-box Optimization","created":"2021-06-17","cited_by_count":6,"area":null},{"id":"2108.07406","title":"From the Greene--Wu Convolution to Gradient Estimation over Riemannian Manifolds","created":"2021-08-17","cited_by_count":6,"area":null},{"id":"2210.04810","title":"Towards a Theoretical Foundation of Policy Optimization for Learning Control Policies","created":"2022-10-10","cited_by_count":6,"area":null},{"id":"2503.12668","title":"ZO2: Scalable Zeroth-Order Fine-Tuning for Extremely Large Language Models with Limited GPU Memory","created":"2025-03-16","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":"2110.13265","title":"On the Second-order Convergence Properties of Random Search Methods","created":"2021-10-25","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":"2502.03604","title":"Bilevel ZOFO: Efficient LLM Fine-Tuning and Meta-Training","created":"2025-02-05","cited_by_count":5,"area":null},{"id":"2502.19571","title":"LORENZA: Enhancing Generalization in Low-Rank Gradient LLM Training via Efficient Zeroth-Order Adaptive SAM","created":"2025-02-26","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":"2603.15757","title":"You've Got a Golden Ticket: Improving Generative Robot Policies With A Single Noise Vector","created":"2026-03-16","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":"2201.10780","title":"On Sharp Stochastic Zeroth Order Hessian Estimators over Riemannian Manifolds","created":"2022-01-26","cited_by_count":4,"area":null},{"id":"2301.11777","title":"Interpreting learning in biological neural networks as zero-order optimization method","created":"2023-01-27","cited_by_count":4,"area":null},{"id":"2303.04030","title":"PyXAB -- A Python Library for $\\mathcal{X}$-Armed Bandit and Online Blackbox Optimization Algorithms","created":"2023-03-07","cited_by_count":4,"area":null},{"id":"2401.17460","title":"Rendering Wireless Environments Useful for Gradient Estimators: A Zero-Order Stochastic Federated Learning Method","created":"2024-01-30","cited_by_count":4,"area":null},{"id":"2410.05880","title":"Improved Sample Complexity for Private Nonsmooth Nonconvex Optimization","created":"2024-10-08","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":"2505.17852","title":"Scaling Recurrent Neural Networks to a Billion Parameters with Zero-Order Optimization","created":"2025-05-23","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":"2509.15552","title":"The Multi-Query Paradox in Zeroth-Order Optimization","created":"2025-09-19","cited_by_count":4,"area":null},{"id":"2509.24837","title":"ZOO-Prune: Training-Free Token Pruning via Zeroth-Order Gradient Estimation in Vision-Language Models","created":"2025-09-29","cited_by_count":4,"area":"lr"},{"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":"2601.17261","title":"AGZO: Activation-Guided Zeroth-Order Optimization for LLM Fine-Tuning","created":"2026-01-24","cited_by_count":4,"area":null},{"id":"2112.12373","title":"Decentralized Multi-Task Stochastic Optimization With Compressed Communications","created":"2021-12-23","cited_by_count":3,"area":null},{"id":"2208.04065","title":"Optimistic Optimisation of Composite Objective with Exponentiated Update","created":"2022-08-08","cited_by_count":3,"area":null},{"id":"2306.09778","title":"Gradient is All You Need? How Consensus-Based Optimization can be Interpreted as a Stochastic Relaxation of Gradient Descent","created":"2023-06-16","cited_by_count":3,"area":null},{"id":"2405.11785","title":"Guided Multi-objective Generative AI to Enhance Structure-based Drug Design","created":"2024-05-20","cited_by_count":3,"area":null},{"id":"2409.15520","title":"MobiZO: Enabling Efficient LLM Fine-Tuning at the Edge via Inference Engines","created":"2024-09-23","cited_by_count":3,"area":null},{"id":"2202.08532","title":"Mitigating Closed-model Adversarial Examples with Bayesian Neural Modeling for Enhanced End-to-End Speech Recognition","created":"2022-02-17","cited_by_count":2,"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":"2210.05618","title":"Zero-Order One-Point Estimate with Distributed Stochastic Gradient-Tracking Technique","created":"2022-10-11","cited_by_count":2,"area":null},{"id":"2301.07806","title":"Federated Automatic Differentiation","created":"2023-01-18","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":"2409.01477","title":"Compatible Gradient Approximations for Actor-Critic Algorithms","created":"2024-09-02","cited_by_count":2,"area":"deeprl"},{"id":"2411.13999","title":"Accelerated zero-order SGD under high-order smoothness and overparameterized regime","created":"2024-11-21","cited_by_count":2,"area":null},{"id":"2501.19099","title":"Elucidating Subspace Perturbation in Zeroth-Order Optimization: Theory and Practice at Scale","created":"2025-01-31","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":"2507.06125","title":"Subspace-based Approximate Hessian Method for Zeroth-Order Optimization","created":"2025-07-08","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}],"next_cursor":"100"}