| 1 |
An Empirical Study of Example Forgetting during Deep Neural Network Learning |
ICLR |
2019 |
| 2 |
ROBUSTNESS May Be at ODDS WITH ACCURACY |
ICLR |
2019 |
| 3 |
Critical Learning Periods in Deep Networks |
ICLR |
2019 |
| 4 |
LEARNING ROBUST REPRESENTATIONS BY PROJECTING SUPERFICIAL STATISTICS OUT |
ICLR |
2019 |
| 5 |
Classification from Positive, Unlabeled and Biased Negative Data |
ICLR |
2019 |
| 6 |
Select Via Proxy: Efficient Data Selection For Training Deep Networks |
ICLR |
2019 |
| 7 |
Using Pre-Training Can Improve Model Robustness and Uncertainty |
ICML |
2019 |
| 8 |
On Learning Invariant Representations for Domain Adaptation |
ICML |
2019 |
| 9 |
Fine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural Networks |
ICML |
2019 |
| 10 |
Gradient Descent Finds Global Minima of Deep Neural Networks |
ICML |
2019 |
| 11 |
When Samples Are Strategically Selected |
ICML |
2019 |
| 12 |
The Odds are Odd: A Statistical Test for Detecting Adversarial Examples |
ICML |
2019 |
| 13 |
Bias Also Matters: Bias Attribution for Deep Neural Network Explanation |
ICML |
2019 |
| 14 |
Escaping Saddle Points with Adaptive Gradient Methods |
ICML |
2019 |
| 15 |
Parameter-Efficient Transfer Learning for NLP |
ICML |
2019 |
| 16 |
Visualizing the Loss Landscape of Neural Nets |
NeurIPS |
2018 |
| 17 |
Modern Neural Networks Generalize on Small Data Sets |
NeurIPS |
2018 |
| 18 |
Generative modeling for protein structures |
NeurIPS |
2018 |
| 19 |
On Binary Classification in Extreme Regions |
NeurIPS |
2018 |
| 20 |
The Description Length of Deep Learning models |
NeurIPS |
2018 |
| 21 |
L1-regression with Heavy-tailed Distributions |
NeurIPS |
2018 |
| 22 |
Dynamic Network Model from Partial Observations |
NeurIPS |
2018 |
| 23 |
Learning Invariances using the Marginal Likelihood |
NeurIPS |
2018 |
| 24 |
How SGD Selects the Global Minima in Over-parameterized Learning: A Dynamical Stability Perspective |
NeurIPS |
2018 |
| 25 |
On the Local Minima of the Empirical Risk |
NeurIPS |
2018 |
| 26 |
Human-in-the-Loop Interpretability Prior |
NeurIPS |
2018 |
| 27 |
Processing of missing data by neural networks |
NeurIPS |
2018 |
| 28 |
Maximum-Entropy Fine Grained Classification |
NeurIPS |
2018 |
| 29 |
Deep Structured Prediction with Nonlinear Output Transformations |
NeurIPS |
2018 |
| 30 |
Large Margin Deep Networks for Classification |
NeurIPS |
2018 |
| 31 |
Towards Understanding Learning Representations: To What Extent Do Different Neural Networks Learn the Same Representation |
NeurIPS |
2018 |
| 32 |
Norm matters: efficient and accurate normalization schemes in deep networks |
NeurIPS |
2018 |
| 33 |
Query K-means Clustering and the Double Dixie Cup Problem |
NeurIPS |
2018 |
| 34 |
Bilevel learning of the Group Lasso structure |
NeurIPS |
2018 |
| 35 |
Loss Functions for Multiset Prediction |
NeurIPS |
2018 |
| 36 |
Active Learning for Non-Parametric Regression Using Purely Random Trees |
NeurIPS |
2018 |
| 37 |
Model compression via distillation and quantization |
ICLR |
2018 |
| 38 |
The power of deeper networks for expressing natural functions |
ICLR |
2018 |
| 39 |
Decision Boundary Analysis of Adversarial Examples |
ICLR |
2018 |
| 40 |
On the Information Bottleneck Theory of Deep Learning |
ICLR |
2018 |
| 41 |
Sensitivity and Generalization in Neural Networks: an Empirical Study |
ICLR |
2018 |
| 42 |
Generating Wikipedia by Summarizing Long Sequences |
ICLR |
2018 |
| 43 |
Can Neural Networks Understand Logical Entailment? |
ICLR |
2018 |
| 44 |
Towards Reverse-Engineering Black-Box Neural Networks |
ICLR |
2018 |
| 45 |
The High-Dimensional Geometry of Binary Neural Networks |
ICLR |
2018 |
| 46 |
Detecting Statistical Interactions from Neural Network Weights |
ICLR |
2018 |
| 47 |
The Implicit Bias of Gradient Descent on Separable Data |
ICLR |
2018 |
| 48 |
Learning how to explain neural networks: PatternNet and PatternAttribution |
ICLR |
2018 |
| 49 |
GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models |
ICML |
2018 |
| 50 |
Which Training Methods for GANs do actually Converge? |
ICML |
2018 |
| 51 |
Nonoverlap-Promoting Variable Selection |
ICML |
2018 |
| 52 |
An Alternative View: When Does SGD Escape Local Minima? |
ICML |
2018 |
| 53 |
Stability and Generalization of Learning Algorithms that Converge to Global Optima |
ICML |
2018 |
| 54 |
Scalable Deletion-Robust Submodular Maximization: Data Summarization with Privacy and Fairness Constraints |
ICML |
2018 |
| 55 |
On the Optimization of Deep Networks: Implicit Acceleration by Overparameterization |
ICML |
2018 |
| 56 |
Escaping Saddles with Stochastic Gradients |
ICML |
2018 |
| 57 |
Deep Asymmetric Multi-task Feature Learning |
ICML |
2018 |
| 58 |
GNN Explainer: A Tool for Post-hoc Explanation of Graph Neural Networks |
KDD |
2018 |