home.social

#regularization — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #regularization, aggregated by home.social.

  1. SLAY-ASR, или как я перестал волноваться и полюбил тренировать модели

    Как добавить аудио-модальность в LLMку максимально экономно? Рассказываю про серию попыток добиться совместимости эмбеддингов разной природы Погрузиться

    habr.com/ru/articles/1009614/

    #representation_learning #multimodality #multimodal_llm #machine_learning #audiomodality #regularization #contrastive_learning #whisper #gemma3

  2. SLAY-ASR, или как я перестал волноваться и полюбил тренировать модели

    Как добавить аудио-модальность в LLMку максимально экономно? Рассказываю про серию попыток добиться совместимости эмбеддингов разной природы Погрузиться

    habr.com/ru/articles/1009614/

    #representation_learning #multimodality #multimodal_llm #machine_learning #audiomodality #regularization #contrastive_learning #whisper #gemma3

  3. SLAY-ASR, или как я перестал волноваться и полюбил тренировать модели

    Как добавить аудио-модальность в LLMку максимально экономно? Рассказываю про серию попыток добиться совместимости эмбеддингов разной природы Погрузиться

    habr.com/ru/articles/1009614/

    #representation_learning #multimodality #multimodal_llm #machine_learning #audiomodality #regularization #contrastive_learning #whisper #gemma3

  4. SLAY-ASR, или как я перестал волноваться и полюбил тренировать модели

    Как добавить аудио-модальность в LLMку максимально экономно? Рассказываю про серию попыток добиться совместимости эмбеддингов разной природы Погрузиться

    habr.com/ru/articles/1009614/

    #representation_learning #multimodality #multimodal_llm #machine_learning #audiomodality #regularization #contrastive_learning #whisper #gemma3

  5. 'Spectral Regularized Kernel Goodness-of-Fit Tests', by Omar Hagrass, Bharath K. Sriperumbudur, Bing Li.

    jmlr.org/papers/v25/23-1031.ht

    #regularization #regularized #spectral

  6. Semantic Self-adaptation: Enhancing Generalization with a Single Sample

    Sherwin Bahmani, Oliver Hahn, Eduard Zamfir, Nikita Araslanov, Daniel Cremers, Stefan Roth

    Action editor: Wei Liu.

    openreview.net/forum?id=ILNqQh

    #regularization #normalization #trained

  7. 'Variance estimation in graphs with the fused lasso', by Oscar Hernan Madrid Padilla.

    jmlr.org/papers/v25/23-1061.ht

    #lasso #regularization #graphs

  8. 'Variation Spaces for Multi-Output Neural Networks: Insights on Multi-Task Learning and Network Compression', by Joseph Shenouda, Rahul Parhi, Kangwook Lee, Robert D. Nowak.

    jmlr.org/papers/v25/23-0677.ht

    #regularization #lasso #representations

  9. Линейная регрессия. Основная идея, модификации и реализация с нуля на Python

    В машинном и глубоком обучении линейная регрессия занимает особое место, являясь не просто статистическим инструментом, но а также фундаментальным компонентом для многих более сложных концепций. В данной статье рассмотрен не только принцип работы линейной регрессии с реализацией с нуля на Python, но а также описаны её модификации и проведён небольшой сравнительный анализ основных методов регуляризации. Помимо этого, в конце указаны дополнительные источники для более глубокого ознакомления.

    habr.com/ru/articles/804135/

    #линейная_регрессия #linear_regression #polynomial #ridge #lasso #elasticnet #regularization #реализация_с_нуля #python #data_science

  10. 'Deep Out-of-Distribution Uncertainty Quantification via Weight Entropy Maximization', by Antoine de Mathelin, François Deheeger, Mathilde Mougeot, Nicolas Vayatis.

    jmlr.org/papers/v26/23-1359.ht

    #regularization #entropy #gaussian

  11. A Stochastic Proximal Polyak Step Size

    Fabian Schaipp, Robert M. Gower, Michael Ulbrich

    Action editor: Stephen Becker.

    openreview.net/forum?id=jWr41h

    #regularization #proxsps #proximal

  12. 'An Optimal Transport Approach for Computing Adversarial Training Lower Bounds in Multiclass Classification', by Nicolas Garcia Trillos, Matt Jacobs, Jakwang Kim, Matthew Werenski.

