conftrace_

straight-through estimator

25 papers

Explore in graph

Also known as

STE

Co-occurring keywords

model compression (3302) neural network optimization (1293) network quantization (37) neural network quantization (122) binary neural network (75) variance reduction (523) quantization-aware training (50) gradient estimation (150) bit-width reduction (4) weight quantization (137)

Papers

PE-QAT: Parameter-Efficient Quantization-Aware Training for Large Language Models ACL 2026
Correcting Quantization-Induced Gradient Mismatch in Neural Image Compression AAAI 2026
Reducing the Side-Effects of Oscillations in Training of Quantized YOLO Networks WACV 2024
Training Binary Neural Networks via Gaussian Variational Inference and Low-Rank Semidefinite Programming NIPS 2024
Learning Discretized Neural Networks under Ricci Flow JMLR 2024
PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM Compression NIPS 2024
Are Straight-Through Gradients and Soft-Thresholding All You Need for Sparse Training? WACV 2023
Cold Analysis of Rao-Blackwellized Straight-Through Gumbel-Softmax Gradient Estimator ICML 2023
Bridging Discrete and Backpropagation: Straight-Through and Beyond NIPS 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
Training Quantised Neural Networks With STE Variants: The Additive Noise Annealing Algorithm CVPR 2022
AdaSTE: An Adaptive Straight-Through Estimator To Train Binary Neural Networks CVPR 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
Injecting Logical Constraints into Neural Networks via Straight-Through Estimators ICML 2022
Network Quantization With Element-Wise Gradient Scaling CVPR 2021
Mirror Descent View for Neural Network Quantization AISTATS 2021
Cluster-Promoting Quantization With Bit-Drop for Minimizing Network Quantization Loss ICCV 2021
Distance-Aware Quantization ICCV 2021
Path Sample-Analytic Gradient Estimators for Stochastic Binary Networks NIPS 2020
Understanding the Mechanics of SPIGOT: Surrogate Gradients for Latent Structure Learning EMNLP 2020
Low Bias Low Variance Gradient Estimates for Boolean Stochastic Networks ICML 2020
STAR-Caps: Capsule Networks with Straight-Through Attentive Routing NIPS 2019
MetaQuant: Learning to Quantize by Learning to Penetrate Non-differentiable Quantization NIPS 2019