conftrace_

gradient estimation

150 papers

Explore in graph

Co-occurring keywords

variance reduction (523) reinforcement learning (4352) zeroth-order optimization (102) policy gradient (520) adversarial attack (1621) stochastic optimization (1060) variational inference (2069) generative model (2892) large language model (13587) black-box attack (237)

Papers

Deep Generalized Unfolding Networks for Image Restoration CVPR 2022
Nearest Neighbour Based Estimates of Gradients: Sharp Nonasymptotic Bounds and Applications AISTATS 2021
Generalized Doubly Reparameterized Gradient Estimators ICML 2021
Improved Contrastive Divergence Training of Energy-Based Models ICML 2021
CARMS: Categorical-Antithetic-REINFORCE Multi-Sample Gradient Estimator NIPS 2021
Don’t Generate Me: Training Differentially Private Generative Models with Sinkhorn Divergence NIPS 2021
Storchastic: A Framework for General Stochastic Automatic Differentiation NIPS 2021
MAZE: Data-Free Model Stealing Attack Using Zeroth-Order Gradient Estimation CVPR 2021
Nonlinear Projection Based Gradient Estimation for Query Efficient Blackbox Attacks AISTATS 2021
Recomposing the Reinforcement Learning Building Blocks with Hypernetworks ICML 2021
ARMS: Antithetic-REINFORCE-Multi-Sample Gradient for Binary Variables ICML 2021
A unified view of likelihood ratio and reparameterization gradients AISTATS 2021
Unbiased Gradient Estimation in Unrolled Computation Graphs with Persistent Evolution Strategies ICML 2021
SA-BNN: State-Aware Binary Neural Network AAAI 2021
Reserve Price Optimization for First Price Auctions in Display Advertising ICML 2021
Deep Bayesian Quadrature Policy Optimization AAAI 2021
Parallel tempering on optimized paths ICML 2021
Attack As the Best Defense: Nullifying Image-to-Image Translation GANs via Limit-Aware Adversarial Attack ICCV 2021
On Training Implicit Models NIPS 2021
Variance-reduced First-order Meta-learning for Natural Language Processing Tasks NAACL 2021
Random Noise Defense Against Query-Based Black-Box Attacks NIPS 2021
On the Convergence of Prior-Guided Zeroth-Order Optimization Algorithms NIPS 2021
Unbiased Risk Estimators Can Mislead: A Case Study of Learning with Complementary Labels ICML 2020
Super-efficiency of automatic differentiation for functions defined as a minimum ICML 2020
Optimizing Black-box Metrics with Adaptive Surrogates ICML 2020