{"list":"other","total":57,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"1602.05629","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","created":"2016-02-17","cited_by_count":7669},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"1708.07747","title":"Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms","created":"2017-08-25","cited_by_count":4349},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"1912.04977","title":"Advances and Open Problems in Federated Learning","created":"2019-12-10","cited_by_count":3046},{"id":"1905.10044","title":"BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions","created":"2019-05-24","cited_by_count":2183},{"id":"1508.05326","title":"A large annotated corpus for learning natural language inference","created":"2015-08-21","cited_by_count":1847},{"id":"2110.08207","title":"Multitask Prompted Training Enables Zero-Shot Task Generalization","created":"2021-10-15","cited_by_count":1470},{"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":"1810.05270","title":"Rethinking the Value of Network Pruning","created":"2018-10-11","cited_by_count":599},{"id":"1802.04434","title":"signSGD: Compressed Optimisation for Non-Convex Problems","created":"2018-02-13","cited_by_count":571},{"id":"1809.07599","title":"Sparsified SGD with Memory","created":"2018-09-20","cited_by_count":376},{"id":"1808.09121","title":"WiC: the Word-in-Context Dataset for Evaluating Context-Sensitive Meaning Representations","created":"2018-08-28","cited_by_count":372},{"id":"1909.13014","title":"FedPAQ: A Communication-Efficient Federated Learning Method with Periodic Averaging and Quantization","created":"2019-09-28","cited_by_count":356},{"id":"2305.17333","title":"Fine-Tuning Language Models with Just Forward Passes","created":"2023-05-27","cited_by_count":345},{"id":"2107.06917","title":"A Field Guide to Federated Optimization","created":"2021-07-14","cited_by_count":315},{"id":"1901.10159","title":"An Investigation into Neural Net Optimization via Hessian Eigenvalue Density","created":"2019-01-29","cited_by_count":292},{"id":"1912.07145","title":"PyHessian: Neural Networks Through the Lens of the Hessian","created":"2019-12-16","cited_by_count":292},{"id":"1905.13727","title":"PowerSGD: Practical Low-Rank Gradient Compression for Distributed Optimization","created":"2019-05-31","cited_by_count":238},{"id":"1810.01075","title":"Implicit Self-Regularization in Deep Neural Networks: Evidence from Random Matrix Theory and Implications for Learning","created":"2018-10-02","cited_by_count":215},{"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":"2007.01154","title":"Federated Learning with Compression: Unified Analysis and Sharp Guarantees","created":"2020-07-02","cited_by_count":160},{"id":"2402.11592","title":"Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark","created":"2024-02-18","cited_by_count":114},{"id":"1805.10367","title":"Zeroth-Order Stochastic Variance Reduction for Nonconvex Optimization","created":"2018-05-25","cited_by_count":111},{"id":"2308.08165","title":"Stochastic Controlled Averaging for Federated Learning with Communication Compression","created":"2023-08-16","cited_by_count":101},{"id":"2008.11865","title":"Traces of Class/Cross-Class Structure Pervade Deep Learning Spectra","created":"2020-08-27","cited_by_count":94},{"id":"2001.04756","title":"Adaptive Gradient Sparsification for Efficient Federated Learning: An Online Learning Approach","created":"2020-01-14","cited_by_count":81},{"id":"1910.06513","title":"ZO-AdaMM: Zeroth-Order Adaptive Momentum Method for Black-Box Optimization","created":"2019-10-15","cited_by_count":76},{"id":"2104.01776","title":"Federated Learning Meets Blockchain in Edge Computing: Opportunities and Challenges","created":"2021-04-05","cited_by_count":76},{"id":"2310.02025","title":"DeepZero: Scaling up Zeroth-Order Optimization for Deep Model Training","created":"2023-10-03","cited_by_count":76},{"id":"2312.11420","title":"Tuning LayerNorm in Attention: Towards Efficient Multi-Modal LLM Finetuning","created":"2023-12-18","cited_by_count":64},{"id":"2102.04487","title":"Adaptive Quantization of Model Updates for Communication-Efficient Federated Learning","created":"2021-02-08","cited_by_count":63},{"id":"2201.09531","title":"Communication-Efficient Stochastic Zeroth-Order Optimization for Federated Learning","created":"2022-01-24","cited_by_count":59},{"id":"1911.08772","title":"Understanding Top-k Sparsification in Distributed Deep Learning","created":"2019-11-20","cited_by_count":56},{"id":"2205.02719","title":"Communication-Efficient Adaptive Federated Learning","created":"2022-05-05","cited_by_count":55},{"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":"2010.04261","title":"Dissecting Hessian: Understanding Common Structure of Hessian in Neural Networks","created":"2020-10-08","cited_by_count":45},{"id":"2111.00465","title":"DAdaQuant: Doubly-adaptive quantization for communication-efficient Federated Learning","created":"2021-10-31","cited_by_count":41},{"id":"2007.15197","title":"Communication-Efficient Federated Learning via Optimal Client Sampling","created":"2020-07-30","cited_by_count":39},{"id":"1912.09135","title":"Distributed Reinforcement Learning for Decentralized Linear Quadratic Control: A Derivative-Free Policy Optimization Approach","created":"2019-12-19","cited_by_count":38},{"id":"2004.13831","title":"A Review of Winograd Schema Challenge Datasets and Approaches","created":"2020-04-23","cited_by_count":27},{"id":"2101.08837","title":"Time-Correlated Sparsification for Communication-Efficient Federated Learning","created":"2021-01-21","cited_by_count":26},{"id":"2402.05926","title":"On the Convergence of Zeroth-Order Federated Tuning for Large Language Models","created":"2024-02-08","cited_by_count":19},{"id":"2203.05878","title":"Wireless Quantized Federated Learning: A Joint Computation and Communication Design","created":"2022-03-11","cited_by_count":15},{"id":"2212.08272","title":"Communication-Efficient Federated Learning for Heterogeneous Edge Devices Based on Adaptive Gradient Quantization","created":"2022-12-16","cited_by_count":14},{"id":"2206.10032","title":"Communication-Efficient Federated Learning With Data and Client Heterogeneity","created":"2022-06-20","cited_by_count":9},{"id":"2106.07155","title":"CFedAvg: Achieving Efficient Communication and Fast Convergence in Non-IID Federated Learning","created":"2021-06-14","cited_by_count":7},{"id":"2403.09904","title":"FedComLoc: Communication-Efficient Distributed Training of Sparse and Quantized Models","created":"2024-03-14","cited_by_count":5},{"id":"2107.12416","title":"Asynchronous Distributed Reinforcement Learning for LQR Control via Zeroth-Order Block Coordinate Descent","created":"2021-07-26","cited_by_count":4},{"id":"2309.13307","title":"CORE: Common Random Reconstruction for Distributed Optimization with Provable Low Communication Complexity","created":"2023-09-23","cited_by_count":1}],"next_cursor":null}