← Optimization & Theory
Deep Learning › Optimization & Theory ›

Optimization

1638 directly classified papers

Papers per year

Papers

LQF: Linear Quadratic Fine-Tuning CVPR 2021
Riggable 3D Face Reconstruction via In-Network Optimization CVPR 2021
Asymmetric Gained Deep Image Compression With Continuous Rate Adaptation CVPR 2021
Optimal Gradient Checkpoint Search for Arbitrary Computation Graphs CVPR 2021
A Decomposition Model for Stereo Matching CVPR 2021
Domain-Independent Dominance of Adaptive Methods CVPR 2021
Permute, Quantize, and Fine-Tune: Efficient Compression of Neural Networks CVPR 2021
3D CNNs With Adaptive Temporal Feature Resolutions CVPR 2021
A Sliced Wasserstein Loss for Neural Texture Synthesis CVPR 2021
A Second-Order Approach to Learning With Instance-Dependent Label Noise CVPR 2021
Hilbert Sinkhorn Divergence for Optimal Transport CVPR 2021
A Generalized Loss Function for Crowd Counting and Localization CVPR 2021
SKFAC: Training Neural Networks With Faster Kronecker-Factored Approximate Curvature CVPR 2021
Cooperative SGD: A Unified Framework for the Design and Analysis of Local-Update SGD Algorithms JMLR 2021
When Does Gradient Descent with Logistic Loss Find Interpolating Two-Layer Networks? JMLR 2021
An algorithmic view of L2 regularization and some path-following algorithms JMLR 2021
An Inertial Newton Algorithm for Deep Learning JMLR 2021
NUQSGD: Provably Communication-efficient Data-parallel SGD via Nonuniform Quantization JMLR 2021
A Unified Analysis of First-Order Methods for Smooth Games via Integral Quadratic Constraints JMLR 2021
Revisiting the Role of Euler Numerical Integration on Acceleration and Stability in Convex Optimization AISTATS 2021
A Dynamical View on Optimization Algorithms of Overparameterized Neural Networks AISTATS 2021
Learning with Gradient Descent and Weakly Convex Losses AISTATS 2021
Adaptive wavelet pooling for convolutional neural networks AISTATS 2021
Stochastic Polyak Step-size for SGD: An Adaptive Learning Rate for Fast Convergence AISTATS 2021
Alternating Direction Method of Multipliers for Quantization AISTATS 2021