AAAI 2020 accepted papers on Optimization
27 of the 1,610 papers accepted at AAAI 2020 (1.7%) are on Optimization, compared with 2.1% at AAAI 2019. They fall into 4 topics.
See AAAI 2020 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
Optimizers · 10 papers
- Transparent Classification with Multilayer Logical Perceptrons and Random Binarization (35 citations)
- Characterizing Membership Privacy in Stochastic Gradient Langevin Dynamics (22 citations)
- How the Duration of the Learning Period Affects the Performance of Random Gradient Selection Hyper-Heuristics (20 citations)
- Inefficiency of K-FAC for Large Batch Size Training (19 citations)
- Low-Variance Black-Box Gradient Estimates for the Plackett-Luce Distribution (10 citations)
- An Implicit Form of Krasulina's k-PCA Update without the Orthonormality Constraint (6 citations)
- Robust Gradient-Based Markov Subsampling (6 citations)
- Infinity Learning: Learning Markov Chains from Aggregate Steady-State Observations (2 citations)
- Optimizing Nondecomposable Data Dependent Regularizers via Lagrangian Reparameterization Offers Significant Performance and Efficiency Gains (2 citations)
- Stochastic Approximate Gradient Descent via the Langevin Algorithm (1 citation)
Nonconvex and smooth optimization · 9 papers
- A Tale of Two-Timescale Reinforcement Learning with the Tightest Finite-Time Bound (44 citations)
- D-SPIDER-SFO: A Decentralized Optimization Algorithm with Faster Convergence Rate for Nonconvex Problems (11 citations)
- Apprenticeship Learning via Frank-Wolfe (8 citations)
- Gradient Boosts the Approximate Vanishing Ideal (7 citations)
- A Stochastic Derivative-Free Optimization Method with Importance Sampling: Theory and Learning to Control (5 citations)
- An Effective Hard Thresholding Method Based on Stochastic Variance Reduction for Nonconvex Sparse Learning (3 citations)
- Projective Quadratic Regression for Online Learning (3 citations)
- SPAN: A Stochastic Projected Approximate Newton Method (2 citations)
- Model and Reinforcement Learning for Markov Games with Risk Preferences
Distributed and compressed · 5 papers
- On the Discrepancy between the Theoretical Analysis and Practical Implementations of Compressed Communication for Distributed Deep Learning (66 citations)
- Quantized Compressive Sampling of Stochastic Gradients for Efficient Communication in Distributed Deep Learning (35 citations)
- Distributed Stochastic Gradient Descent with Event-Triggered Communication (28 citations)
- Delay-Adaptive Distributed Stochastic Optimization (8 citations)
- Indirect Stochastic Gradient Quantization and Its Application in Distributed Deep Learning (5 citations)
