Optimization

Optimal and Approximate Adaptive Stochastic Quantization NeurIPS 2024 Optimal deep learning of holomorphic operators between Banach spaces NeurIPS 2024 Optimal First-Order Algorithms as a Function of Inequalities JMLR 2024 Optimistic Verifiable Training by Controlling Hardware Nondeterminism NeurIPS 2024 Optimized Speculative Sampling for GPU Hardware Accelerators EMNLP 2024 Optimizing ADMM and Over-Relaxed ADMM Parameters for Linear Quadratic Problems AAAI 2024 Optimizing Diffusion Noise Can Serve As Universal Motion Priors CVPR 2024 Orchid: Flexible and Data-Dependent Convolution for Sequence Modeling NeurIPS 2024 ORPO: Monolithic Preference Optimization without Reference Model EMNLP 2024 PACE: Pacing Operator Learning to Accurate Optical Field Simulation for Complicated Photonic Devices NeurIPS 2024 Parameter-Agnostic Optimization under Relaxed Smoothness AISTATS 2024 Parameter Efficient Fine-tuning via Cross Block Orchestration for Segment Anything Model CVPR 2024 Parameter-free Clipped Gradient Descent Meets Polyak NeurIPS 2024 PDE+: Enhancing Generalization via PDE with Adaptive Distributional Diffusion AAAI 2024 PELA: Learning Parameter-Efficient Models with Low-Rank Approximation CVPR 2024 PeLK: Parameter-efficient Large Kernel ConvNets with Peripheral Convolution CVPR 2024 PeRFlow: Piecewise Rectified Flow as Universal Plug-and-Play Accelerator NeurIPS 2024 Persistence Homology Distillation for Semi-supervised Continual Learning NeurIPS 2024 PGMax: Factor Graphs for Discrete Probabilistic Graphical Models and Loopy Belief Propagation in JAX JMLR 2024 Physics-informed Neural Networks for Functional Differential Equations: Cylindrical Approximation and Its Convergence Guarantees NeurIPS 2024 PINNacle: A Comprehensive Benchmark of Physics-Informed Neural Networks for Solving PDEs NeurIPS 2024 Plum: Prompt Learning using Metaheuristics ACL 2024 Practical Shuffle Coding NeurIPS 2024 Preparing Lessons for Progressive Training on Language Models AAAI 2024 Pre-trained Large Language Models Use Fourier Features to Compute Addition NeurIPS 2024