    jmlr.org/papers/v25/24-0268.ht

    #adversarial #regularization #classifiers

  13. 'An Inexact Projected Regularized Newton Method for Fused Zero-norms Regularization Problems', by Yuqia Wu, Shaohua Pan, Xiaoqi Yang.

    jmlr.org/papers/v25/23-1700.ht

    #regularization #regularized #gradient

  14. 'Entropic Gromov-Wasserstein Distances: Stability and Algorithms', by Gabriel Rioux, Ziv Goldfeld, Kengo Kato.

    jmlr.org/papers/v25/24-0039.ht

    #regularization #wasserstein #variational

  15. 'Stochastic Regularized Majorization-Minimization with weakly convex and multi-convex surrogates', by Hanbaek Lyu.

    jmlr.org/papers/v25/23-0349.ht

    #regularization #regularized #minimization

  16. 'Random Smoothing Regularization in Kernel Gradient Descent Learning', by Liang Ding, Tianyang Hu, Jiahang Jiang, Donghao Li, Wenjia Wang, Yuan Yao.

    jmlr.org/papers/v25/23-0580.ht

    #regularization #smoothing #gradient

  17. 'Functional optimal transport: regularized map estimation and domain adaptation for functional data', by Jiacheng Zhu, Aritra Guha, Dat Do, Mengdi Xu, XuanLong Nguyen, Ding Zhao.

    jmlr.org/papers/v25/22-0217.ht

    #transport #regularization #measures

  18. 'On Regularized Radon-Nikodym Differentiation', by Duc Hoan Nguyen, Werner Zellinger, Sergei Pereverzyev.

    jmlr.org/papers/v25/23-0567.ht

    #regularization #regularized #estimation

  19. 'Label Alignment Regularization for Distribution Shift', by Ehsan Imani, Guojun Zhang, Runjia Li, Jun Luo, Pascal Poupart, Philip H.S. Torr, Yangchen Pan.

    jmlr.org/papers/v25/23-0899.ht

    #regularization #regularizing #label

  20. 'The Loss Landscape of Deep Linear Neural Networks: a Second-order Analysis', by El Mehdi Achour, François Malgouyres, Sébastien Gerchinovitz.

    jmlr.org/papers/v25/23-0493.ht

    #minimizers #regularization #optimization

  21. 'Understanding Entropic Regularization in GANs', by Daria Reshetova, Yikun Bai, Xiugang Wu, Ayfer Özgür.

    jmlr.org/papers/v25/21-1295.ht

    #regularization #adversarial #gans

  22. 'Dropout Regularization Versus l2-Penalization in the Linear Model', by Gabriel Clara, Sophie Langer, Johannes Schmidt-Hieber.

    jmlr.org/papers/v25/23-0803.ht

    #regularization #dropout #penalization

  23. 'Blessings and Curses of Covariate Shifts: Adversarial Learning Dynamics, Directional Convergence, and Equilibria', by Tengyuan Liang.

    jmlr.org/papers/v25/23-0651.ht

    #adversarial #learned #regularization

  24. 'Sparse Representer Theorems for Learning in Reproducing Kernel Banach Spaces', by Rui Wang, Yuesheng Xu, Mingsong Yan.

    jmlr.org/papers/v25/23-0645.ht

    #regularization #sparse #regularized

  25. 'The good, the bad and the ugly sides of data augmentation: An implicit spectral regularization perspective', by Chi-Heng Lin, Chiraag Kaushik, Eva L. Dyer, Vidya Muthukumar.

    jmlr.org/papers/v25/22-1312.ht

    #regularization #overparameterized #augmentation

  26. 'Improving Lipschitz-Constrained Neural Networks by Learning Activation Functions', by Stanislas Ducotterd et al.

    jmlr.org/papers/v25/22-1347.ht

    #regularization #optimization #lipschitz

  27. 'Sparse NMF with Archetypal Regularization: Computational and Robustness Properties', by Kayhan Behdin, Rahul Mazumder.

