Approximate Computing

Ask about this topic

Overview

Approximate computing studies how to save hardware and software resources by allowing controlled errors in calculations or representations. Common approaches include truncated or logarithmic multipliers, reduced precision, configurable arithmetic circuits, and compiler- or search-guided selection of approximations; retraining can help models recover accuracy. Work spans CNNs, vision transformers, graph neural networks, and edge devices, with evaluation on benchmarks such as CIFAR-10 and ImageNet and implementations on FPGAs, ASICs, and embedded processors. A central tension is that accuracy loss depends on the model and workload, while operation-count savings may not reduce total energy when memory access or other system costs dominate.

Latest papers

CardsList

22 papers2 papers in the last four weeks, down 33% on the four weeks before. 0.0% of all new papers.

  1. SETAREH Transform: A Sorting-Assisted Haar-Wavelet Sparsification Method for Approximate Inner-Product Computation

    Oct 16, 2026Seyed Kamaledin SetarehdanApproximate ComputingWavelet Methods

    Control and Intelligent Processing Centre of Excellence, School of Electrical and Computer Engineering, College of Engineering, University of Tehran, Tehran, Iran

  2. Co-Optimizing Graph Sparsification and Approximate Computing for Energy-Efficient FPGA-Based GCN Inference

    Oct 5, 2026Nathaniel Kaye Mellor, Shreejith Shanker, George FlorosEdge ComputingGraph Sparsification

    Department of Electronic and Electrical Engineering, Trinity College Dublin, Ireland

  3. FAME: An FPGA-Based Platform for Approximate Multipliers Evaluation with Pattern-Guided DNN Retraining

    Sep 15, 2026Rappy Saha, Nima Amirafshar, Jude Haris +2FPGA-Based Neural Network AccelerationApproximate Computing

    University of Glasgow, UK · Heidelberg University, Germany

  4. GaLe: memory-efficient Global Approximate and Local Exact features

    Sep 2, 2026Alberto Ancilotto, Elisabetta FarellaMemory-Efficient InferenceEdge AI

    Fondazione Bruno Kessler (FBK), Trento, Italy

  5. CircuitsDNA: Discovering Unconventional Multi-Accuracy Arithmetic Circuits via Evolutionary Synthesis

    Sep 1, 2026Ruichen Qi, Junyi Luo, Xinting Jiang +5Efficient Neural Network InferenceApproximate Computing

    Brown University · Google · University of Michigan

  6. Precision-Aware Variable Bit Processing Elements for Hardware-Efficient Systolic Array Designs

    Aug 23, 2026Dantu Nandini Devi, Madhav RaoApproximate ComputingAI Accelerator Inference

    Department of Electronics & Communication Engineering, IIIT-Bangalore, Karnataka, India

  7. CurveFP: Co-Designing Numerical Representation and Product Arithmetic for Language Models

    Aug 8, 2026Ye QiaoLLM QuantizationLow-Bit Quantization

    Department of Electrical Engineering and Computer Science University of California, Irvine Irvine, CA, USA

  8. Toward Energy-Efficient and Low-Power Arrhythmia Detection for Wearable Devices

    Jul 16, 2026Floriaan Bulten, Yawar Rasheed, Arlene John +2Energy-Efficient MLElectrocardiogram Classification

    Computer Architecture for Embedded Systems, University of Twente, The Netherlands · Biomedical Signals and Systems, University of Twente, The Netherlands · Faculty of Science, Computer Science, Vrije Universiteit Amsterdam, The Netherlands

  9. Harvesting AI Computation at the Edge via Generic Approximation

    Jun 28, 2026Yihan Wang, Huiru Yan, Luxin Zhang +6Edge ComputingApproximate Computing

    Institute of Computing Technology (ICT), Chinese Academy of Sciences (CAS), Beijing 100190, China · North China Electric Power University, Beijing 102206, China

  10. Compiler-Driven Approximation Tuning for Hyperdimensional Computing

    Jun 25, 2026Xavier Routh, Abdul Rafae Noor, Akash Kothari +4Compiler OptimizationHyperdimensional Computing

    University of Illinois Urbana-Champaign Urbana, IL, USA · University of California San Diego La Jolla, CA, USA

  11. Multi-Objective Coevolution of Prompts and Templates for Circuit Approximation

    Jun 11, 2026Martin Tomasovic, Lukas SekaninaMulti-Objective Evolutionary OptimizationLarge Language Model-Guided Optimization

