gradient descent

Learning Compositional Functions with Transformers from Easy-to-Hard Data COLT 2025 Learning Dynamics of Deep Matrix Factorization Beyond the Edge of Stability ICLR 2025 Learning High-Degree Parities: The Crucial Role of the Initialization ICLR 2025 Learning Multi-Index Models with Neural Networks via Mean-Field Langevin Dynamics ICLR 2025 Learning Task Representations from In-Context Learning ACL 2025 Learning to Generate Gradients for Test-Time Adaptation via Test-Time Training Layers AAAI 2025 Level Set Teleportation: An Optimization Perspective AISTATS 2025 Leveraging Per-Instance Privacy for Machine Unlearning ICML 2025 Leveraging Variable Sparsity to Refine Pareto Stationarity in Multi-Objective Optimization ICLR 2025 LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently ICML 2025 Loss Landscape of Shallow ReLU-like Neural Networks: Stationary Points, Saddle Escape, and Network Embedding ICLR 2025 LUSD: Localized Update Score Distillation for Text-Guided Image Editing ICCV 2025 Massively Parallel Continuous Local Search for Hybrid SAT Solving on GPUs AAAI 2025 Maximum Causal Entropy IRL in Mean-Field Games and GNEP Framework for Forward RL JMLR 2025 Memory-Reduced Meta-Learning with Guaranteed Convergence AAAI 2025 MeMoTune: A Measure and Moment-Driven Fine-Tuning Framework for Quantized Large Language Models ACL 2025 Metamizer: A Versatile Neural Optimizer for Fast and Accurate Physics Simulations ICLR 2025 Mitigating Visual Knowledge Forgetting in MLLM Instruction-tuning via Modality-decoupled Gradient Descent EMNLP 2025 Modeling Multi-Task Model Merging as Adaptive Projective Gradient Descent ICML 2025 Non-convex matrix sensing: Breaking the quadratic rank barrier in the sample complexity Extended Abstract COLT 2025 Nonparametric Teaching for Graph Property Learners ICML 2025 ODDN: Addressing Unpaired Data Challenges in Open-World Deepfake Detection on Online Social Networks AAAI 2025 On the Learn-to-Optimize Capabilities of Transformers in In-Context Sparse Recovery ICLR 2025 On the O(sqrt(d)/T^(1/4)) Convergence Rate of RMSProp and Its Momentum Extension Measured by l_1 Norm JMLR 2025 On the Power of Multitask Representation Learning with Gradient Descent AISTATS 2025