{"list":"other","total":70,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1706.06083","title":"Towards Deep Learning Models Resistant to Adversarial Attacks","created":"2017-06-19","cited_by_count":6415},{"id":"1510.00149","title":"Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding","created":"2015-10-01","cited_by_count":2329},{"id":"1803.03635","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","created":"2018-03-09","cited_by_count":2262},{"id":"1706.02677","title":"Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour","created":"2017-06-08","cited_by_count":1492},{"id":"1608.03981","title":"Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising","created":"2016-08-13","cited_by_count":1358},{"id":"1902.02918","title":"Certified Adversarial Robustness via Randomized Smoothing","created":"2019-02-08","cited_by_count":1340},{"id":"1810.02340","title":"SNIP: Single-shot Network Pruning based on Connection Sensitivity","created":"2018-10-04","cited_by_count":812},{"id":"1309.5549","title":"Stochastic First- and Zeroth-order Methods for Nonconvex Stochastic Programming","created":"2013-09-22","cited_by_count":724},{"id":"1708.03999","title":"ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Models","created":"2017-08-14","cited_by_count":666},{"id":"2003.03033","title":"What is the State of Neural Network Pruning?","created":"2020-03-06","cited_by_count":583},{"id":"1804.08598","title":"Black-box Adversarial Attacks with Limited Queries and Information","created":"2018-04-23","cited_by_count":501},{"id":"2006.05467","title":"Pruning neural networks without any data by iteratively conserving synaptic flow","created":"2020-06-09","cited_by_count":479},{"id":"2002.07376","title":"Picking Winning Tickets Before Training by Preserving Gradient Flow","created":"2020-02-18","cited_by_count":471},{"id":"1910.01739","title":"Scalable Global Optimization via Local Bayesian Optimization","created":"2019-10-03","cited_by_count":374},{"id":"2305.17333","title":"Fine-Tuning Language Models with Just Forward Passes","created":"2023-05-27","cited_by_count":345},{"id":"2212.13345","title":"The Forward-Forward Algorithm: Some Preliminary Investigations","created":"2022-12-27","cited_by_count":266},{"id":"1804.08150","title":"Deep Learning in Spiking Neural Networks","created":"2018-04-22","cited_by_count":263},{"id":"2201.03514","title":"Black-Box Tuning for Language-Model-as-a-Service","created":"2022-01-10","cited_by_count":256},{"id":"1609.01596","title":"Direct Feedback Alignment Provides Learning in Deep Neural Networks","created":"2016-09-06","cited_by_count":240},{"id":"2007.00016","title":"Solver-in-the-Loop: Learning from Differentiable Physics to Interact with Iterative PDE-Solvers","created":"2020-06-30","cited_by_count":205},{"id":"1312.2139","title":"Optimal rates for zero-order convex optimization: the power of two function evaluations","created":"2013-12-07","cited_by_count":198},{"id":"2006.06224","title":"A Primer on Zeroth-Order Optimization in Signal Processing and Machine Learning","created":"2020-06-11","cited_by_count":162},{"id":"1807.07978","title":"Prior Convictions: Black-Box Adversarial Attacks with Bandits and Priors","created":"2018-07-20","cited_by_count":146},{"id":"1608.05343","title":"Decoupled Neural Interfaces using Synthetic Gradients","created":"2016-08-18","cited_by_count":137},{"id":"1805.11770","title":"AutoZOOM: Autoencoder-based Zeroth Order Optimization Method for Attacking Black-box Neural Networks","created":"2018-05-30","cited_by_count":137},{"id":"1901.06656","title":"Training Neural Networks with Local Error Signals","created":"2019-01-20","cited_by_count":136},{"id":"2001.07457","title":"Learning to Control PDEs with Differentiable Physics","created":"2020-01-21","cited_by_count":132},{"id":"1805.10367","title":"Zeroth-Order Stochastic Variance Reduction for Nonconvex Optimization","created":"2018-05-25","cited_by_count":111},{"id":"1810.01054","title":"ChainQueen: A Real-Time Differentiable Physical Simulator for Soft Robotics","created":"2018-10-02","cited_by_count":98},{"id":"2007.08714","title":"Transfer Learning without Knowing: Reprogramming Black-box Machine Learning Models with Scarce Data and Limited Resources","created":"2020-07-17","cited_by_count":83},{"id":"2202.08587","title":"Gradients without Backpropagation","created":"2022-02-17","cited_by_count":73},{"id":"2201.08531","title":"Black-box Prompt Learning for Pre-trained Language Models","created":"2022-01-21","cited_by_count":70},{"id":"1905.01332","title":"A Theoretical and Empirical Comparison of Gradient Approximations in Derivative-Free Optimization","created":"2019-05-03","cited_by_count":68},{"id":"2009.11094","title":"Sanity-Checking Pruning Methods: Random Tickets can Win the Jackpot","created":"2020-09-22","cited_by_count":66},{"id":"2210.03310","title":"Scaling Forward Gradient With Local Losses","created":"2022-10-07","cited_by_count":65},{"id":"1710.10551","title":"Stochastic Zeroth-order Optimization in High Dimensions","created":"2017-10-29","cited_by_count":63},{"id":"2106.09129","title":"A Winning Hand: Compressing