AAAI 2019 accepted papers on Optimization
24 of the 1,147 papers accepted at AAAI 2019 (2.1%) are on Optimization, compared with 1.4% at AAAI 2018. They fall into 4 topics.
See AAAI 2019 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest papers by meaning and how crowded the spot has become.
Topics and papers
Nonconvex and smooth optimization · 12 papers
- Explicitly Imposing Constraints in Deep Networks via Conditional Gradients Gives Improved Generalization and Faster Convergence (51 citations)
- Robust Optimization over Multiple Domains (50 citations)
- Differentially Private Empirical Risk Minimization with Smooth Non-Convex Loss Functions: A Non-Stationary View (45 citations)
- Non-Ergodic Convergence Analysis of Heavy-Ball Algorithms (44 citations)
- Faster Gradient-Free Proximal Stochastic Methods for Nonconvex Nonsmooth Optimization (21 citations)
- A Non–Convex Optimization Approach to Correlation Clustering (16 citations)
- Revisiting Projection-Free Optimization for Strongly Convex Constraint Sets (8 citations)
- Asynchronous Proximal Stochastic Gradient Algorithm for Composition Optimization Problems (6 citations)
- Task Embedded Coordinate Update: A Realizable Framework for Multivariate Non-Convex Optimization (4 citations)
- Coreset Stochastic Variance-Reduced Gradient with Application to Optimal Margin Distribution Machine (3 citations)
- Asynchronous Delay-Aware Accelerated Proximal Coordinate Descent for Nonconvex Nonsmooth Problems (1 citation)
- Adaptive Proximal Average Based Variance Reducing Stochastic Methods for Optimization with Composite Regularization
Optimizers · 7 papers
- Active Mini-Batch Sampling Using Repulsive Point Processes (44 citations)
- HyperAdam: A Learnable Task-Adaptive Adam for Network Training (23 citations)
- Cogra: Concept-Drift-Aware Stochastic Gradient Descent for Time-Series Forecasting (21 citations)
- Scalable and Efficient Pairwise Learning to Achieve Statistical Accuracy (13 citations)
- Meta-Descent for Online, Continual Prediction (11 citations)
- Communication-Efficient Stochastic Gradient MCMC for Neural Networks (10 citations)
- Calibrated Stochastic Gradient Descent for Convolutional Neural Networks (9 citations)
Distributed and compressed · 3 papers
- Parallel Restarted SGD with Faster Convergence and Less Communication: Demystifying Why Model Averaging Works for Deep Learning (548 citations)
- RSA: Byzantine-Robust Stochastic Aggregation Methods for Distributed Learning from Heterogeneous Datasets (422 citations)
- Scalable Distributed DL Training: Batching Communication and Computation (40 citations)
Implicit bias and generalization · 2 papers
- Lifted Proximal Operator Machines (29 citations)
- Non-Parametric Transformation Networks for Learning General Invariances from Data (6 citations)
