{"list":"other","total":59,"rows":[{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"2103.13630","title":"A Survey of Quantization Methods for Efficient Neural Network Inference","created":"2021-03-25","cited_by_count":815},{"id":"1708.08987","title":"Deep Learning for Medical Image Analysis","created":"2017-08-17","cited_by_count":401},{"id":"1610.00633","title":"Deep Reinforcement Learning for Robotic Manipulation with Asynchronous Off-Policy Updates","created":"2016-10-03","cited_by_count":353},{"id":"1802.05799","title":"Horovod: fast and easy distributed deep learning in TensorFlow","created":"2018-02-15","cited_by_count":279},{"id":"2101.09671","title":"Pruning and Quantization for Deep Neural Network Acceleration: A Survey","created":"2021-01-24","cited_by_count":263},{"id":"1612.03079","title":"Clipper: A Low-Latency Online Prediction Serving System","created":"2016-12-09","cited_by_count":191},{"id":"1912.09789","title":"A Survey on Distributed Machine Learning","created":"2019-12-20","cited_by_count":188},{"id":"2006.02464","title":"Serving DNNs like Clockwork: Performance Predictability from the Bottom Up","created":"2020-06-03","cited_by_count":120},{"id":"1712.06139","title":"TensorFlow-Serving: Flexible, High-Performance ML Serving","created":"2017-12-17","cited_by_count":85},{"id":"1901.05758","title":"Analysis of Large-Scale Multi-Tenant GPU Clusters for DNN Training Workloads","created":"2019-01-17","cited_by_count":79},{"id":"2008.12260","title":"Pollux: Co-adaptive Cluster Scheduling for Goodput-Optimized Deep Learning","created":"2020-08-27","cited_by_count":72},{"id":"1706.03292","title":"Poseidon: An Efficient Communication Architecture for Distributed Deep Learning on GPU Clusters","created":"2017-06-11","cited_by_count":57},{"id":"2008.09213","title":"Heterogeneity-Aware Cluster Scheduling Policies for Deep Learning Workloads","created":"2020-08-20","cited_by_count":56},{"id":"2001.02772","title":"DeepRecSys: A System for Optimizing End-To-End At-scale Neural Recommendation Inference","created":"2020-01-08","cited_by_count":54},{"id":"1907.01484","title":"Themis: Fair and Efficient GPU Cluster Scheduling","created":"2019-07-02","cited_by_count":43},{"id":"1903.11314","title":"Scalable Deep Learning on Distributed Infrastructures: Challenges, Techniques and Tools","created":"2019-03-27","cited_by_count":40},{"id":"1811.09886","title":"Deep Learning Inference in Facebook Data Centers: Characterization, Performance Optimizations and Hardware Implications","created":"2018-11-24","cited_by_count":36},{"id":"1804.06087","title":"Rafiki: Machine Learning as an Analytics Service System","created":"2018-04-17","cited_by_count":33},{"id":"2109.01313","title":"Characterization and Prediction of Deep Learning Workloads in Large-Scale GPU Datacenters","created":"2021-09-03","cited_by_count":31},{"id":"1810.06115","title":"PRETZEL: Opening the Black Box of Machine Learning Prediction Serving Systems","created":"2018-10-14","cited_by_count":22},{"id":"2005.05968","title":"Centaur: A Chiplet-based, Hybrid Sparse-Dense Accelerator for Personalized Recommendations","created":"2020-05-12","cited_by_count":21},{"id":"2011.01302","title":"IOS: Inter-Operator Scheduler for CNN Acceleration","created":"2020-11-02","cited_by_count":20},{"id":"1708.07308","title":"Ease.ml: Towards Multi-tenant Resource Sharing for Machine Learning Workloads","created":"2017-08-24","cited_by_count":16},{"id":"1909.06040","title":"DL2: A Deep Learning-driven Scheduler for Deep Learning Clusters","created":"2019-09-13","cited_by_count":14},{"id":"2110.11927","title":"Solving Large-Scale Granular Resource Allocation Problems Efficiently with POP","created":"2021-10-22","cited_by_count":13},{"id":"2201.01684","title":"Dynamic GPU Energy Optimization for Machine Learning Training Workloads","created":"2022-01-05","cited_by_count":12},{"id":"1901.00041","title":"Dynamic Space-Time Scheduling for GPU Inference","created":"2018-12-31","cited_by_count":11},{"id":"1910.05930","title":"Characterizing Deep Learning Training Workloads on Alibaba-PAI","created":"2019-10-14","cited_by_count":11},{"id":"2007.13005","title":"Jointly Optimizing Preprocessing and Inference for DNN-based Visual Analytics","created":"2020-07-25","cited_by_count":11},{"id":"1909.01502","title":"Privacy