No article text was recorded for this version.
continuous relaxation bias
Version 1 of 136 papers46 conceptsfrozen 2026-10-04
Papers in this version
- Blog: A Review of the Gumbel-max Trick and its Extensions for Discrete Stochasticity in Machine Learning
- Blog: Latent Structure Models for Natural Language Processing
- Blog: Learnable Bernoulli Dropout for Bayesian Deep Learning
- Blog: Direct Optimization through arg max for Discrete Variational Auto-Encoder
- Blog: ARSM: Augment-REINFORCE-Swap-Merge Estimator for Gradient Backpropagation Through Categorical Variables
- Blog: Stability Regularization for Discrete Representation Learning
- Blog: Cold Analysis of Rao-Blackwellized Straight-Through Gumbel-Softmax Gradient Estimator
- Blog: Bayesian Learning of Neural Network Architectures
- Blog: ARMS: Antithetic-REINFORCE-Multi-Sample Gradient for Binary Variables
- Blog: Rao-Blackwellized Stochastic Gradients for Discrete Distributions
- Blog: Coupled Gradient Estimators for Discrete Latent Variables
- Blog: Hindsight Network Credit Assignment: Efficient Credit Assignment in Networks of Discrete Stochastic Units
- Blog: Information-Bottleneck Approach to Salient Region Discovery
- Blog: Differentiable Feature Selection, a Reparameterization Approach
- Blog: Align Forward, Adapt Backward: Closing the Discretization Gap in Logic Gate Networks
- Blog: Categorical Reparameterization with Gumbel-Softmax
- Blog: Cold Rao-Blackwellized Straight-Through Gumbel-Softmax Gradient Estimator
- Blog: Discrete Latent Structure in Neural Networks
- Blog: CoT: Cooperative Training for Generative Modeling of Discrete Data
- Blog: Stochastic Optimization of Sorting Networks via Continuous Relaxations
- Blog: Techniques for Learning Binary Stochastic Feedforward Neural Networks
- Blog: Low Bias Low Variance Gradient Estimates for Boolean Stochastic Networks
- Blog: Doubly Reparameterized Gradient Estimators for Monte Carlo Objectives
- Blog: SIMPLE: A Gradient Estimator for k-Subset Sampling
- Blog: DVAE#: Discrete Variational Autoencoders with Relaxed Boltzmann Priors
- Blog: Differentiable Sampling of Categorical Distributions Using the CatLog-Derivative Trick
- Blog: Categorical Reparameterization with Denoising Diffusion Models
- Blog: Leveraging Recursive Gumbel-Max Trick for Approximate Inference in Combinatorial Spaces
- Blog: Smoothing Nonlinear Variational Objectives with Sequential Monte Carlo
- Blog: The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables
- Blog: L0-ARM: Network Sparsification via Stochastic Binary Optimization
- Blog: REBAR: Low-variance, unbiased gradient estimates for discrete latent variable models
- Blog: SWING: Unlocking Implicit Graph Representations for Graph Random Features
- Blog: Efficient Marginalization of Discrete and Structured Latent Variables via Sparsity
- Blog: Latent Template Induction with Gumbel-CRFs
- Blog: CARMS: Categorical-Antithetic-REINFORCE Multi-Sample Gradient Estimator
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_continuous_relaxation_bias_5a770eef,
title = {continuous relaxation bias},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/continuous-relaxation-bias/rdr_5a770eef83094fef9ba3aa8dcc266a9c},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_continuous_relaxation_bias_5a770eef_v1,
title = {continuous relaxation bias},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/continuous-relaxation-bias/rdr_5a770eef83094fef9ba3aa8dcc266a9c/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}