gradient estimation

Robust and Faster Zeroth-Order Minimax Optimization: Complexity and Applications NeurIPS 2024 Safe online convex optimization with multi-point feedback L4DC 2024 S-STE: Continuous Pruning Function for Efficient 2:4 Sparse Pre-training NeurIPS 2024 Thinking Forward: Memory-Efficient Federated Finetuning of Language Models NeurIPS 2024 User-level Differentially Private Stochastic Convex Optimization: Efficient Algorithms with Optimal Rates AISTATS 2024 Adaptive Perturbation-Based Gradient Estimation for Discrete Latent Variable Models AAAI 2023 A Generalizable Physics-informed Learning Framework for Risk Probability Estimation L4DC 2023 Black-Box Adversarial Attack on Time Series Classification AAAI 2023 Boosting Decision-Based Black-Box Adversarial Attack with Gradient Priors IJCAI 2023 CAME: Confidence-guided Adaptive Memory Efficient Optimization ACL 2023 Can Forward Gradient Match Backpropagation? ICML 2023 CASN:Class-Aware Score Network for Textual Adversarial Detection ACL 2023 Cold Analysis of Rao-Blackwellized Straight-Through Gumbel-Softmax Gradient Estimator ICML 2023 Differentiable Sampling of Categorical Distributions Using the CatLog-Derivative Trick NeurIPS 2023 Dual Student Networks for Data-Free Model Stealing ICLR 2023 Efficient Quantum Algorithms for Quantum Optimal Control ICML 2023 Explaining the effects of non-convergent MCMC in the training of Energy-Based Models ICML 2023 First Order Stochastic Optimization with Oblivious Noise NeurIPS 2023 Gradient Estimation for Binary Latent Variables via Gradient Variance Clipping AAAI 2023 Improving Dual-Encoder Training through Dynamic Indexes for Negative Mining AISTATS 2023 Low-Variance Gradient Estimation in Unrolled Computation Graphs with ES-Single ICML 2023 Stable and low-precision training for large-scale vision-language models NeurIPS 2023 Variance-Reduced Gradient Estimation via Noise-Reuse in Online Evolution Strategies NeurIPS 2023 Weighted Sampling without Replacement for Deep Top-k Classification ICML 2023 A contrastive rule for meta-learning NeurIPS 2022