Theory

Uniform-PAC Bounds for Reinforcement Learning with Linear Function Approximation NeurIPS 2021 Unifying lower bounds on prediction dimension of convex surrogates NeurIPS 2021 UNIPoint: Universally Approximating Point Processes Intensities AAAI 2021 Universal Rate-Distortion-Perception Representations for Lossy Compression NeurIPS 2021 Universal Spectral Adversarial Attacks for Deformable Shapes CVPR 2021 Unsupervised Representation Disentanglement of Text: An Evaluation on Synthetic Datasets ACL 2021 Validating the Lottery Ticket Hypothesis with Inertial Manifold Theory NeurIPS 2021 Vector-output ReLU Neural Network Problems are Copositive Programs: Convex Analysis of Two Layer Networks and Polynomial-time Algorithms ICLR 2021 Verifying Reinforcement Learning up to Infinity IJCAI 2021 Visualizing the Emergence of Intermediate Visual Patterns in DNNs NeurIPS 2021 V-statistics and Variance Estimation JMLR 2021 We Need to Consider Disagreement in Evaluation ACL 2021 WGAN with an Infinitely Wide Generator Has No Spurious Stationary Points ICML 2021 What can linearized neural networks actually say about generalization? NeurIPS 2021 What is SemEval evaluating? A Systematic Analysis of Evaluation Campaigns in NLP EMNLP 2021 What’s the Context? Implicit and Explicit Assumptions in Model-Based Goal Recognition IJCAI 2021 What training reveals about neural network complexity NeurIPS 2021 When Are Solutions Connected in Deep Networks? NeurIPS 2021 When does preconditioning help or hurt generalization? ICLR 2021 When Expressivity Meets Trainability: Fewer than n Neurons Can Work NeurIPS 2021 Which transformer architecture fits my data? A vocabulary bottleneck in self-attention ICML 2021 Why Adversarial Interaction Creates Non-Homogeneous Patterns: A Pseudo-Reaction-Diffusion Model for Turing Instability AAAI 2021 Why Do Document-Level Polarity Classifiers Fail? NAACL 2021 Abstract Interpretation of Decision Tree Ensemble Classifiers AAAI 2020 A closer look at the approximation capabilities of neural networks ICLR 2020