{"list":"other","total":68,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2106.01946","title":"Convex optimization","created":"2021-06-03","cited_by_count":2515},{"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":"1609.04747","title":"An overview of gradient descent optimization algorithms","created":"2016-09-15","cited_by_count":1033},{"id":"1705.09056","title":"Can Decentralized Algorithms Outperform Centralized Algorithms? A Case Study for Decentralized Parallel Stochastic Gradient Descent","created":"2017-05-25","cited_by_count":502},{"id":"1809.07599","title":"Sparsified SGD with Memory","created":"2018-09-20","cited_by_count":376},{"id":"1807.06629","title":"Parallel Restarted SGD with Faster Convergence and Less Communication: Demystifying Why Model Averaging Works for Deep Learning","created":"2018-07-17","cited_by_count":278},{"id":"1612.07119","title":"FINN: A Framework for Fast, Scalable Binarized Neural Network Inference","created":"2016-12-01","cited_by_count":150},{"id":"2010.05627","title":"Towards Theoretically Understanding Why SGD Generalizes Better Than ADAM in Deep Learning","created":"2020-10-12","cited_by_count":126},{"id":"2007.00072","title":"Data Movement Is All You Need: A Case Study on Optimizing Transformers","created":"2020-06-30","cited_by_count":108},{"id":"1708.01012","title":"On the convergence properties of a $K$-step averaging stochastic gradient descent algorithm for nonconvex optimization","created":"2017-08-03","cited_by_count":92},{"id":"2305.13230","title":"To Repeat or Not To Repeat: Insights from Scaling LLM under Token-Crisis","created":"2023-05-22","cited_by_count":92},{"id":"2306.11987","title":"Training Transformers with 4-bit Integers","created":"2023-06-21","cited_by_count":60},{"id":"1912.12953","title":"RecNMP: Accelerating Personalized Recommendation with Near-Memory Processing","created":"2019-12-30","cited_by_count":49},{"id":"1701.03961","title":"Communication-Efficient Algorithms for Decentralized and Stochastic Optimization","created":"2017-01-14","cited_by_count":43},{"id":"1908.03072","title":"TensorDIMM: A Practical Near-Memory Processing Architecture for Embeddings and Tensor Operations in Deep Learning","created":"2019-08-08","cited_by_count":43},{"id":"2008.03911","title":"A Survey on Large-scale Machine Learning","created":"2020-08-10","cited_by_count":35},{"id":"1606.07365","title":"Parallel SGD: When does averaging help?","created":"2016-06-23","cited_by_count":32},{"id":"2012.03112","title":"A Modern Primer on Processing in Memory","created":"2020-12-05","cited_by_count":32},{"id":"2109.14320","title":"Google Neural Network Models for Edge Devices: Analyzing and Mitigating Machine Learning Inference Bottlenecks","created":"2021-09-29","cited_by_count":23},{"id":"1903.03988","title":"Processing Data Where It Makes Sense: Enabling In-Memory Computation","created":"2019-03-10","cited_by_count":21},{"id":"2210.11948","title":"lo-fi: distributed fine-tuning without communication","created":"2022-10-19","cited_by_count":19},{"id":"2104.05245","title":"Distributed Learning Systems with First-order Methods","created":"2021-04-12","cited_by_count":17},{"id":"2104.07582","title":"SISA: Set-Centric Instruction Set Architecture for Graph Mining on Processing-in-Memory Systems","created":"2021-04-15","cited_by_count":17},{"id":"2105.07806","title":"Towards Demystifying Serverless Machine Learning Training","created":"2021-05-17","cited_by_count":16},{"id":"2308.00846","title":"Pathfinding Future PIM Architectures by Demystifying a Commercial PIM Technology","created":"2023-08-01","cited_by_count":14},{"id":"2110.01709","title":"Benchmarking Memory-Centric Computing Systems: Analysis of Real Processing-in-Memory Hardware","created":"2021-10-04","cited_by_count":13},{"id":"1702.06269","title":"Memory and Communication Efficient Distributed Stochastic Optimization with Minibatch-Prox","created":"2017-02-21","cited_by_count":12},{"id":"1711.01177","title":"GRIM-Filter: Fast Seed Location Filtering in DNA Read Mapping Using Processing-in-Memory Technologies","created":"2017-11-02","cited_by_count":11},{"id":"2010.02079","title":"NATSA: A Near-Data Processing Accelerator for Time Series Analysis","created":"2020-10-05","cited_by_count":10},{"id":"2102.07511","title":"GradPIM: A Practical Processing-in-DRAM Architecture for Gradient Descent","created":"2021-02-15","cited_by_count":10},{"id":"2105.03725","title":"DAMOV: A New Methodology and Benchmark Suite for Evaluating Data Movement Bottlenecks","created":"2021-05-08","cited_by_count":10},{"id":"2009.07692","title":"GenASM: A High-Performance, Low-Power Approximate String Matching Acceleration Framework for Genome Sequence Analysis","created":"2020-09-16","cited_by_count":9},{"id":"2101.07557","title":"SynCron: Efficient Synchronization Support for Near-Data-Processing Architectures","created":"2021-01-19","cited_by_count":9},{"id":"2009.08241","title":"NERO: A Near High-Bandwidth Memory Stencil Accelerator for Weather Prediction Modeling","created":"2020-09-17","cited_by_count":8},{"id":"2310.09385","title":"PIM-GPT: