Probability

Noisy Computing of the Threshold Function ALT 2025 On Learning Parallel Pancakes with Mostly Uniform Weights ICML 2025 On the Convergence of Tâtonnement for Linear Fisher Markets AAAI 2025 On the Hardness of Bandit Learning COLT 2025 Optimal Transport on Categorical Data for Conterfactuals Using Compositional Data and Dirichlet Transport IJCAI 2025 Piecewise deterministic sampling with splitting schemes JMLR 2025 Polynomial low degree hardness for Broadcasting on Trees (Extended Abstract) COLT 2025 Private Lossless Multiple Release ICML 2025 Probability Distribution Collapse: A Critical Bottleneck to Compact Unsupervised Neural Grammar Induction EMNLP 2025 Rate-Preserving Reductions for Blackwell Approachability COLT 2025 Rethinking the Role of Prompting Strategies in LLM Test-Time Scaling: A Perspective of Probability Theory ACL 2025 Revisiting Cosine Similarity via Normalized ICA-transformed Embeddings COLING 2025 Safe Online Convex Optimization with Heavy-Tailed Observation Noises AAAI 2025 Sample Complexity of Branch-length Estimation by Maximum Likelihood ICML 2025 Sample Complexity of Correlation Detection in the Gaussian Wigner Model ICML 2025 Sampling from Binary Quadratic Distributions via Stochastic Localization ICML 2025 Sharp bounds on aggregate expert error ALT 2025 Singular Subspace Perturbation Bounds via Rectangular Random Matrix Diffusions ICLR 2025 Statistical and Computational Guarantees of Kernel Max-Sliced Wasserstein Distances ICML 2025 Statistical Query Hardness of Multiclass Linear Classification with Random Classification Noise ICML 2025 Stochastic block models with many communities and the Kesten–Stigum bound - extended abstract COLT 2025 Stream-level Flow Matching with Gaussian Processes ICML 2025 The Batch Complexity of Bandit Pure Exploration ICML 2025 The Global Convergence Time of Stochastic Gradient Descent in Non-Convex Landscapes: Sharp Estimates via Large Deviations ICML 2025 The Harder Path: Last Iterate Convergence for Uncoupled Learning in Zero-Sum Games with Bandit Feedback ICML 2025