← Optimization & Theory
Deep Learning › Optimization & Theory ›

Optimization

1638 directly classified papers

Papers per year

Papers

Auto-NBA: Efficient and Effective Search Over the Joint Space of Networks, Bitwidths, and Accelerators ICML 2021
Revealing the Structure of Deep Neural Networks via Convex Duality ICML 2021
Newton Method over Networks is Fast up to the Statistical Precision ICML 2021
Principal Bit Analysis: Autoencoding with Schur-Concave Loss ICML 2021
Loss Surface Simplexes for Mode Connecting Volumes and Fast Ensembling ICML 2021
Training Quantized Neural Networks to Global Optimality via Semidefinite Programming ICML 2021
Slot Machines: Discovering Winning Combinations of Random Weights in Neural Networks ICML 2021
Acceleration via Fractal Learning Rate Schedules ICML 2021
Sequence Length is a Domain: Length-based Overfitting in Transformer Models EMNLP 2021
MTAdam: Automatic Balancing of Multiple Training Loss Terms EMNLP 2021
Improving Privacy Guarantee and Efficiency of Latent Dirichlet Allocation Model Training Under Differential Privacy EMNLP 2021
Corrected CBOW Performs as well as Skip-gram EMNLP 2021
EASE: Extractive-Abstractive Summarization End-to-End using the Information Bottleneck Principle EMNLP 2021
Low Resource Quadratic Forms for Knowledge Graph Embeddings EMNLP 2021
Speeding Up Transformer Training By Using Dataset Subsampling - An Exploratory Analysis EMNLP 2021
Hyperparameter Power Impact in Transformer Language Model Training EMNLP 2021
Automated Log-Scale Quantization for Low-Cost Deep Neural Networks CVPR 2021
Achieving Robustness in Classification Using Optimal Transport With Hinge Regularization CVPR 2021
Towards Efficient Tensor Decomposition-Based DNN Model Compression With Optimization Framework CVPR 2021
Limitations of Post-Hoc Feature Alignment for Robustness CVPR 2021
Neural Reprojection Error: Merging Feature Learning and Camera Pose Estimation CVPR 2021
Cross Modal Focal Loss for RGBD Face Anti-Spoofing CVPR 2021
Tangent Space Backpropagation for 3D Transformation Groups CVPR 2021
Architectural Adversarial Robustness: The Case for Deep Pursuit CVPR 2021
GrooMeD-NMS: Grouped Mathematically Differentiable NMS for Monocular 3D Object Detection CVPR 2021