Accounting and Quality Control in the Sage Differentially Private ML Platform","created":"2019-09-04","cited_by_count":10},{"id":"2106.01674","title":"JIZHI: A Fast and Cost-Effective Model-As-A-Service System for Web-Scale Online Inference at Baidu","created":"2021-06-03","cited_by_count":10},{"id":"1710.08460","title":"Serving deep learning models in a serverless platform","created":"2017-10-23","cited_by_count":9},{"id":"1801.00936","title":"Online Job Scheduling in Distributed Machine Learning Clusters","created":"2018-01-03","cited_by_count":9},{"id":"1906.11307","title":"One Size Does Not Fit All: Quantifying and Exposing the Accuracy-Latency Trade-off in Machine Learning Cloud Service APIs via Tolerance Tiers","created":"2019-06-26","cited_by_count":7},{"id":"2108.03645","title":"Online Evolutionary Batch Size Orchestration for Scheduling Deep Learning Workloads in GPU Clusters","created":"2021-08-08","cited_by_count":7},{"id":"2109.11067","title":"Serving DNN Models with Multi-Instance GPUs: A Case of the Reconfigurable Machine Scheduling Problem","created":"2021-09-18","cited_by_count":7},{"id":"2203.09040","title":"A Survey of Multi-Tenant Deep Learning Inference on GPU","created":"2022-03-17","cited_by_count":7},{"id":"1904.01576","title":"BARISTA: Efficient and Scalable Serverless Serving System for Deep Learning Prediction Services","created":"2019-04-02","cited_by_count":6},{"id":"2001.02338","title":"HyperSched: Dynamic Resource Reallocation for Model Development on a Deadline","created":"2020-01-08","cited_by_count":6},{"id":"1912.02322","title":"Perseus: Characterizing Performance and Cost of Multi-Tenant Serving for CNN Models","created":"2019-12-05","cited_by_count":5},{"id":"2006.05117","title":"Hysia: Serving DNN-Based Video-to-Retail Applications in Cloud","created":"2020-06-09","cited_by_count":5},{"id":"2105.13855","title":"A Sum-of-Ratios Multi-Dimensional-Knapsack Decomposition for DNN Resource Scheduling","created":"2021-05-28","cited_by_count":5},{"id":"2111.14247","title":"A Survey of Large-Scale Deep Learning Serving System Optimization: Challenges and Opportunities","created":"2021-11-28","cited_by_count":5},{"id":"1811.09732","title":"TrIMS: Transparent and Isolated Model Sharing for Low Latency Deep LearningInference in Function as a Service Environments","created":"2018-11-24","cited_by_count":4},{"id":"1909.06526","title":"FfDL : A Flexible Multi-tenant Deep Learning Platform","created":"2019-09-14","cited_by_count":4},{"id":"2006.13878","title":"Effective Elastic Scaling of Deep Learning Workloads","created":"2020-06-24","cited_by_count":4},{"id":"2106.15335","title":"Privacy Budget Scheduling","created":"2021-06-29","cited_by_count":4},{"id":"2202.01158","title":"GADGET: Online Resource Optimization for Scheduling Ring-All-Reduce Learning Jobs","created":"2022-02-02","cited_by_count":4},{"id":"1710.08731","title":"HPC Cloud for Scientific and Business Applications: Taxonomy, Vision, and Research Challenges","created":"2017-10-24","cited_by_count":3},{"id":"2002.02885","title":"Understanding and Optimizing Packed Neural Network Training for Hyper-Parameter Tuning","created":"2020-02-07","cited_by_count":3},{"id":"2002.10105","title":"Communication Contention Aware Scheduling of Multiple Deep Learning Training Jobs","created":"2020-02-24","cited_by_count":3},{"id":"2104.00486","title":"Energy-aware Task Scheduling with Deadline Constraint in DVFS-enabled Heterogeneous Clusters","created":"2021-04-01","cited_by_count":2},{"id":"2105.05080","title":"ANDREAS: Artificial intelligence traiNing scheDuler foR accElerAted resource clusterS","created":"2021-05-11","cited_by_count":2},{"id":"2111.10672","title":"Doing More by Doing Less: How Structured Partial Backpropagation Improves Deep Learning Clusters","created":"2021-11-20","cited_by_count":2},{"id":"1704.06738","title":"Towards Distributed Machine Learning in Shared Clusters: A Dynamically-Partitioned Approach","created":"2017-04-22","cited_by_count":1},{"id":"1705.03102","title":"Scalable System Scheduling for HPC and Big Data","created":"2017-05-08","cited_by_count":1},{"id":"2106.05345","title":"Cocktail: Leveraging Ensemble Learning for Optimized Model Serving in Public Cloud","created":"2021-06-09","cited_by_count":1}],"next_cursor":null}