← Optimization & Theory
Deep Learning › Optimization & Theory ›

Optimization

1638 directly classified papers

Papers per year

Papers

DPFPS: Dynamic and Progressive Filter Pruning for Compressing Convolutional Neural Networks from Scratch AAAI 2021
Fast and Compact Bilinear Pooling by Shifted Random Maclaurin AAAI 2021
Differentiable Fluids with Solid Coupling for Learning and Control AAAI 2021
Robust Model Compression Using Deep Hypotheses AAAI 2021
Understanding Decoupled and Early Weight Decay AAAI 2021
A Trace-restricted Kronecker-Factored Approximation to Natural Gradient AAAI 2021
Scaling-Up Robust Gradient Descent Techniques AAAI 2021
ACMo: Angle-Calibrated Moment Methods for Stochastic Optimization AAAI 2021
Large Batch Optimization for Deep Learning Using New Complete Layer-Wise Adaptive Rate Scaling AAAI 2021
Asynchronous Optimization Methods for Efficient Training of Deep Neural Networks with Guarantees AAAI 2021
Learning Graph Neural Networks with Approximate Gradient Descent AAAI 2021
Unchain the Search Space with Hierarchical Differentiable Architecture Search AAAI 2021
On the Adequacy of Untuned Warmup for Adaptive Optimization AAAI 2021
Learning Dynamics Models with Stable Invariant Sets AAAI 2021
Non-asymptotic Convergence of Adam-type Reinforcement Learning Algorithms under Markovian Sampling AAAI 2021
Correlation-Aware Heuristic Search for Intelligent Virtual Machine Provisioning in Cloud Systems AAAI 2021
Reducing Neural Network Parameter Initialization Into an SMT Problem (Student Abstract) AAAI 2021
LocalNewton: Reducing communication rounds for distributed learning UAI 2021
Faster Policy Learning with Continuous-Time Gradients L4DC 2021
Analysis of the Optimization Landscape of Linear Quadratic Gaussian (LQG) Control L4DC 2021
PET: Optimizing Tensor Programs with Partially Equivalent Transformations and Automated Corrections OSDI 2021
On Orthogonality Constraints for Transformers ACL 2021
Projection Robust Wasserstein Barycenters ICML 2021
MARINA: Faster Non-Convex Distributed Learning with Compression ICML 2021
Global Optimality Beyond Two Layers: Training Deep ReLU Networks via Convex Programs ICML 2021