Methods › General › Parameter Norm Penalties › L1 Regularization
L1 Regularization
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
L₁ Regularization is a regularization technique applied to the weights of a neural network. We minimize a loss function compromising both the primary loss function and a penalty on the L₁ Norm of the weights:
L_(new)(w) = L_(original)(w) + λ||w||₁
where λ is a value determining the strength of the penalty. In contrast to weight decay, L₁ regularization promotes sparsity; i.e. some parameters have an optimal value of zero.
Image Source: Wikipedia
#/media/File:Sparsityl1.png){kind=link}
Papers archive 2025-07-28
30 shown of 90, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
PRETI: Patient-Aware Retinal Foundation Model via Metadata-Guided Representation Learning 18 May 2025 · 0 repositories · arXiv:2505.12233
-
SPAT: Sensitivity-based Multihead-attention Pruning on Time Series Forecasting Models 13 May 2025 · 0 repositories · arXiv:2505.08768
-
Decoding Futures Price Dynamics: A Regularized Sparse Autoencoder for Interpretable Multi-Horizon Forecasting and Factor Discovery 11 May 2025 · 0 repositories · arXiv:2505.06795
-
High-Frequency Prior-Driven Adaptive Masking for Accelerating Image Super-Resolution 11 May 2025 · 1 repository · arXiv:2505.06975
-
BQSched: A Non-intrusive Scheduler for Batch Concurrent Queries via Reinforcement Learning 27 Apr 2025 · 1 repository · arXiv:2504.19142
-
From Gaze to Insight: Bridging Human Visual Attention and Vision Language Model Explanation for Weakly-Supervised Medical Image Segmentation 15 Apr 2025 · 0 repositories · arXiv:2504.11368
-
NNN: Next-Generation Neural Networks for Marketing Measurement 8 Apr 2025 · 0 repositories · arXiv:2504.06212
-
Remarks on the Polyak-Lojasiewicz inequality and the convergence of gradient systems 31 Mar 2025 · 0 repositories · arXiv:2503.23641
-
Adaptive Rank Allocation: Speeding Up Modern Transformers with RaNA Adapters 23 Mar 2025 · 1 repository · arXiv:2503.18216Syntology ran 3 of 4 samples · 1 unverified
-
Al-Khwarizmi: Discovering Physical Laws with Foundation Models 3 Feb 2025 · 0 repositories · arXiv:2502.01702
-
Renewable Energy Prediction: A Comparative Study of Deep Learning Models for Complex Dataset Analysis 27 Jan 2025 · 0 repositories · arXiv:2501.15731
-
HAC++: Towards 100X Compression of 3D Gaussian Splatting 21 Jan 2025 · 2 repositories · arXiv:2501.12255
-
Kryptonite-N: Machine Learning Strikes Back 29 Dec 2024 · 0 repositories · arXiv:2412.20588
-
Efficient Masked AutoEncoder for Video Object Counting and A Large-Scale Benchmark 20 Nov 2024 · 0 repositories · arXiv:2411.13056
-
Carbon price fluctuation prediction using blockchain information A new hybrid machine learning approach 5 Nov 2024 · 0 repositories · arXiv:2411.02709
-
EH-MAM: Easy-to-Hard Masked Acoustic Modeling for Self-Supervised Speech Representation Learning 17 Oct 2024 · 1 repository · arXiv:2410.13179Syntology ran 6 of 10 samples · 4 unverified
-
Defending Membership Inference Attacks via Privacy-aware Sparsity Tuning 9 Oct 2024 · 0 repositories · arXiv:2410.06814
-
Adaptive Masking Enhances Visual Grounding 4 Oct 2024 · 0 repositories · arXiv:2410.03161
-
Pre-training on High Definition X-ray Images: An Experimental Study 27 Apr 2024 · 1 repository · arXiv:2404.17926
-
Salience-Based Adaptive Masking: Revisiting Token Dynamics for Enhanced Pre-training 12 Apr 2024 · 0 repositories · arXiv:2404.08327
-
Sparse Concept Bottleneck Models: Gumbel Tricks in Contrastive Learning 4 Apr 2024 · 2 repositories · arXiv:2404.03323
-
Retentive Decision Transformer with Adaptive Masking for Reinforcement Learning based Recommendation Systems 26 Mar 2024 · 0 repositories · arXiv:2403.17634
-
HAC: Hash-grid Assisted Context for 3D Gaussian Splatting Compression 21 Mar 2024 · 2 repositories · arXiv:2403.14530
-
Exploiting Adaptive Contextual Masking for Aspect-Based Sentiment Analysis 21 Feb 2024 · 0 repositories · arXiv:2402.13722
-
Manipulating Sparse Double Descent 19 Jan 2024 · 1 repository · arXiv:2401.10686
-
A novel hybrid time-varying graph neural network for traffic flow forecasting 17 Jan 2024 · 0 repositories · arXiv:2401.10155
-
On sparse regression, Lp-regularization, and automated model discovery 9 Oct 2023 · 0 repositories · arXiv:2310.06872
-
Dynamic ASR Pathways: An Adaptive Masking Approach Towards Efficient Pruning of A Multilingual ASR Model 22 Sep 2023 · 0 repositories · arXiv:2309.13018
-
AMLP:Adaptive Masking Lesion Patches for Self-supervised Medical Image Segmentation 8 Sep 2023 · 0 repositories · arXiv:2309.04312
-
SDR-GAIN: A High Real-Time Occluded Pedestrian Pose Completion Method for Autonomous Driving 6 Jun 2023 · 0 repositories · arXiv:2306.03538
Tasks archive 2025-07-28
20 shown of 120 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections