mlsanityData to 7 Oct 2026

Evolutionary Retrofitting

arXiv 2410.11330 ↗First posted 15 Oct 2024cs.LG cs.NE math.OCcited by 2

Not on the map. Why?

Abstract (arXiv)

AfterLearnER (After Learning Evolutionary Retrofitting) consists in applying evolutionary optimization to refine fully trained machine learning models by optimizing a set of carefully chosen parameters or hyperparameters of the model, with respect to some actual, exact, and hence possibly non-differentiable error signal, performed on a subset of the standard validation set. The efficiency of AfterLearnER is demonstrated by tackling non-differentiable signals such as threshold-based criteria in depth sensing, the word error rate in speech re-synthesis, the number of kills per life at Doom, computational accuracy or BLEU in code translation, image quality in 3D generative adversarial networks (GANs), and user feedback in image generation via Latent Diffusion Models (LDM). This retrofitting can be done after training, or dynamically at inference time by taking into account the user feedback. The advantages of AfterLearnER are its versatility, the possibility to use non-differentiable feedback, including human evaluations (i.e., no gradient is needed), the limited overfitting supported by a theoretical study, and its anytime behavior. Last but not least, AfterLearnER requires only a small amount of feedback, i.e., a few dozen to a few hundred scalars, compared to the tens of thousands needed in most related published works.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 56 of its 116 references that are in the map. First posted on arXiv 15 Oct 2024.

Builds on

56 of 116 references.

References · 56

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  3. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  4. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,195
  5. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,853
  6. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  7. 2014Conditional Generative Adversarial Netscited by 2,152
  8. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,484
  9. 2019A Comprehensive Survey on Transfer Learningcited by 1,154
  10. 2016ConceptNet 5.5: An Open Multilingual Graph of General Knowledgecited by 1,065
  11. 2015Sequence Level Training with Recurrent Neural Networkscited by 568
  12. 2017Evolution Strategies as a Scalable Alternative to Reinforcement Learningcited by 555
38 more
  1. 2022Efficient Test-Time Model Adaptation without Forgettingcited by 467
  2. 2023Aligning Text-to-Image Models using Human Feedbackcited by 418
  3. 2023Towards Stable Test-Time Adaptation in Dynamic Wild Worldcited by 409
  4. 2018WaveGlow: A Flow-based Generative Network for Speech Synthesiscited by 308
  5. 2017Train longer, generalize better: closing the generalization gap in large batch training of neural networkscited by 278
  6. 2020Unsupervised Translation of Programming Languagescited by 262
  7. 2022Black-Box Tuning for Language-Model-as-a-Servicecited by 254
  8. 2023Principled Reinforcement Learning with Human Feedback from Pairwise or K-wise Comparisonscited by 244
  9. 2021Speech Resynthesis from Discrete Disentangled Self-Supervised Representationscited by 243
  10. 2018Neural Architecture Search with Bayesian Optimisation and Optimal Transportcited by 192
  11. 2016ViZDoom: A Doom-based AI Research Platform for Visual Reinforcement Learningcited by 178
  12. 2023MiDaS v3.1 -- A Model Zoo for Robust Monocular Relative Depth Estimationcited by 173
  13. 2017Sparse-to-Dense: Depth Prediction from Sparse Depth Samples and a Single Imagecited by 159
  14. 2017BEGAN: Boundary Equilibrium Generative Adversarial Networkscited by 121
  15. 2019Learning the Depths of Moving People by Watching Frozen Peoplecited by 120
  16. 2022Test-Time Adaptation via Conjugate Pseudo-labelscited by 98
  17. 2016Playing FPS Games with Deep Reinforcement Learningcited by 95
  18. 2019Asymmetric Valleys: Beyond Sharp and Flat Local Minimacited by 90
  19. 2023Preference Transformer: Modeling Human Preferences using Transformers for RLcited by 77
  20. 2020DiverseDepth: Affine-invariant Depth Prediction Using Diverse Datacited by 60
  21. 2019Optimizing Rank-based Metrics with Blackbox Differentiationcited by 58
  22. 2018DQN-TAMER: Human-in-the-Loop Reinforcement Learning with Intractable Feedbackcited by 39
  23. 2023Towards Open-Set Test-Time Adaptation Utilizing the Wisdom of Crowds in Entropy Minimizationcited by 39
  24. 2023Tuning computer vision models with task rewardscited by 36
  25. 2016Learning Preferences for Manipulation Tasks from Online Coactive Feedbackcited by 31
  26. 2022Improving Multimodal Interactive Agents with Reinforcement Learning from Human Feedbackcited by 26
  27. 2023On the Evaluation of Neural Code Translation: Taxonomy and Benchmarkcited by 23
  28. 2020Versatile Black-Box Optimizationcited by 22
  29. 2018DENSER: Deep Evolutionary Network Structured Representationcited by 16
  30. 2020Black-Box Optimization Revisited: Improving Algorithm Selection Wizards through Massive Benchmarkingcited by 14
  31. 2018Deep Interactive Evolutioncited by 13
  32. 2019Self-Adjusting Mutation Rates with Provably Optimal Success Rulescited by 13
  33. 2023The Expressive Power of Tuning Only the Normalization Layerscited by 13
  34. 2020Wide flat minima and optimal generalization in classifying high-dimensional Gaussian mixturescited by 9
  35. 2021MetricOpt: Learning to Optimize Black-Box Evaluation Metricscited by 9
  36. 2020Optimizing Black-box Metrics with Adaptive Surrogatescited by 7
  37. 2016Self-adaptation of Mutation Rates in Non-elitist Populationscited by 6
  38. 2020EvolGAN: Evolutionary Generative Adversarial Networkscited by 6

50 most cited of 56 All 56 (JSON)

Built on by

Cited by year

Citing papers per year: 2024: 1; 2025: 1.

2 papers.

  1. 2024Evolutionary Pre-Prompt Optimization for Mathematical Reasoningcited by 1
  2. 2025Tuning without Peeking: Provable Generalization Bounds and Robust LLM Post-Trainingcited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2024Heuristically Adaptive Diffusion-Model Evolutionary Strategy
  2. 2026From Collapse to Improvement: Statistical Perspectives on the Evolutionary Dynamics of Iterative Training on Contaminated Sources
  3. 2024Diffusion Models are Evolutionary Algorithms
  4. 2026When Does Adversarial Refinement Help? A Negative Result and Open Problem in Adapting R3GAN to Time Series Imputation
  5. 2026When Generative Augmentation Hurts: A Benchmark Study of GAN and Diffusion Models for Bias Correction in AI Classification Systems
  6. 2024EvoMerge: Neuroevolution for Large Language Models
  7. 2026PAST: Prompt-Adaptive Sampling Termination for Efficient Diffusion Model
  8. 2025Exploring the Design Space of Transition Matching