gradient approximation

Gradient-Guided Multi-Judge Prompt Optimization ACL 2026 Coherence-based Approximate Derivatives via Web of Affine Spaces Optimization RSS 2025 Erase Then Rectify: A Training-Free Parameter Editing Approach for Cost-Effective Graph Unlearning AAAI 2025 Fast and Slow Gradient Approximation for Binary Neural Network Optimization AAAI 2025 Fewer May Be Better: Enhancing Offline Reinforcement Learning with Reduced Dataset ICLR 2025 LimaCost: Data Valuation for Instruction Tuning of Large Language Models EMNLP 2025 BiPer: Binary Neural Networks using a Periodic Function CVPR 2024 Differentiable JPEG: The Devil Is in the Details WACV 2024 DisC-GS: Discontinuity-aware Gaussian Splatting NeurIPS 2024 ECoFLaP: Efficient Coarse-to-Fine Layer-Wise Pruning for Vision-Language Models ICLR 2024 Efficient Sharpness-Aware Minimization for Molecular Graph Transformer Models ICLR 2024 LoRA-GA: Low-Rank Adaptation with Gradient Approximation NeurIPS 2024 Memory-Efficient Fine-Tuning of Transformers via Token Selection EMNLP 2024 SLED: Self Logits Evolution Decoding for Improving Factuality in Large Language Models NeurIPS 2024 Unlocking Black-Box Prompt Tuning Efficiency via Zeroth-Order Optimization EMNLP 2024 Any-scale Balanced Samplers for Discrete Space ICLR 2023 Backpropagation at the Infinitesimal Inference Limit of Energy-Based Models: Unifying Predictive Coding, Equilibrium Propagation, and Contrastive Hebbian Learning ICLR 2023 Black-Box Tuning of Vision-Language Models with Effective Gradient Approximation EMNLP 2023 Bridging Discrete and Backpropagation: Straight-Through and Beyond NeurIPS 2023 DropIT: Dropping Intermediate Tensors for Memory-Efficient DNN Training ICLR 2023 Efficient Gradient Approximation Method for Constrained Bilevel Optimization AAAI 2023 Provable Data Subset Selection For Efficient Neural Networks Training ICML 2023 Scalable Set Encoding with Universal Mini-Batch Consistency and Unbiased Full Set Gradient Approximation ICML 2023 Scalable Subset Sampling with Neural Conditional Poisson Networks ICLR 2023 Softmax Output Approximation for Activation Memory-Efficient Training of Attention-based Networks NeurIPS 2023