No article text was recorded for this version.
dynamic penalty scaling
Version 1 of 135 papers46 conceptsfrozen 2026-10-04
Papers in this version
- Blog: On the Overlooked Pitfalls of Weight Decay and How to Mitigate Them: A Gradient-Norm Perspective
- Blog: Understanding and Scheduling Weight Decay
- Blog: On the training dynamics of deep networks with $L_2$ regularization
- Blog: Adaptive Weight Decay for Deep Neural Networks
- Blog: Coverage ≠ Exposure: Auditable Control of Same-Support Tail Failures under Multimodal Missingness
- Blog: Neural Stein Critics With Staged L 2-Regularization
- Blog: Meta-Learning with Adaptive Hyperparameters
- Blog: Amos: An Adam-style Optimizer with Adaptive Weight Decay towards Model-Oriented Scale
- Blog: Adaptive Weight Decay: On The Fly Weight Decay Tuning for Improving Robustness
- Blog: MobileOne: An Improved One millisecond Mobile Backbone
- Blog: Variational Discriminator Bottleneck: Improving Imitation Learning, Inverse RL, and GANs by Constraining Information Flow
- Blog: Improving Robustness with Adaptive Weight Decay
- Blog: $\beta$-DPO: Direct Preference Optimization with Dynamic $\beta$
- Blog: Learning dynamic representations via an optimally-weighted maximum mean discrepancy optimization framework for continual learning
- Blog: Enhancing Neural Architecture Search With Multiple Hardware Constraints for Deep Learning Model Deployment on Tiny IoT Devices
- Blog: Optimization as a Model for Few-Shot Learning
- Blog: Worst-case Feature Risk Minimization for Data-Efficient Learning
- Blog: Sharpness-Aware Minimization with Adaptive Regularization for Training Deep Neural Networks
- Blog: A unified DNN weight compression framework using reweighted optimization methods
- Blog: Dynamic Gradient Alignment for Online Data Mixing
- Blog: Regularized Gradient Descent Ascent for Two-Player Zero-Sum Markov Games
- Blog: Conformal Symplectic Optimization for Stable Reinforcement Learning
- Blog: Global Update Guided Federated Learning
- Blog: CoRe Optimizer: An All-in-One Solution for Machine Learning
- Blog: Fine-grained Optimization of Deep Neural Networks
- Blog: Evolving neural selection with adaptive regularization
- Blog: Understanding Dropout
- Blog: On Fast Dropout and its Applicability to Recurrent Networks
- Blog: KL Penalty Control via Perturbation for Direct Preference Optimization
- Blog: Heavy-Tailed Regularization of Weight Matrices in Deep Neural Networks
- Blog: OvSW: Overcoming Silent Weights for Accurate Binary Neural Networks
- Blog: Assisting the Adversary to Improve GAN Training
- Blog: Generalization by Weight-Elimination with Application to Forecasting
- Blog: Untrained neural network embedded Fourier phase retrieval from few measurements
- Blog: AEM: Attention Entropy Maximization for Multiple Instance Learning Based Whole Slide Image Classification
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_dynamic_penalty_scaling_2fd56dee,
title = {dynamic penalty scaling},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/dynamic-penalty-scaling/rdr_2fd56dee2a734b5098c6fd3e15eb8f5f},
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_dynamic_penalty_scaling_2fd56dee_v1,
title = {dynamic penalty scaling},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/dynamic-penalty-scaling/rdr_2fd56dee2a734b5098c6fd3e15eb8f5f/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}