| Deep Hidden Physics Models: Deep Learning of Nonlinear Partial Differential Equations |
49 |
| Neural Architecture Search: A Survey |
43 |
| Automatic Differentiation in Machine Learning: a Survey |
29 |
| To Tune or Not to Tune the Number of Trees in Random Forest |
26 |
| Pyro: Deep Universal Probabilistic Programming |
26 |
| All Models are Wrong, but Many are Useful: Learning a Variable's Importance by Studying an Entire Class of Prediction Models Simultaneously |
25 |
| Emergence of Invariance and Disentanglement in Deep Representations |
22 |
| PyOD: A Python Toolbox for Scalable Outlier Detection |
22 |
| Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations |
20 |
| Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization |
20 |
| Community Detection and Stochastic Block Models: Recent Developments |
20 |
| Deep Optimal Stopping |
18 |
| Scikit-Multiflow: A Multi-output Streaming Framework |
17 |
| TensorLy: Tensor Learning in Python |
17 |
| iNNvestigate Neural Networks! |
17 |
| The Implicit Bias of Gradient Descent on Separable Data |
14 |
| Tunability: Importance of Hyperparameters of Machine Learning Algorithms |
14 |
| Permuted and Augmented Stick-Breaking Bayesian Multinomial Regression |
13 |
| RSG: Beating Subgradient Method without Smoothness and Strong Convexity |
10 |
| Gradient Descent Learns Linear Dynamical Systems |
10 |
| How Deep Are Deep Gaussian Processes? |
10 |
| Forward-Backward Selection with Early Dropping |
9 |
| Approximate Profile Maximum Likelihood |
9 |
| ThunderSVM: A Fast SVM Library on GPUs and CPUs |
9 |
| Invariant Models for Causal Transfer Learning |
9 |
| Multi-class Heterogeneous Domain Adaptation |
8 |
| On the Stability of Feature Selection Algorithms |
8 |
| Robust Frequent Directions with Application in Online Learning |
8 |
| Deep Reinforcement Learning for Swarm Systems |
8 |
| Statistical Inference on Random Dot Product Graphs: a Survey |
7 |
| Variational Fourier Features for Gaussian Processes |
7 |
| Fairness Constraints: A Flexible Approach for Fair Classification |
7 |
| Provably Correct Algorithms for Matrix Column Subset Selection with Selectively Sampled Data |
7 |
| Nearly-tight VC-dimension and Pseudodimension Bounds for Piecewise Linear Neural Networks |
7 |
| Parallelizing Spectrally Regularized Kernel Algorithms |
7 |
| Parsimonious Online Learning with Kernels via Sparse Projections in Function Space |
6 |
| Scalable Bayes via Barycenter in Wasserstein Space |
6 |
| A Robust Learning Approach for Regression Models Based on Distributionally Robust Optimization |
6 |
| Probabilistic preference learning with the Mallows rank model |
6 |
| pomegranate: Fast and Flexible Probabilistic Modeling in Python |
6 |
| Differentiable reservoir computing |
5 |
| Measuring the Effects of Data Parallelism on Neural Network Training |
5 |
| A Constructive Approach to L-0 Penalized Regression |
5 |
| Matched Bipartite Block Model with Covariates |
5 |
| A Representer Theorem for Deep Neural Networks |
5 |
| Time-to-Event Prediction with Neural Networks and Cox Regression |
5 |
| Scalable Interpretable Multi-Response Regression via SEED |
5 |
| Multi-scale Online Learning: Theory and Applications to Online Auctions and Pricing |
5 |
| Parallelizing Stochastic Gradient Descent for Least Squares Regression: Mini-batching, Averaging, and Model Misspecification |
5 |
| Random Forests, Decision Trees, and Categorical Predictors: The Absent Levels Problem |
5 |
