← Optimization & Theory
Deep Learning › Optimization & Theory ›

Optimization

1638 directly classified papers

Papers per year

Papers

Neural Flow Diffusion Models: Learnable Forward Process for Improved Diffusion Modelling NIPS 2024
Towards Scalable and Stable Parallelization of Nonlinear RNNs NIPS 2024
Common Diffusion Noise Schedules and Sample Steps Are Flawed WACV 2024
Towards Fast Multilingual LLM Inference: Speculative Decoding and Specialized Drafters EMNLP 2024
Integrating GNN and Neural ODEs for Estimating Non-Reciprocal Two-Body Interactions in Mixed-Species Collective Motion NIPS 2024
Layer-Wise Auto-Weighting for Non-Stationary Test-Time Adaptation WACV 2024
Favoring One Among Equals - Not a Good Idea: Many-to-One Matching for Robust Transformer Based Pedestrian Detection WACV 2024
ADOPT: Modified Adam Can Converge with Any $\beta_2$ with the Optimal Rate NIPS 2024
A Generic and Flexible Regularization Framework for NeRFs WACV 2024
Decoding Matters: Addressing Amplification Bias and Homogeneity Issue in Recommendations for Large Language Models EMNLP 2024
ORPO: Monolithic Preference Optimization without Reference Model EMNLP 2024
Even Sparser Graph Transformers NIPS 2024
The Star Geometry of Critic-Based Regularizer Learning NIPS 2024
2DQuant: Low-bit Post-Training Quantization for Image Super-Resolution NIPS 2024
MetaLA: Unified Optimal Linear Approximation to Softmax Attention Map NIPS 2024
Tensor-Based Synchronization and the Low-Rankness of the Block Trifocal Tensor NIPS 2024
Group and Shuffle: Efficient Structured Orthogonal Parametrization NIPS 2024
OptEx: Expediting First-Order Optimization with Approximately Parallelized Iterations NIPS 2024
SOI: Scaling Down Computational Complexity by Estimating Partial States of the Model NIPS 2024
Symmetry-Informed Governing Equation Discovery NIPS 2024
Fast Forwarding Low-Rank Training EMNLP 2024
Training Binary Neural Networks via Gaussian Variational Inference and Low-Rank Semidefinite Programming NIPS 2024
Differentially Private Optimization with Sparse Gradients NIPS 2024
Provably Transformers Harness Multi-Concept Word Semantics for Efficient In-Context Learning NIPS 2024
PTQ4DiT: Post-training Quantization for Diffusion Transformers NIPS 2024