Theory

Bounds all around: training energy-based models with bidirectional bounds NeurIPS 2021 Characterizing Structural Regularities of Labeled Data in Overparameterized Models ICML 2021 Convergence and Alignment of Gradient Descent with Random Backpropagation Weights NeurIPS 2021 Data and Parameter Scaling Laws for Neural Machine Translation EMNLP 2021 Deep Equals Shallow for ReLU Networks in Kernel Regimes ICLR 2021 Deep Frequency Principle Towards Understanding Why Deeper Learning Is Faster AAAI 2021 Deep Learning on a Data Diet: Finding Important Examples Early in Training NeurIPS 2021 Deep Neural Tangent Kernel and Laplace Kernel Have the Same RKHS ICLR 2021 DEEPSPLIT: An Efficient Splitting Method for Neural Network Verification via Indirect Effect Analysis IJCAI 2021 Differentiable Spline Approximations NeurIPS 2021 Direction Matters: On the Implicit Bias of Stochastic Gradient Descent with Moderate Learning Rate ICLR 2021 Dropout: Explicit Forms and Capacity Control ICML 2021 Efficient Certification of Spatial Robustness AAAI 2021 Elementary superexpressive activations ICML 2021 Embedding Principle of Loss Landscape of Deep Neural Networks NeurIPS 2021 Estimating informativeness of samples with Smooth Unique Information ICLR 2021 Exact Gap between Generalization Error and Uniform Convergence in Random Feature Models ICML 2021 Examining the Inductive Bias of Neural Language Models with Artificial Languages ACL 2021 Expected Validation Performance and Estimation of a Random Variable’s Maximum EMNLP 2021 Exponentially Many Local Minima in Quantum Neural Networks ICML 2021 Fast Axiomatic Attribution for Neural Networks NeurIPS 2021 Formalizing Generalization and Adversarial Robustness of Neural Networks to Weight Perturbations NeurIPS 2021 Fractal Structure and Generalization Properties of Stochastic Optimization Algorithms NeurIPS 2021 Frivolous Units: Wider Networks Are Not Really That Wide AAAI 2021 General Low-rank Matrix Optimization: Geometric Analysis and Sharper Bounds NeurIPS 2021