Neural Network Optimization

SADDLe: Sharpness-Aware Decentralized Deep Learning with Heterogeneous Data WACV 2025 Scaling Collapse Reveals Universal Dynamics in Compute-Optimally Trained Neural Networks ICML 2025 Scaling LLM Test-Time Compute Optimally Can be More Effective than Scaling Parameters for Reasoning ICLR 2025 Scaling ResNets in the Large-depth Regime JMLR 2025 Scaling, Simplification, and Adaptation: Lessons from Pretraining on Machine-Translated Text EMNLP 2025 SDP-CROWN: Efficient Bound Propagation for Neural Network Verification with Tightness of Semidefinite Programming ICML 2025 Second-Order Fine-Tuning without Pain for LLMs: A Hessian Informed Zeroth-Order Optimizer ICLR 2025 Self-Adjust Softmax EMNLP 2025 Self-Aligning Depth-Regularized Radiance Fields for Asynchronous RGB-D Sequences WACV 2025 Self-Normalized Resets for Plasticity in Continual Learning ICLR 2025 Semi-Implicit Neural Ordinary Differential Equations AAAI 2025 Sensitivity-Aware Efficient Fine-Tuning via Compact Dynamic-Rank Adaptation CVPR 2025 Sensitivity-LoRA : Low-Load Sensitivity-Based Fine-Tuning for Large Language Models EMNLP 2025 SGD Jittering: A Training Strategy for Robust and Accurate Model-Based Architectures ICML 2025 Sharper Guarantees for Learning Neural Network Classifiers with Gradient Methods ICLR 2025 Sharpness-Aware Minimization Efficiently Selects Flatter Minima Late In Training ICLR 2025 Sharpness-Aware Minimization: General Analysis and Improved Rates ICLR 2025 Sharpness-aware Zeroth-order Optimization for Graph Transformers IJCAI 2025 ShortGPT: Layers in Large Language Models are More Redundant Than You Expect ACL 2025 SimpleTM: A Simple Baseline for Multivariate Time Series Forecasting ICLR 2025 Simplicity Bias and Optimization Threshold in Two-Layer ReLU Networks ICML 2025 Slamming: Training a Speech Language Model on One GPU in a Day ACL 2025 SLIM: Subtrajectory-Level Elimination for More Effective Reasoning EMNLP 2025 Smart-Searcher: Incentivizing the Dynamic Knowledge Acquisition of LLMs via Reinforcement Learning EMNLP 2025 SMMF: Square-Matricized Momentum Factorization for Memory-Efficient Optimization AAAI 2025