Deep Networks Can Improve Out-Of-Distribution Robustness","created":"2021-06-16","cited_by_count":62},{"id":"2210.04092","title":"Advancing Model Pruning via Bi-level Optimization","created":"2022-10-08","cited_by_count":56},{"id":"2103.09377","title":"Multi-Prize Lottery Ticket Hypothesis: Finding Accurate Binary Neural Networks by Pruning A Randomly Weighted Network","created":"2021-03-17","cited_by_count":55},{"id":"2107.00166","title":"Sanity Checks for Lottery Tickets: Does Your Winning Ticket Really Win the Jackpot?","created":"2021-07-01","cited_by_count":52},{"id":"1411.0247","title":"Random feedback weights support learning in deep neural networks","created":"2014-11-02","cited_by_count":47},{"id":"2003.13001","title":"Zeroth-Order Regularized Optimization (ZORO): Approximately Sparse Gradients and Adaptive Sampling","created":"2020-03-29","cited_by_count":46},{"id":"2102.10707","title":"A Zeroth-Order Block Coordinate Descent Algorithm for Huge-Scale Black-Box Optimization","created":"2021-02-21","cited_by_count":46},{"id":"1606.00498","title":"A Comprehensive Linear Speedup Analysis for Asynchronous Stochastic Parallel Optimization from Zeroth-Order to First-Order","created":"2016-06-01","cited_by_count":44},{"id":"1906.00117","title":"Model Agnostic Contrastive Explanations for Structured Data","created":"2019-05-31","cited_by_count":41},{"id":"2203.14195","title":"How to Robustify Black-Box ML Models? A Zeroth-Order Optimization Perspective","created":"2022-03-27","cited_by_count":39},{"id":"2210.06640","title":"Compute-Efficient Deep Learning: Algorithmic Trends and Opportunities","created":"2022-10-13","cited_by_count":38},{"id":"1809.06474","title":"Zeroth-order Nonconvex Stochastic Optimization: Handling Constraints, High-Dimensionality and Saddle-Points","created":"2018-09-17","cited_by_count":37},{"id":"2107.05747","title":"SoftHebb: Bayesian Inference in Unsupervised Hebbian Soft Winner-Take-All Networks","created":"2021-07-12","cited_by_count":30},{"id":"2208.14197","title":"A Comprehensive Review of Digital Twin -- Part 1: Modeling and Twinning Enabling Technologies","created":"2022-08-26","cited_by_count":28},{"id":"1901.11503","title":"Contrasting Exploration in Parameter and Action Space: A Zeroth-Order Optimization Perspective","created":"2019-01-31","cited_by_count":27},{"id":"2012.11148","title":"Efficient On-Chip Learning for Optical Neural Networks Through Power-Aware Sparse Zeroth-Order Optimization","created":"2020-12-21","cited_by_count":24},{"id":"2107.10110","title":"On the Convergence of Prior-Guided Zeroth-Order Optimization Algorithms","created":"2021-07-21","cited_by_count":23},{"id":"1707.07113","title":"Adversarial Variational Optimization of Non-Differentiable Simulators","created":"2017-07-22","cited_by_count":22},{"id":"1710.07804","title":"Zeroth-Order Online Alternating Direction Method of Multipliers: Convergence Analysis and Applications","created":"2017-10-21","cited_by_count":22},{"id":"1907.11684","title":"On the Design of Black-box Adversarial Examples by Leveraging Gradient-free Optimization and Operator Splitting Method","created":"2019-07-26","cited_by_count":21},{"id":"2110.14807","title":"L2ight: Enabling On-Chip Learning for Optical Neural Networks via Efficient in-situ Subspace Optimization","created":"2021-10-27","cited_by_count":21},{"id":"2110.04743","title":"ZARTS: On Zero-order Optimization for Neural Architecture Search","created":"2021-10-10","cited_by_count":18},{"id":"1812.11377","title":"Hessian-Aware Zeroth-Order Optimization for Black-Box Adversarial Attack","created":"2018-12-29","cited_by_count":14},{"id":"2102.09026","title":"Optimizing Large-Scale Hyperparameters via Automated Learning Algorithm","created":"2021-02-17","cited_by_count":13},{"id":"2106.08453","title":"How to Train Your Wide Neural Network Without Backprop: An Input-Weight Alignment Perspective","created":"2021-06-15","cited_by_count":13},{"id":"2209.06302","title":"Optimization without Backpropagation","created":"2022-09-13","cited_by_count":11},{"id":"2304.06430","title":"Certified Zeroth-order Black-Box Defense with Robust UNet Denoiser","created":"2023-04-13","cited_by_count":11},{"id":"1910.05268","title":"Improving Gradient Estimation in Evolutionary Strategies With Past Descent Directions","created":"2019-10-11","cited_by_count":8},{"id":"2006.01759","title":"Sparse Perturbations for Improved Convergence in Stochastic Zeroth-Order Optimization","created":"2020-06-02","cited_by_count":8},{"id":"2304.11153","title":"Low-Variance Gradient Estimation in Unrolled Computation Graphs with ES-Single","created":"2023-04-21","cited_by_count":7},{"id":"2206.02785","title":"Zeroth-Order SciML: Non-intrusive Integration of Scientific Software with Deep Learning","created":"2022-06-04","cited_by_count":4},{"id":"1811.03733","title":"Universal Decision-Based Black-Box Perturbations: Breaking Security-Through-Obscurity Defenses","created":"2018-11-09","cited_by_count":3},{"id":"2206.02341","title":"Complex Locomotion Skill Learning via Differentiable Physics","created":"2022-06-06","cited_by_count":2}],"next_cursor":null}