Theory

iDECODe: In-Distribution Equivariance for Conformal Out-of-Distribution Detection AAAI 2022 Identifiability of deep generative models without auxiliary information NeurIPS 2022 Identification in Tree-shaped Linear Structural Causal Models AISTATS 2022 If Influence Functions are the Answer, Then What is the Question? NeurIPS 2022 Imbalance Trouble: Revisiting Neural-Collapse Geometry NeurIPS 2022 Implicit Bias of Adversarial Training for Deep Neural Networks ICLR 2022 Implicit Bias of Gradient Descent on Reparametrized Models: On Equivalence to Mirror Descent NeurIPS 2022 Implicit Bias of Linear Equivariant Networks ICML 2022 Implicit Bias of MSE Gradient Optimization in Underparameterized Neural Networks ICLR 2022 Implicit Regularization in Hierarchical Tensor Factorization and Deep Convolutional Neural Networks ICML 2022 Improved Bounds on Neural Complexity for Representing Piecewise Linear Functions NeurIPS 2022 Improved Certified Defenses against Data Poisoning with (Deterministic) Finite Aggregation ICML 2022 Improved Utility Analysis of Private CountSketch NeurIPS 2022 Improving Certified Robustness via Statistical Learning with Logical Reasoning NeurIPS 2022 Improving Screening Processes via Calibrated Subset Selection ICML 2022 Incomplete Argumentation Frameworks: Properties and Complexity AAAI 2022 Inconsistent Planning: When in Doubt, Toss a Coin! AAAI 2022 Individual Representation in Approval-Based Committee Voting AAAI 2022 Inductive Bias of Multi-Channel Linear Convolutional Networks with Bounded Weight Norm COLT 2022 Influence Functions for Sequence Tagging Models EMNLP 2022 Information Bottleneck: Exact Analysis of (Quantized) Neural Networks ICLR 2022 Information bottleneck theory of high-dimensional regression: relevancy, efficiency and optimality NeurIPS 2022 Inherent Tradeoffs in Learning Fair Representations JMLR 2022 Interaction and Expressivity in Collective Decision-Making IJCAI 2022 Interpolation and Regularization for Causal Learning NeurIPS 2022