Straight-Through Estimator

Ask about this topic

Latest papers

CardsList

11 papers2 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

  1. Q-MINO: A Minimal-Norm Method for Quantization-Aware Training

    Sep 30, 2026Don LiStraight-Through EstimatorQuantization-Aware Training

    Department of Mathematics & Statistics Portland State University

  2. StableVQ: Practical Guidelines for Stable Vector-Quantized Tokenizer Training

    Sep 22, 2026Bao Tang, Jiahao Guo, Haoxiang Cao +4Straight-Through EstimatorVector Quantization

    Huazhong University of Science and Technology · KlingAI Research · South China Normal University

  3. Stability and Generalization of Straight-Through Estimators for Training Two-Layer Quantized Neural Networks

    Sep 6, 2026Yiming YingStraight-Through EstimatorNeural Network Generalization

    School of Mathematics and Statistics University of Sydney

  4. Propensity Straight-Through Gradients for Discrete Stochastic Systems

    Aug 26, 2026Jose M. G. Vilar, Leonor SaizStraight-Through EstimatorMarkov Chains

    Biofisika Institute (CSIC, UPV/EHU), University of the Basque Country, P.O. Box 644, 48080 Bilbao, Spain · IKERBASQUE, Basque Foundation for Science, 48011 Bilbao, Spain · Department of Biomedical Engineering, University of California, 451 East Health Sciences Drive, Davis, CA 95616, USA

  5. Layerwise Progressive Freezing: A Training Scaffold for Depth-Scalable Binary Networks

    Jun 26, 2026Evan Gibson Smith, Bashima IslamStraight-Through EstimatorBinary Neural Networks

    Worcester Polytechnic Institute

  6. Understanding Quantization-Aware Training: Gradients at Quantized Weights Bias to the Low-Loss Basin

    Jun 8, 2026Hanyang Li, Jianhao Ma, Ying CuiNeural Network OptimizationStraight-Through Estimator

    Department of IEOR, University of California, Berkeley · Department of Statistics and Data Science, University of Pennsylvania

  7. Gradient estimators for parameter inference in discrete stochastic kinetic models

    Apr 2, 2026Ludwig Burger, Annalena Kofler, Lukas Heinrich +1Straight-Through EstimatorParameter Estimation

    Physics of Complex Biosystems, School of Natural Sciences, James-Franck-Straße 1, 85748 Garching, Germany · Max Planck Institute for Intelligent Systems, Max-Planck-Ring 4, 72076 Tübingen, Germany · Max Planck Institute for Gravitational Physics (Albert Einstein Institute), Am Mühlenberg 1, 14476 Potsdam, Germany +2

  8. Learning Tree-Based Models with Gradient Descent

    Mar 11, 2026Sascha MartonStraight-Through EstimatorDecision Tree Learning

    UNIVERSITY OF MANNHEIM

  9. SoftJAX & SoftTorch: Empowering Automatic Differentiation Libraries with Informative Gradients

    Mar 9, 2026Anselm Paulus, A. René Geist, Vít Musil +3Straight-Through EstimatorDifferentiable Programming

    University of Tübingen, Germany · Max Planck Institute for Intelligent Systems, Tübingen, Germany · Masaryk University, Czechia +1

  10. Beyond ReinMax: Low-Variance Gradient Estimators for Discrete Latent Variables

    Mar 9, 2026Daniel Wang, Thang D. BuiStraight-Through EstimatorVariance Reduction

    School of Computing, College of Systems and Society, Australian National University

  11. Exact Discrete Stochastic Simulation with Deep-Learning-Scale Gradient Optimization

    Feb 23, 2026Jose M. G. Vilar, Leonor SaizStraight-Through EstimatorMarkov Chains

    Biofisika Institute (CSIC, UPV/EHU), University of the Basque Country (UPV/EHU), P.O. Box 644, 48080 Bilbao, Spain · IKERBASQUE, Basque Foundation for Science, 48011 Bilbao, Spain · Department of Biomedical Engineering, University of California, 451 E. Health Sciences Drive, Davis, CA 95616, USA