Title |
|---|
 How Neural Networks Extrapolate: From Feedforward to Graph Neural
NetworksInternational Conference on Learning Representations (ICLR), 2020 |
 Theoretical Analysis of the Advantage of Deepening Neural NetworksInternational Conference on Machine Learning and Applications (ICMLA), 2020 |
 How benign is benign overfitting?International Conference on Learning Representations (ICLR), 2020 |
 On the Number of Linear Regions of Convolutional Neural NetworksInternational Conference on Machine Learning (ICML), 2020 |
 Provably Good Solutions to the Knapsack Problem via Neural Networks of
Bounded SizeAAAI Conference on Artificial Intelligence (AAAI), 2020 |
 Piecewise linear activations substantially shape the loss surfaces of
neural networksInternational Conference on Learning Representations (ICLR), 2020 |
 Uncertainty Quantification for Sparse Deep LearningInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2020 |
 Investigating the Compositional Structure Of Deep Neural NetworksInternational Conference on Machine Learning, Optimization, and Data Science (MOD), 2020 |
 Self-explaining AI as an alternative to interpretable AIArtificial General Intelligence (AGI), 2020 |
 Empirical Studies on the Properties of Linear Regions in Deep Neural
NetworksInternational Conference on Learning Representations (ICLR), 2020 |
 Lossless Compression of Deep Neural NetworksIntegration of AI and OR Techniques in Constraint Programming (CPAIOR), 2020 |
 Trajectory growth lower bounds for random sparse deep ReLU networksInternational Conference on Machine Learning and Applications (ICMLA), 2019 |
 The Local Elasticity of Neural NetworksInternational Conference on Learning Representations (ICLR), 2019 Hangfeng He Weijie J. Su |
 Reverse-Engineering Deep ReLU NetworksInternational Conference on Machine Learning (ICML), 2019 |
 |
 Computing Linear Restrictions of Neural NetworksNeural Information Processing Systems (NeurIPS), 2019 |
 Gradient Dynamics of Shallow Univariate ReLU NetworksNeural Information Processing Systems (NeurIPS), 2019 |
 Deep ReLU Networks Have Surprisingly Few Activation PatternsNeural Information Processing Systems (NeurIPS), 2019 |
 Expression of Fractals Through Neural Network FunctionsIEEE Journal on Selected Areas in Information Theory (JSAIT), 2019 |
 The Geometry of Deep Networks: Power Diagram SubdivisionNeural Information Processing Systems (NeurIPS), 2019 |
