theoretical analysis

Climbing towards NLU: On Meaning, Form, and Understanding in the Age of Data ACL 2020 Dual Learning: Theoretical Study and an Algorithmic Extension ACML 2020 On the Relationship between Self-Attention and Convolutional Layers ICLR 2020 Random Smoothing Might be Unable to Certify ℓ_∞ Robustness for High-Dimensional Images JMLR 2020 Rational neural networks NeurIPS 2020 (Re)construing Meaning in NLP ACL 2020 RNNs can generate bounded hierarchical languages with optimal memory EMNLP 2020 Stolen Probability: A Structural Weakness of Neural Language Models ACL 2020 The Expressive Power of a Class of Normalizing Flow Models AISTATS 2020 The Surprising Simplicity of the Early-Time Learning Dynamics of Neural Networks NeurIPS 2020 A Theory of State Abstraction for Reinforcement Learning AAAI 2019 Foundations of Sequence-to-Sequence Modeling for Time Series AISTATS 2019 Observations on Darwiche and Pearl's Approach for Iterated Belief Revision IJCAI 2019 Theoretical Analysis of Efficiency and Robustness of Softmax and Gap-Increasing Operators in Reinforcement Learning AISTATS 2019 Why do Larger Models Generalize Better? A Theoretical Perspective via the XOR Problem ICML 2019 A Theoretical Explanation for Perplexing Behaviors of Backpropagation-based Visualizations ICML 2018 A Theory-Based Evaluation of Nearest Neighbor Models Put Into Practice NeurIPS 2018 Expressive power of recurrent neural networks ICLR 2018 Learning One Convolutional Layer with Overlapping Patches ICML 2018 On the Cost Complexity of Crowdsourcing IJCAI 2018 Failures of Gradient-Based Deep Learning ICML 2017 Optimal Architectures in a Solvable Model of Deep Networks NeurIPS 2016 On the Accuracy of Self-Normalized Log-Linear Models NeurIPS 2015 Optimal Rates for Random Fourier Features NeurIPS 2015 Convex Optimization Procedure for Clustering: Theoretical Revisit NeurIPS 2014