    Brno University of Technology, Faculty of Information Technology Brno, Czech Republic

  12. SPARX: Secure and Privacy-Aware Approximate CNN Acceleration with Edge RISC-V SoC

    Jun 8, 2026Sonu Kumar, Akash Sankhe, Mukul Lokhande +1Edge InferencePrivacy-Preserving ML

    Centre for Advanced Electronics · Dept. of Electrical Engineering

  13. Genetic Programming with Transformer-Based Mutation for Approximate Circuit Design

    May 20, 2026Ondrej Galeta, Lukas SekaninaElectronic Design AutomationGenetic Programming

    Brno University of Technology, Faculty of Information Technology, Brno, Czech Republic

  14. A Reconfigurable Multiplier Architecture for Error-Resilient Applications in RISC-V Core

    May 9, 2026Pragun Jaswal, L. Hemanth Krishna, B. SrinivasuEfficient Neural Network InferenceEnergy-Efficient ML

    Indian Institute of Technology Mandi, Mandi–175005, India

  15. CARMEN: CORDIC-Accelerated Resource-Efficient Multi-Precision Inference Engine for Deep Learning

    May 7, 2026Sonu Kumar, Mukul Lokhande, Santosh Kumar Vishvakarma +1Efficient Neural Network InferenceEnergy-Efficient ML

    Dept. of Electrical Engineering Indian Institute of Technology Indore Simrol 453552, Indore, India · EnICS Labs Bar-Ilan University Ramat Gan, Israel

  16. EULER-ADAS: Energy-Efficient & SIMD-Unified Logarithmic-Posit Engine for Precision-Reconfigurable Approximate ADAS Acceleration

    May 7, 2026Mukul Lokhande, Ratko Pilipovic, Omkar Kokane +2Energy-Efficient MLFPGA-Based Neural Network Acceleration

    NSDCS Research Group, Dept. of Electrical Engineering, Indian Institute of Technology Indore, Indore, India · Faculty of Computer and Information Science, University of Ljubljana, Ljubljana, Slovenia · EnICS Labs, Bar-Ilan Univ., Ramat Gan 5290002, Israel

  17. TRAM: Training Approximate Multiplier Structures for Low-Power AI Accelerators

    May 6, 2026Chang Meng, Hanyu Wang, Yuyang Ye +3AI Accelerator InferenceEnergy-Efficient ML

    Eindhoven University of Technology Eindhoven, The Netherlands · University of California, Los Angeles Los Angeles, USA · Chinese University of Hong Kong Hong Kong, China +2

  18. AxMoE: Characterizing the Impact of Approximate Multipliers on Mixture-of-Experts DNN Architectures

    May 6, 2026Omkar B Shende, Marcello Traiola, Gayathri AnanthanarayananEfficient Neural Network InferenceEdge Inference

    Dept. of Computer Science and Engineering · Univ Rennes, CNRS, Inria, IRISA

  19. OpenACMv2: An Accuracy-Constrained Co-Optimization Framework for Approximate DCiM

    Mar 13, 2026Yiqi Zhou, Yue Yuan, Yikai Wang +8Compute-in-MemoryApproximate Computing

    Nanjing University of Science and Technology, China · Shenzhen University, China · Beihang University, China +2

  20. Hardware Efficient Approximate Convolution with Tunable Error Tolerance for CNNs

    Mar 10, 2026Vishal Shashidhar, Anupam Kumari, Roy P PailyEfficient Neural Network InferenceNeural Network Hardware Acceleration

    Department of Electronics and Electrical Engineering, Indian Institute of Technology Guwahati

  21. HAWX: A Hardware-Aware FrameWork for Fast and Scalable ApproXimation of DNNs

    Feb 18, 2026Samira Nazari, Mohammad Saeed Almasi, Mahdi Taheri +4Neural Network Hardware AccelerationNeural Network Optimization

    University of Zanjan, Zanjan, Iran · Brandenburg Technical University, Cottbus, Germany · Tallinn University of Technology, Tallinn, Estonia +1

  22. PhD Thesis Summary: Methods for Reliability Assessment and Enhancement of Deep Neural Network Hardware Accelerators

    Feb 17, 2026Mahdi TaheriApproximate Computing

    Tallinn University of Technology, Tallinn, Estonia