← Optimization & Theory
Deep Learning › Optimization & Theory ›

Optimization

1638 directly classified papers

Papers per year

Papers

Lipschitz-Certifiable Training with a Tight Outer Bound NIPS 2020
Efficient Algorithms for Device Placement of DNN Graph Operators NIPS 2020
Coresets via Bilevel Optimization for Continual Learning and Streaming NIPS 2020
AdaTune: Adaptive Tensor Program Compilation Made Efficient NIPS 2020
Optimistic Dual Extrapolation for Coherent Non-monotone Variational Inequalities NIPS 2020
Instead of Rewriting Foreign Code for Machine Learning, Automatically Synthesize Fast Gradients NIPS 2020
Learning to solve TV regularised problems with unrolled algorithms NIPS 2020
An implicit function learning approach for parametric modal regression NIPS 2020
Hybrid Variance-Reduced SGD Algorithms For Minimax Problems with Nonconvex-Linear Function NIPS 2020
Efficient Projection-free Algorithms for Saddle Point Problems NIPS 2020
Conic Descent and its Application to Memory-efficient Optimization over Positive Semidefinite Matrices NIPS 2020
An efficient nonconvex reformulation of stagewise convex optimization problems NIPS 2020
Understanding the Role of Training Regimes in Continual Learning NIPS 2020
Regularized linear autoencoders recover the principal components, eventually NIPS 2020
Minibatch vs Local SGD for Heterogeneous Distributed Learning NIPS 2020
Random Reshuffling is Not Always Better NIPS 2020
On the training dynamics of deep networks with $L_2$ regularization NIPS 2020
Efficient Low Rank Gaussian Variational Inference for Neural Networks NIPS 2020
Benchmarking Deep Inverse Models over time, and the Neural-Adjoint method NIPS 2020
SPAN: A Stochastic Projected Approximate Newton Method AAAI 2020
Information-Theoretic Understanding of Population Risk Improvement with Model Compression AAAI 2020
RTN: Reparameterized Ternary Network AAAI 2020
Learning to Auto Weight: Entirely Data-Driven and Highly Efficient Weighting Framework AAAI 2020
AutoCompress: An Automatic DNN Structured Pruning Framework for Ultra-High Compression Rates AAAI 2020
Stochastic Loss Function AAAI 2020