conftrace_

learning rate

192 papers

Explore in graph

Also known as

LR

Co-occurring keywords

stochastic gradient descent (1091) neural network optimization (1293) gradient descent (1144) convergence rate (607) convergence analysis (395) stochastic optimization (1060) online learning (1777) kernel methods (1097) neural network (6616) regret bound (1926)

Papers

Optimizer Choice and Calibration for QARiB on Arabic-Script Social Media Offensive Language Detection EACL 2026
Good regularity creates large learning rate implicit biases: edge of stability, balancing, and catapult JMLR 2025
ALRMR-GEC: Adjusting Learning Rate Based on Memory Rate to Optimize the Edit Scorer for Grammatical Error Correction AAAI 2025
HVAdam: A Full-Dimension Adaptive Optimizer AAAI 2025
Learning Is Not A Race: Improving Retrieval in Language Models via Equal Learning EMNLP 2025
Large Learning Rates Simultaneously Achieve Robustness to Spurious Correlations and Compressibility ICCV 2025
Theoretical Insights into Fine-Tuning Attention Mechanism: Generalization and Optimization IJCAI 2025
Stabilizing Sharpness-Aware Minimization Through A Simple Renormalization Strategy JMLR 2025
Taming LLMs with Gradient Grouping ACL 2025
The Warmup Dilemma: How Learning Rate Strategies Impact Speech-to-Text Model Convergence ACL 2025
Kernel-based L_2-Boosting with Structure Constraints JMLR 2025
Towards Improved Risk Bounds for Transductive Learning IJCAI 2025
Optimal Rates for Vector-Valued Spectral Regularization Learning Algorithms NIPS 2024
Universal Rates for Active Learning NIPS 2024
The Sample Complexity of Gradient Descent in Stochastic Convex Optimization NIPS 2024
On the Hyperparameters in Stochastic Gradient Descent with Momentum JMLR 2024
Adaptive Learning Rate for Follow-the-Regularized-Leader: Competitive Analysis and Best-of-Both-Worlds COLT 2024
On the Unstable Convergence Regime of Gradient Descent AAAI 2024
Iterate Averaging in the Quest for Best Test Error JMLR 2024
Exact Mean Square Linear Stability Analysis for SGD COLT 2024
Small steps no more: Global convergence of stochastic gradient bandits for arbitrary learning rates NIPS 2024
Parameter-free Clipped Gradient Descent Meets Polyak NIPS 2024
Stable Minima Cannot Overfit in Univariate ReLU Networks: Generalization by Large Step Sizes NIPS 2024
Get rich quick: exact solutions reveal how unbalanced initializations promote rapid feature learning NIPS 2024
ADOPT: Modified Adam Can Converge with Any $\beta_2$ with the Optimal Rate NIPS 2024