straight-through estimator

Approximation-Free Differentiable Oblique Decision Trees JMLR 2026 Correcting Quantization-Induced Gradient Mismatch in Neural Image Compression AAAI 2026 PE-QAT: Parameter-Efficient Quantization-Aware Training for Large Language Models ACL 2026 Analysis of Linear Mode Connectivity via Permutation-Based Weight Matching: With Insights into Other Permutation Search Methods ICLR 2025 Linear Mode Connectivity between Multiple Models modulo Permutation Symmetries ICML 2025 PARQ: Piecewise-Affine Regularized Quantization ICML 2025 Learning Discretized Neural Networks under Ricci Flow JMLR 2024 PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM Compression NeurIPS 2024 Reducing the Side-Effects of Oscillations in Training of Quantized YOLO Networks WACV 2024 Straight-Through Meets Sparse Recovery: the Support Exploration Algorithm ICML 2024 Training Binary Neural Networks via Gaussian Variational Inference and Low-Rank Semidefinite Programming NeurIPS 2024 Are Straight-Through Gradients and Soft-Thresholding All You Need for Sparse Training? WACV 2023 Bridging Discrete and Backpropagation: Straight-Through and Beyond NeurIPS 2023 Cold Analysis of Rao-Blackwellized Straight-Through Gumbel-Softmax Gradient Estimator ICML 2023 Estimator Meets Equilibrium Perspective: A Rectified Straight Through Estimator for Binary Neural Networks Training ICCV 2023 Straightening Out the Straight-Through Estimator: Overcoming Optimization Challenges in Vector Quantized Networks ICML 2023 AdaSTE: An Adaptive Straight-Through Estimator To Train Binary Neural Networks CVPR 2022 Injecting Logical Constraints into Neural Networks via Straight-Through Estimators ICML 2022 Nonuniform-to-Uniform Quantization: Towards Accurate Quantization via Generalized Straight-Through Estimation CVPR 2022 Training Discrete Deep Generative Models via Gapped Straight-Through Estimator ICML 2022 Training Quantised Neural Networks With STE Variants: The Additive Noise Annealing Algorithm CVPR 2022 Cluster-Promoting Quantization With Bit-Drop for Minimizing Network Quantization Loss ICCV 2021 Distance-Aware Quantization ICCV 2021 IDF++: Analyzing and Improving Integer Discrete Flows for Lossless Compression ICLR 2021 Learning N:M Fine-grained Structured Sparse Neural Networks From Scratch ICLR 2021