No article text was recorded for this version.
cyclic learning rate scheduling
Version 2 of 261 papers75 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Snapshot Ensembles: Train 1, Get M for Free
- Blog: Multilingual Deep Neural Network Training Using Cyclical Learning Rate
- Blog: CyclicAugment: Speech Data Random Augmentation with Cosine Annealing Scheduler for Automatic Speech Recognition
- Blog: Demystifying Learning Rate Policies for High Accuracy Training of Deep Neural Networks
- Blog: Wide-minima Density Hypothesis and the Explore-Exploit Learning Rate Schedule
- Blog: A New Snapshot Ensemble Convolutional Neural Network for Fault Diagnosis
- Blog: Enhancing Organ at Risk Segmentation with Improved Deep Neural Networks
- Blog: Navigating Local Minima in Quantized Spiking Neural Networks
- Blog: Stochastic Weight Averaging Revisited
- Blog: Selecting and Composing Learning Rate Policies for Deep Neural Networks
- Blog: Collaborative deep learning across multiple data centers
- Blog: Navigating Local Minima in Quantized Spiking Neural Networks
- Blog: Online Embedding Compression for Text Classification Using Low Rank Matrix Factorization.
- Blog: FastSpiker: Enabling Fast Training for Spiking Neural Networks on Event-based Data through Learning Rate Enhancements for Autonomous Embedded Systems
- Blog: On Generalizing Detection Models for Unconstrained Environments
- Blog: Homotopy Relaxation Training Algorithms for Infinite-Width Two-Layer ReLU Neural Networks
- Blog: Averaging Weights Leads to Wider Optima and Better Generalization
- Blog: SGDR: Stochastic Gradient Descent with Warm Restarts
- Blog: Snapshot Ensembles: Train 1, Get M for Free
- Blog: A Closer Look at Deep Learning Heuristics: Learning rate restarts, Warmup and Distillation
- Blog: FissionFusion: Fast Geometric Generation and Hierarchical Souping for Medical Image Analysis
- Blog: CONGA:Confidence-and-Gradient-Aware Learning Rate Schedule for Test Time Adaptation
- Blog: The Noise Geometry of Stochastic Gradient Descent: A Quantitative and Analytical Characterization
- Blog: Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs
- Blog: Snapshot Distillation: Teacher-Student Optimization in One Generation
- Blog: Towards Mitigating Architecture Overfitting in Dataset Distillation
- Blog: SGDR: Stochastic Gradient Descent with Warm Restarts
- Blog: Exploring Deep Learning Models for EEG Neural Decoding
- Blog: RIFLE: Backpropagation in Depth for Deep Transfer Learning through Re-Initializing the Fully-connected LayEr
- Blog: Automated machine vision enabled detection of movement disorders from hand drawn spirals
- Blog: Interpreting Fine-Grained Dermatological Classification by Deep Learning
- Blog: Towards Flatter Loss Surface via Nonmonotonic Learning Rate Scheduling
- Blog: The Second Place Solution for The 4th Large-scale Video Object Segmentation Challenge-Track 3: Referring Video Object Segmentation
- Blog: Use neural networks to recognize students' handwritten letters and incorrect symbols
- Blog: Pixel Is All You Need: Adversarial Trajectory-Ensemble Active Learning for Salient Object Detection
- Blog: PWR Core Loading Pattern Design Assisted by Artificial Intelligence
- Blog: Performance evaluation of mainstream chromosome recognition algorithms under deep learning
- Blog: There Are Many Consistent Explanations of Unlabeled Data: Why You Should Average
- Blog: Assessing Robustness of Deep learning Methods in Dermatological Workflow
- Blog: Transfer Learning for Predicting Conversion from Mild Cognitive Impairment to Dementia of Alzheimer’s Type based on 3D-Convolutional Neural Network
- Blog: Decoupled Weight Decay Regularization
- Blog: DFML: Decentralized Federated Mutual Learning
- Blog: Improving Multi-fidelity Optimization with a Recurring Learning Rate for Hyperparameter Tuning
- Blog: CYFLOD: Cyclic Filtering and Loss Damping for Alleviating Noisy Labels in Fine-grained Visual Classification
- Blog: Enhancing Language Model Hypernetworks with Restart: A Study on Optimization
- Blog: Improving image classifiers for small datasets by learning rate adaptations
- Blog: Variational Annealing on Graphs for Combinatorial Optimization
- Blog: Extremely Lightweight Quantization Robust Real-Time Single-Image Super Resolution for Mobile Devices
- Blog: Online Embedding Compression for Text Classification Using Low Rank Matrix Factorization
- Blog: Collaborative deep learning across multiple data centers
- Blog: Causality-Respecting Adaptive Refinement for PINNs: Enabling Precise Interface Evolution in Phase Field Modeling
- Blog: ERLP: Ensembles of Reinforcement Learning Policies (Student Abstract)
- Blog: 3D Object Reconstruction from Imperfect Depth Data Using Extended YOLOv3 Network
- Blog: Deep Learning for Visual Recognition of Environmental Enteropathy and Celiac Disease
- Blog: Demystifying Learning Rate Polices for High Accuracy Training of Deep Neural Networks
- Blog: TAC at SemEval-2020 Task 12: Ensembling Approach for Multilingual Offensive Language Identification in Social Media
- Blog: Training Scale-Invariant Neural Networks on the Sphere Can Happen in Three Regimes
- Blog: Enabling robust offline active learning for machine learning potentials using simple physics-based priors
- Blog: Automatic Classification of Whole Slide Pap Smear Images Using CNN With PCA Based Feature Interpretation
- Blog: Asymptotic theory of SGD with a general learning-rate
Showing 60 of 61 papers.
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_cyclic_learning_rate_scheduling_43ee7a27,
title = {cyclic learning rate scheduling},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/cyclic-learning-rate-scheduling/rdr_43ee7a2713f8466094b365d21a838b08},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 2, frozen text):
@misc{lacuna_cyclic_learning_rate_scheduling_43ee7a27_v2,
title = {cyclic learning rate scheduling},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/cyclic-learning-rate-scheduling/rdr_43ee7a2713f8466094b365d21a838b08/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-20},
}