Theory

The Hintons in your Neural Network: a Quantum Field Theory View of Deep Learning ICML 2021 The Implicit Bias for Adaptive Optimization Algorithms on Homogeneous Neural Networks ICML 2021 The Implicit Bias of Minima Stability: A View from Function Space NeurIPS 2021 The Importance of Pessimism in Fixed-Dataset Policy Optimization ICLR 2021 The Limits of Min-Max Optimization Algorithms: Convergence to Spurious Non-Critical Sets ICML 2021 The Lipschitz Constant of Self-Attention ICML 2021 The Low-Dimensional Linear Geometry of Contextualized Word Representations CoNLL 2021 The Minecraft Kernel: Modelling correlated Gaussian Processes in the Fourier domain AISTATS 2021 The Neural Tangent Link Between CNN Denoisers and Non-Local Filters CVPR 2021 Theoretical Analyses of Multi-Objective Evolutionary Algorithms on Multi-Modal Objectives AAAI 2021 Theoretically Principled Deep RL Acceleration via Nearest Neighbor Function Approximation AAAI 2021 The Parameterized Complexity of Clustering Incomplete Data AAAI 2021 The Pareto Frontier of model selection for general Contextual Bandits NeurIPS 2021 The Smoothed Complexity of Computing Kemeny and Slater Rankings AAAI 2021 The Unexpected Deterministic and Universal Behavior of Large Softmax Classifiers AISTATS 2021 Thinking Like Transformers ICML 2021 Thou Shalt Love Thy Neighbor as Thyself When Thou Playest: Altruism in Game Theory AAAI 2021 Tight Bounds on the Smallest Eigenvalue of the Neural Tangent Kernel for Deep ReLU Networks ICML 2021 Tighter Expected Generalization Error Bounds via Wasserstein Distance NeurIPS 2021 Tight High Probability Bounds for Linear Stochastic Approximation with Fixed Stepsize NeurIPS 2021 Time-independent Generalization Bounds for SGLD in Non-convex Settings NeurIPS 2021 Too Much in Common: Shifting of Embeddings in Transformer Language Models and its Implications NAACL 2021 Topological Machine Learning Methods for Power System Responses to Contingencies AAAI 2021 Toward Better Generalization Bounds with Locally Elastic Stability ICML 2021 Towards a Theoretical Understanding of the Robustness of Variational Autoencoders AISTATS 2021