theoretical analysis

An Augmentation Overlap Theory of Contrastive Learning JMLR 2025 Ask, and it shall be given: On the Turing completeness of prompting ICLR 2025 A Theory for Token-Level Harmonization in Retrieval-Augmented Generation ICLR 2025 Fundamental Limits of Membership Inference Attacks on Machine Learning Models JMLR 2025 Hierarchical Reinforcement Learning with Targeted Causal Interventions ICML 2025 Homomorphism Expressivity of Spectral Invariant Graph Neural Networks ICLR 2025 On the Generalization of Feature Incremental Learning IJCAI 2025 Provable Efficiency of Guidance in Diffusion Models for General Data Distribution ICML 2025 Scaling Capability in Token Space: An Analysis of Large Vision Language Model JMLR 2025 Subgroups Matter for Robust Bias Mitigation ICML 2025 Theoretical Analysis of Hierarchical Language Recognition and Generation by Transformers without Positional Encoding ACL 2025 Theory, Analysis, and Best Practices for Sigmoid Self-Attention ICLR 2025 Unraveling the Smoothness Properties of Diffusion Models: A Gaussian Mixture Perspective ICCV 2025 Adapting to Unknown Low-Dimensional Structures in Score-Based Diffusion Models NeurIPS 2024 An exactly solvable model for emergence and scaling laws in the multitask sparse parity problem NeurIPS 2024 A Phase Transition between Positional and Semantic Learning in a Solvable Model of Dot-Product Attention NeurIPS 2024 Approximation Rate of the Transformer Architecture for Sequence Modeling NeurIPS 2024 A provable control of sensitivity of neural networks through a direct parameterization of the overall bi-Lipschitzness NeurIPS 2024 A Theoretical Perspective for Speculative Decoding Algorithm NeurIPS 2024 Bridging the Divide: Reconsidering Softmax and Linear Attention NeurIPS 2024 Can Transformers Learn n-gram Language Models? EMNLP 2024 Demystifying Poisoning Backdoor Attacks from a Statistical Perspective ICLR 2024 From Activation to Initialization: Scaling Insights for Optimizing Neural Fields CVPR 2024 How to Solve Contextual Goal-Oriented Problems with Offline Datasets? NeurIPS 2024 Improved Sample Complexity Bounds for Diffusion Model Training NeurIPS 2024