neural network optimization

On the hardness of learning under symmetries ICLR 2024 On the Inductive Bias of Stacking Towards Improving Reasoning NeurIPS 2024 On the Limitations of Fractal Dimension as a Measure of Generalization NeurIPS 2024 On the Parameterization of Second-Order Optimization Effective towards the Infinite Width ICLR 2024 On the Power of Small-size Graph Neural Networks for Linear Programming NeurIPS 2024 On the Role of Attention Masks and LayerNorm in Transformers NeurIPS 2024 On the Unstable Convergence Regime of Gradient Descent AAAI 2024 OptEx: Expediting First-Order Optimization with Approximately Parallelized Iterations NeurIPS 2024 Outliers with Opposing Signals Have an Outsized Effect on Neural Network Optimization ICLR 2024 Parameter-free Clipped Gradient Descent Meets Polyak NeurIPS 2024 ParameterNet: Parameters Are All You Need for Large-scale Visual Pretraining of Mobile Networks CVPR 2024 Parameter Symmetry and Noise Equilibrium of Stochastic Gradient Descent NeurIPS 2024 Parseval Regularization for Continual Reinforcement Learning NeurIPS 2024 Physics-Informed Neural Networks: Minimizing Residual Loss with Wide Networks and Effective Activations IJCAI 2024 PikeLPN: Mitigating Overlooked Inefficiencies of Low-Precision Neural Networks CVPR 2024 PINNacle: A Comprehensive Benchmark of Physics-Informed Neural Networks for Solving PDEs NeurIPS 2024 Post-Hoc Reversal: Are We Selecting Models Prematurely? NeurIPS 2024 Predictor-Corrector Enhanced Transformers with Exponential Moving Average Coefficient Learning NeurIPS 2024 Preparing Lessons for Progressive Training on Language Models AAAI 2024 Pretraining with Random Noise for Fast and Robust Learning without Weight Transport NeurIPS 2024 PRILoRA: Pruned and Rank-Increasing Low-Rank Adaptation EACL 2024 Principled Architecture-aware Scaling of Hyperparameters ICLR 2024 Provably Transformers Harness Multi-Concept Word Semantics for Efficient In-Context Learning NeurIPS 2024 PTQ4DiT: Post-training Quantization for Diffusion Transformers NeurIPS 2024 PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM Compression NeurIPS 2024