1、Dynamic Pricing and Matching in Ride-Hailing Platforms

2、A taxi order dispatch model based on combinatorial optimization

3、Aircraft Design Optimization

4、101 Formulaic Alphas

5、Adam: A Method for Stochastic Optimization

6、Adaptive Subgradient Methods for Online Learning and Stochastic Optimization

7、A Survey of Optimization Methods from a Machine Learning Perspective

8、A Comparison of Optimization Algorithms for Deep Learning

9、ADADELTA: An Adaptive Learning Rate Method

10、A novel particle swarm optimization algorithm with Levy flight

11、A survey of swarm intelligence for dynamic optimization: Algorithms and applications

1、Learning Convolutional Neural Networks for Graphs

2、Semi-supervised classification with graph convolutional networks

3、Convolutional neural networks on graphs with fast localized spectral filtering

4、Deep Convolutional Networks on Graph-Structured Data

5、Graph Attention Networks

6、Inductive Representation Learning on Large Graphs

7、HyperGCN: A New Method of Training Graph Convolutional Networks on Hypergraphs

8、Modeling relational data with graph convolutional networks

1、Latent dirichlet allocation

2、Bayesian learning via stochastic gradient Langevin dynamics

3、What uncertainties do we need in bayesian deep learning for computer vision?

4、A survey on Bayesian deep learning

5、Evaluating bayesian deep learning methods for semantic segmentation

6、Deep Bayesian natural language processing

7、Quantifying uncertainties in natural language processing tasks

8、An introduction to MCMC for machine learning

9、Bayesian graph convolutional neural networks for semi-supervised classification

10、November. Bayesian graph neural networks with adaptive connection sampling

11、Practical bayesian optimization of machine learning algorithms

12、Stochastic variational inference

1、Human-level control through deep reinforcement learning

2、Mastering the game of go without human knowledge

3、Resource management with deep reinforcement learning

4、Tuning recurrent neural networks with reinforcement learning

5、The predictron: End-to-end learning and planning

6、Towards generalization and simplicity in continuous control

7、An algorithmic perspective on imitation learning

8、Generative adversarial imitation learning

9、Sim-to-Real: Learning Agile Locomotion For Quadruped Robots

10、Deal or no deal? end-to-end learning for negotiation dialogues

11、Applying reinforcement learning for web pages ranking algorithms

12、Using confidence bounds for exploitation-exploration trade-offs

13、Thompson sampling for contextual bandits with linear payoffs

14、Curiosity-driven exploration by self-supervised prediction

15、A Survey of Exploration Strategies in Reinforcement Learning

16、Schema networks: Zero-shot transfer with a generative causal model of intuitive physics

17、Deep reinforcement learning: An overview

18、Deep Reinforcement Learning For Sequence to Sequence Models Apprenticeship learning via inverse reinforcement learning