paper-with-me

Papers

Bridging Discrete and Backpropagation: Straight-Through and Beyond

2023-09-21 · NeurIPS 2023 11

Backpropagation, the cornerstone of deep learning, is limited to computing gradients for continuous variables. This limitation poses challenges for problems involving discrete latent variables. To address this issue, we propose a novel approach to approximate the gradient of parameters involved in generating discrete latent variables. First, we examine the widely used Straight-Through (ST) heuristic and demonstrate that it works as a first-order approximation of the gradient. Guided by our findings, we propose ReinMax, which achieves second-order accuracy by integrating Heun’s method, a second-order numerical method for solving ODEs. ReinMax does not require Hessian or other second-order derivatives, thus having negligible computation overheads. Extensive experimental results on various tasks demonstrate the superiority of ReinMax over the state of the art.

📄 PDF Abstract BibTeX

Code (1)

microsoft/reinmax 공식 구현 pytorch

Similar Papers 제목 키워드 기반

Learning Discrete Directed Acyclic Graphs via Backpropagation

2022-10-27 · Andrew J. Wren, Pasquale Minervini, Luca Franceschi, Valentina Zantedeschi

Recently continuous relaxations have been proposed in order to learn Directed Acyclic Graphs (DAGs) from data by backpropagation, instead of using combinatorial optimization. However, a number of techniques for fully dis…

Combinatorial Optimization

Beyond Discreteness: Finite-Sample Analysis of Straight-Through Estimator for Quantization

2025-05-23 · Halyun Jeong, Jack Xin, Penghang Yin

Training quantized neural networks requires addressing the non-differentiable and discrete nature of the underlying optimization problem. To tackle this challenge, the straight-through estimator (STE) has become the most…

compressed sensingQuantization

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

2026-03-09 · Daniel Wang, Thang D. Bui arxiv

Machine learning models involving discrete latent variables require gradient estimators to facilitate backpropagation in a computationally efficient manner. The most recent addition to the Straight-Through family of esti…

Generalized Stochastic Backpropagation

2021-01-01 · Amine Echraibi, Joachim Flocon Cholet, Stéphane Gosselin, Sandrine Vaton

Backpropagating gradients through random variables is at the heart of numerous machine learning applications. In this paper, we present a general framework for deriving stochastic backpropagation rules for any distributi…

Backpropagation through Combinatorial Algorithms: Identity with Projection Works

2022-05-30 · Subham Sekhar Sahoo, Anselm Paulus, Marin Vlastelica, Vít Musil 외

Embedding discrete solvers as differentiable layers has given modern deep learning architectures combinatorial expressivity and discrete reasoning capabilities. The derivative of these solvers is zero or undefined, there…

Density EstimationGraph MatchingImage RetrievalRetrieval+1