Theory

Identifying Causal Effects Under Functional Dependencies NeurIPS 2024 Identifying Causal Effects using Instrumental Time Series: Nuisance IV and Correcting for the Past JMLR 2024 Identifying Confounding from Causal Mechanism Shifts AISTATS 2024 Identifying Equivalent Training Dynamics NeurIPS 2024 Identifying Important Group of Pixels using Interactions CVPR 2024 Implicit Bias of Mirror Flow on Separable Data NeurIPS 2024 Improved Analysis for Bandit Learning in Matching Markets NeurIPS 2024 Improved Bounds for Pure Private Agnostic Learning: Item-Level and User-Level Privacy ICML 2024 Improved Hardness Results for Learning Intersections of Halfspaces COLT 2024 Improved Regret of Linear Ensemble Sampling NeurIPS 2024 Improved Sample Complexity Bounds for Diffusion Model Training NeurIPS 2024 Improving Alignment and Robustness with Circuit Breakers NeurIPS 2024 Improving equilibrium propagation without weight symmetry through Jacobian homeostasis ICLR 2024 Improving the Worst-Case Bidirectional Communication Complexity for Nonconvex Distributed Optimization under Function Similarity NeurIPS 2024 Incentivizing Quality Text Generation via Statistical Contracts NeurIPS 2024 In-Context Learning with Transformers: Softmax Attention Adapts to Function Lipschitzness NeurIPS 2024 Individual Causal Structure Learning from Population Data IJCAI 2024 Inexact Augmented Lagrangian Methods for Conic Optimization: Quadratic Growth and Linear Convergence NeurIPS 2024 Information Retention via Learning Supplemental Features ICLR 2024 Information-theoretic Generalization Analysis for Expected Calibration Error NeurIPS 2024 Information-theoretic Limits of Online Classification with Noisy Labels NeurIPS 2024 Information-Theoretic Thresholds for the Alignments of Partially Correlated Graphs COLT 2024 Inspecting Prediction Confidence for Detecting Black-Box Backdoor Attacks AAAI 2024 Integrated Decision Gradients: Compute Your Attributions Where the Model Makes Its Decision AAAI 2024 Interpretable Network Visualizations: A Human-in-the-Loop Approach for Post-hoc Explainability of CNN-based Image Classification IJCAI 2024