No article text was recorded for this version.
differentiable metric approximation (differentiable metric surrogacy)
Version 1 of 120 papers25 conceptsfrozen 2026-10-04
Papers in this version
- Blog: iMetricGAN: Intelligibility Enhancement for Speech-in-Noise Using Generative Adversarial Network-Based Metric Learning
- Blog: MetricGAN: Generative Adversarial Networks based Black-box Metric Scores Optimization for Speech Enhancement
- Blog: MetricGAN-U: Unsupervised speech enhancement/ dereverberation based only on noisy/ reverberated speech
- Blog: Improving Character Error Rate is Not Equal to Having Clean Speech: Speech Enhancement for ASR Systems with Black-Box Acoustic Models
- Blog: Learning With Learned Loss Function: Speech Enhancement With Quality-Net to Improve Perceptual Evaluation of Speech Quality
- Blog: Metric-oriented Speech Enhancement using Diffusion Probabilistic Model
- Blog: Does a PESQNet (Loss) Require a Clean Reference Input? The Original PESQ Does, But ACR Listening Tests Don't
- Blog: Deep Noise Suppression Maximizing Non-Differentiable PESQ Mediated by a Non-Intrusive PESQNet
- Blog: Combinatorial Optimization for Panoptic Segmentation: A Fully Differentiable Approach
- Blog: Task-Based Learning via Task-Oriented Prediction Network with Applications in Finance
- Blog: RankSRGAN: Generative Adversarial Networks with Ranker for Image Super-Resolution
- Blog: Machine Translation Models Stand Strong in the Face of Adversarial Attacks
- Blog: MetricOpt: Learning To Optimize Black-Box Evaluation Metrics
- Blog: MetricGAN+: An Improved Version of MetricGAN for Speech Enhancement
- Blog: Internal Evaluation of Density-Based Clusterings with Noise
- Blog: RankSRGAN: Super Resolution Generative Adversarial Networks with Learning to Rank
- Blog: Training Deep Networks to be Spatially Sensitive
- Blog: Learning to Watermark: A Selective Watermarking Framework for Large Language Models via Multi-Objective Optimization
- Blog: The PESQetarian: On the Relevance of Goodhart's Law for Speech Enhancement
- Blog: ProxIQA: A Proxy Approach to Perceptual Optimization of Learned Image Compression
History & citation
Current · Permanent link
- This direction split from Optimizing Non-Differentiable Objectives via Neural Surrogates (80% overlap)
- This direction split from non-differentiable objective functions (non-differentiable metric optimization) (60% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_differentiable_metric_approximation_diff_fbb94122,
title = {differentiable metric approximation (differentiable metric surrogacy)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/differentiable-metric-approximation-differentiable-metric-surrogacy/rdr_fbb94122c37b46b4b55c8bd3e1505eb2},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-19},
}This exact version (version 1, frozen text):
@misc{lacuna_differentiable_metric_approximation_diff_fbb94122_v1,
title = {differentiable metric approximation (differentiable metric surrogacy)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/differentiable-metric-approximation-differentiable-metric-surrogacy/rdr_fbb94122c37b46b4b55c8bd3e1505eb2/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-19},
}