A Hybrid Process-in-Memory Accelerator for Autoregressive Transformers","created":"2023-10-13","cited_by_count":8},{"id":"2401.14428","title":"The Landscape of Compute-near-memory and Compute-in-memory: A Research and Commercial Overview","created":"2024-01-24","cited_by_count":8},{"id":"2005.01988","title":"One-step regression and classification with crosspoint resistive memory arrays","created":"2020-05-05","cited_by_count":7},{"id":"1611.09988","title":"Buddy-RAM: Improving the Performance and Efficiency of Bulk Bitwise Operations Using DRAM","created":"2016-11-30","cited_by_count":6},{"id":"1701.06420","title":"Neurostream: Scalable and Energy Efficient Deep Learning with Smart Memory Cubes","created":"2017-01-23","cited_by_count":6},{"id":"2104.07699","title":"pLUTo: Enabling Massively Parallel Computation in DRAM via Lookup Tables","created":"2021-04-15","cited_by_count":6},{"id":"1803.04783","title":"A Scalable Near-Memory Architecture for Training Deep Neural Networks on Large In-Memory Datasets","created":"2018-02-19","cited_by_count":5},{"id":"2012.12381","title":"Intelligent Architectures for Intelligent Computing Systems","created":"2020-12-22","cited_by_count":5},{"id":"2103.00798","title":"Polynesia: Enabling Effective Hybrid Transactional/Analytical Databases with Specialized Hardware/Software Co-Design","created":"2021-03-01","cited_by_count":5},{"id":"2112.14216","title":"Casper: Accelerating Stencil Computation using Near-cache Processing","created":"2021-12-28","cited_by_count":5},{"id":"2208.01243","title":"A Framework for High-throughput Sequence Alignment using Real Processing-in-Memory Systems","created":"2022-08-02","cited_by_count":5},{"id":"2301.07486","title":"CINM (Cinnamon): A Compilation Infrastructure for Heterogeneous Compute In-Memory and Compute Near-Memory Paradigms","created":"2022-12-25","cited_by_count":5},{"id":"2310.01893","title":"SimplePIM: A Software Framework for Productive and Efficient Processing-in-Memory","created":"2023-10-03","cited_by_count":5},{"id":"1403.7550","title":"DimmWitted: A Study of Main-Memory Statistical Analytics","created":"2014-03-28","cited_by_count":4},{"id":"1803.06333","title":"Snap ML: A Hierarchical Framework for Machine Learning","created":"2018-03-16","cited_by_count":4},{"id":"2111.00082","title":"PiDRAM: A Holistic End-to-end FPGA-based Framework for Processing-in-DRAM","created":"2021-10-29","cited_by_count":4},{"id":"2206.06022","title":"Machine Learning Training on a Real Processing-in-Memory System","created":"2022-06-13","cited_by_count":4},{"id":"1812.11473","title":"ORIGAMI: A Heterogeneous Split Architecture for In-Memory Acceleration of Learning","created":"2018-12-30","cited_by_count":3},{"id":"2209.08600","title":"GenPIP: In-Memory Acceleration of Genome Analysis via Tight Integration of Basecalling and Read Mapping","created":"2022-09-18","cited_by_count":3},{"id":"2402.16731","title":"PyGim: An Efficient Graph Neural Network Library for Real Processing-In-Memory Architectures","created":"2024-02-26","cited_by_count":3},{"id":"2402.18736","title":"Functionally-Complete Boolean Logic in Real DRAM Chips: Experimental Characterization and Analysis","created":"2024-02-28","cited_by_count":3},{"id":"1903.03404","title":"Accelerating Generalized Linear Models with MLWeaving: A One-Size-Fits-All System for Any-precision Learning (Technical Report)","created":"2019-03-08","cited_by_count":2},{"id":"1905.04376","title":"Enabling Practical Processing in and near Memory for Data-Intensive Computing","created":"2019-05-02","cited_by_count":2},{"id":"2207.07886","title":"An Experimental Evaluation of Machine Learning Training on a Real Processing-in-Memory System","created":"2022-07-16","cited_by_count":2},{"id":"1605.06483","title":"Simple DRAM and Virtual Memory Abstractions to Enable Highly Efficient Memory Systems","created":"2016-05-20","cited_by_count":1},{"id":"1712.08304","title":"Understanding and Improving the Latency of DRAM-Based Memory Systems","created":"2017-12-22","cited_by_count":1},{"id":"2105.12839","title":"SIMDRAM: An End-to-End Framework for Bit-Serial SIMD Computing in DRAM","created":"2021-05-26","cited_by_count":1},{"id":"2205.14664","title":"Heterogeneous Data-Centric Architectures for Modern Data-Intensive Applications: Case Studies in Machine Learning and Databases","created":"2022-05-29","cited_by_count":1},{"id":"2212.06292","title":"ALP: Alleviating CPU-Memory Data Movement Overheads in Memory-Centric Systems","created":"2022-12-13","cited_by_count":1},{"id":"2309.06545","title":"Evaluating Homomorphic Operations on a Real-World Processing-In-Memory System","created":"2023-09-12","cited_by_count":1},{"id":"2310.04366","title":"Swordfish: A Framework for Evaluating Deep Neural Network-based Basecalling using Computation-In-Memory with Non-Ideal Memristors","created":"2023-10-06","cited_by_count":1},{"id":"2310.10168","title":"DaPPA: A Data-Parallel Programming Framework for Processing-in-Memory Architectures","created":"2023-10-16","cited_by_count":1}],"next_cursor":null}