Optimization

CR-SAM: Curvature Regularized Sharpness-Aware Minimization AAAI 2024 Decoding Matters: Addressing Amplification Bias and Homogeneity Issue in Recommendations for Large Language Models EMNLP 2024 Decoupled Kullback-Leibler Divergence Loss NeurIPS 2024 DeepBern-Nets: Taming the Complexity of Certifying Neural Networks Using Bernstein Polynomial Activations and Precise Bound Propagation AAAI 2024 Deep Graph Neural Networks via Posteriori-Sampling-based Node-Adaptative Residual Module NeurIPS 2024 Deep linear networks for regression are implicitly regularized towards flat minima NeurIPS 2024 Deep Plug-and-Play Nighttime Non-Blind Deblurring With Saturated Pixel Handling Schemes WACV 2024 DeepSpeed Data Efficiency: Improving Deep Learning Model Quality and Training Efficiency via Efficient Data Sampling and Routing AAAI 2024 DeltaDEQ: Exploiting Heterogeneous Convergence for Accelerating Deep Equilibrium Iterations NeurIPS 2024 DiffAvatar: Simulation-Ready Garment Optimization with Differentiable Simulation CVPR 2024 Differentially Private Optimization with Sparse Gradients NeurIPS 2024 Differentially Private SGD Without Clipping Bias: An Error-Feedback Approach ICLR 2024 DiP-GO: A Diffusion Pruner via Few-step Gradient Optimization NeurIPS 2024 Distribution Alignment Optimization through Neural Collapse for Long-tailed Classification ICML 2024 Distributional Reinforcement Learning with Regularized Wasserstein Loss NeurIPS 2024 DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models CVPR 2024 DreamPropeller: Supercharge Text-to-3D Generation with Parallel Sampling CVPR 2024 DreamTime: An Improved Optimization Strategy for Diffusion-Guided 3D Generation ICLR 2024 Dr.Hair: Reconstructing Scalp-Connected Hair Strands without Pre-Training via Differentiable Rendering of Line Segments CVPR 2024 Dual Lagrangian Learning for Conic Optimization NeurIPS 2024 DuQuant: Distributing Outliers via Dual Transformation Makes Stronger Quantized LLMs NeurIPS 2024 Dynamic Neural Regeneration: Enhancing Deep Learning Generalization on Small Datasets NeurIPS 2024 ECLipsE: Efficient Compositional Lipschitz Constant Estimation for Deep Neural Networks NeurIPS 2024 EControl: Fast Distributed Optimization with Compression and Error Control ICLR 2024 Efficient Error Certification for Physics-Informed Neural Networks ICML 2024