Theory

Towards Model Agnostic Federated Learning Using Knowledge Distillation ICLR 2022 Towards Theoretical Analysis of Transformation Complexity of ReLU DNNs ICML 2022 Towards Theoretically Grounded Evolutionary Learning IJCAI 2022 Towards Understanding Generalization via Decomposing Excess Risk Dynamics ICLR 2022 Towards Understanding Grokking: An Effective Theory of Representation Learning NeurIPS 2022 Towards Understanding Sharpness-Aware Minimization ICML 2022 Towards Understanding the Robustness Against Evasion Attack on Categorical Data ICLR 2022 Toward Understanding Convolutional Neural Networks from Volterra Convolution Perspective JMLR 2022 Toward Zero Oracle Word Error Rate on the Switchboard Benchmark Interspeech 2022 TPC: Transformation-Specific Smoothing for Point Cloud Models ICML 2022 Trade-off between Payoff and Model Rewards in Shapley-Fair Collaborative Machine Learning NeurIPS 2022 Training-Free Uncertainty Estimation for Dense Regression: Sensitivity as a Surrogate AAAI 2022 Training invariances and the low-rank phenomenon: beyond linear networks ICLR 2022 Training Scale-Invariant Neural Networks on the Sphere Can Happen in Three Regimes NeurIPS 2022 Transformers from an Optimization Perspective NeurIPS 2022 Transition to Linearity of General Neural Networks with Directed Acyclic Graph Architecture NeurIPS 2022 Tree Mover's Distance: Bridging Graph Metrics and Stability of Graph Neural Networks NeurIPS 2022 Tree-Values: Selective Inference for Regression Trees JMLR 2022 Truthful Aggregation of Budget Proposals with Proportionality Guarantees AAAI 2022 Truthful Cake Sharing AAAI 2022 TruthfulQA: Measuring How Models Mimic Human Falsehoods ACL 2022 Turbocharging Solution Concepts: Solving NEs, CEs and CCEs with Neural Equilibrium Solvers NeurIPS 2022 Two Coupled Rejection Metrics Can Tell Adversarial Examples Apart CVPR 2022 Uncalibrated Models Can Improve Human-AI Collaboration NeurIPS 2022 Underspecification Presents Challenges for Credibility in Modern Machine Learning JMLR 2022