conftrace_

straight-through estimator

35 papers

Explore in graph

Also known as

STE

Co-occurring keywords · papers mentioning both

model compression (13) network quantization (6) neural network optimization (6) quantization-aware training (5) neural network quantization (5) binary neural network (4) variance reduction (4) gradient descent (4) weight quantization (3) gradient estimation (3)

Papers

Mirror Descent View for Neural Network Quantization AISTATS 2021 Network Quantization With Element-Wise Gradient Scaling CVPR 2021 Training with Quantization Noise for Extreme Model Compression ICLR 2021 Low Bias Low Variance Gradient Estimates for Boolean Stochastic Networks ICML 2020 Path Sample-Analytic Gradient Estimators for Stochastic Binary Networks NeurIPS 2020 Understanding the Mechanics of SPIGOT: Surrogate Gradients for Latent Structure Learning EMNLP 2020 MetaQuant: Learning to Quantize by Learning to Penetrate Non-differentiable Quantization NeurIPS 2019 STAR-Caps: Capsule Networks with Straight-Through Attentive Routing NeurIPS 2019 Understanding Straight-Through Estimator in Training Activation Quantized Neural Nets ICLR 2019 Deep Learning as a Mixed Convex-Combinatorial Optimization Problem ICLR 2018