    jmlr.org/papers/v25/21-0233.ht

    #sparse #regularization #robustness

  28. 'Optimal Bump Functions for Shallow ReLU networks: Weight Decay, Depth Separation, Curse of Dimensionality', by Stephan Wojtowytsch.

    jmlr.org/papers/v25/22-1296.ht

    #regularization #minimizer #neuron

  29. 'Post-Regularization Confidence Bands for Ordinary Differential Equations', by Xiaowu Dai, Lexin Li.

    jmlr.org/papers/v25/22-0487.ht

    #regularization #kernel #regulatory

  30. 'On the Effect of Initialization: The Scaling Path of 2-Layer Neural Networks', by Sebastian Neumayer, Lénaïc Chizat, Michael Unser.

    jmlr.org/papers/v25/23-0549.ht

    #regularization #gradient #optimization

  31. 'Fast Policy Extragradient Methods for Competitive Games with Entropy Regularization', by Shicong Cen, Yuting Wei, Yuejie Chi.

    jmlr.org/papers/v25/21-1205.ht

    #regularization #reinforcement #regularized

  32. Robustness through Data Augmentation Loss Consistency

    Tianjian Huang, Shaunak Ashish Halbe, Chinnadhurai Sankar et al.

    openreview.net/forum?id=a1meaR

    #regularization #adversarial #augment

  33. 'An Inexact Projected Regularized Newton Method for Fused Zero-norms Regularization Problems', by Yuqia Wu, Shaohua Pan, Xiaoqi Yang.

    jmlr.org/papers/v25/23-1700.ht

    #regularization #regularized #gradient

  34. 'An Inexact Projected Regularized Newton Method for Fused Zero-norms Regularization Problems', by Yuqia Wu, Shaohua Pan, Xiaoqi Yang.

    jmlr.org/papers/v25/23-1700.ht

    #regularization #regularized #gradient

  35. 'An Inexact Projected Regularized Newton Method for Fused Zero-norms Regularization Problems', by Yuqia Wu, Shaohua Pan, Xiaoqi Yang.

    jmlr.org/papers/v25/23-1700.ht

    #regularization #regularized #gradient

  36. 'Spectral Regularized Kernel Goodness-of-Fit Tests', by Omar Hagrass, Bharath K. Sriperumbudur, Bing Li.

    jmlr.org/papers/v25/23-1031.ht

    #regularization #regularized #spectral

  37. 'Spectral Regularized Kernel Goodness-of-Fit Tests', by Omar Hagrass, Bharath K. Sriperumbudur, Bing Li.

    jmlr.org/papers/v25/23-1031.ht

    #regularization #regularized #spectral

  38. 'Spectral Regularized Kernel Goodness-of-Fit Tests', by Omar Hagrass, Bharath K. Sriperumbudur, Bing Li.

    jmlr.org/papers/v25/23-1031.ht

    #regularization #regularized #spectral

  39. 'Stochastic Regularized Majorization-Minimization with weakly convex and multi-convex surrogates', by Hanbaek Lyu.

    jmlr.org/papers/v25/23-0349.ht

    #regularization #regularized #minimization

  40. 'Stochastic Regularized Majorization-Minimization with weakly convex and multi-convex surrogates', by Hanbaek Lyu.

    jmlr.org/papers/v25/23-0349.ht

    #regularization #regularized #minimization

  41. 'Stochastic Regularized Majorization-Minimization with weakly convex and multi-convex surrogates', by Hanbaek Lyu.

    jmlr.org/papers/v25/23-0349.ht

    #regularization #regularized #minimization

  42. 'On Regularized Radon-Nikodym Differentiation', by Duc Hoan Nguyen, Werner Zellinger, Sergei Pereverzyev.

    jmlr.org/papers/v25/23-0567.ht

    #regularization #regularized #estimation

  43. 'On Regularized Radon-Nikodym Differentiation', by Duc Hoan Nguyen, Werner Zellinger, Sergei Pereverzyev.

    jmlr.org/papers/v25/23-0567.ht

    #regularization #regularized #estimation

  44. 'On Regularized Radon-Nikodym Differentiation', by Duc Hoan Nguyen, Werner Zellinger, Sergei Pereverzyev.

    jmlr.org/papers/v25/23-0567.ht

    #regularization #regularized #estimation