Theory

Smoothed Online Classification can be Harder than Batch Classification NeurIPS 2024 Soft Mixture Denoising: Beyond the Expressive Bottleneck of Diffusion Models ICLR 2024 Solving for X and Beyond: Can Large Language Models Solve Complex Math Problems with More-Than-Two Unknowns? EMNLP 2024 Span-Based Optimal Sample Complexity for Weakly Communicating and General Average Reward MDPs NeurIPS 2024 Spectral Analysis of the Neural Tangent Kernel for Deep Residual Networks JMLR 2024 Spectral Filters, Dark Signals, and Attention Sinks ACL 2024 Split Conformal Prediction and Non-Exchangeable Data JMLR 2024 SpreadsheetBench: Towards Challenging Real World Spreadsheet Manipulation NeurIPS 2024 Stability Analysis of Switched Linear Systems with Neural Lyapunov Functions AAAI 2024 Stack Attention: Improving the Ability of Transformers to Model Hierarchical Patterns ICLR 2024 Stationary Representations: Optimally Approximating Compatibility and Implications for Improved Model Replacements CVPR 2024 Statistical-Computational Trade-offs for Density Estimation NeurIPS 2024 Statistical Perspective of Top-K Sparse Softmax Gating Mixture of Experts ICLR 2024 Statistical Properties of Robust Satisficing ICML 2024 Stochastic Approximation with Decision-Dependent Distributions: Asymptotic Normality and Optimality JMLR 2024 Stochastic Zeroth-Order Optimization under Strongly Convexity and Lipschitz Hessian: Minimax Sample Complexity NeurIPS 2024 STORYSUMM: Evaluating Faithfulness in Story Summarization EMNLP 2024 Strengthened stability analysis of discrete-time Lurie systems involving ReLU neural networks L4DC 2024 Structured d-DNNF Is Not Closed under Negation IJCAI 2024 Structured Tree Alignment for Evaluation of (Speech) Constituency Parsing ACL 2024 Sudden Drops in the Loss: Syntax Acquisition, Phase Transitions, and Simplicity Bias in MLMs ICLR 2024 Sufficient conditions for offline reactivation in recurrent neural networks ICLR 2024 Super Consistency of Neural Network Landscapes and Learning Rate Transfer NeurIPS 2024 Superconstant Inapproximability of Decision Tree Learning COLT 2024 SURE: SUrvey REcipes for building reliable and robust deep networks CVPR 2024