Probability

Computational Explorations of Total Variation Distance ICLR 2025 Computationally efficient reductions between some statistical models ALT 2025 Connecting Thompson Sampling and UCB: Towards More Efficient Trade-offs Between Privacy and Regret ICML 2025 Convergence Rate in a Nonlinear Two-Time-Scale Stochastic Approximation with State (Time)-Dependence AAAI 2025 Decision Making in Changing Environments: Robustness, Query-Based Learning, and Differential Privacy COLT 2025 Decision Making under the Exponential Family: Distributionally Robust Optimisation with Bayesian Ambiguity Sets ICML 2025 Density Ratio Estimation via Sampling along Generalized Geodesics on Statistical Manifolds AISTATS 2025 Detecting Arbitrary Planted Subgraphs in Random Graphs COLT 2025 Differentially Private Multi-Sampling from Distributions ALT 2025 Differential Privacy Guarantees of Markov Chain Monte Carlo Algorithms ICML 2025 Distance Estimation for High-Dimensional Discrete Distributions AISTATS 2025 Distribution Estimation under the Infinity Norm JMLR 2025 Effective Littlestone dimension ALT 2025 Efficient Multivariate Robust Mean Estimation Under Mean-Shift Contamination ICML 2025 Error bounds for particle gradient descent, and extensions of the log-Sobolev and Talagrand inequalities JMLR 2025 Estimation of Large Zipfian Distributions with Sort and Snap AISTATS 2025 Expected Sliced Transport Plans ICLR 2025 FAB-PPI: Frequentist, Assisted by Bayes, Prediction-Powered Inference ICML 2025 Fast Convergence of $Φ$-Divergence Along the Unadjusted Langevin Algorithm and Proximal Sampler ALT 2025 Finite-Time Analysis of Discrete-Time Stochastic Interpolants ICML 2025 Fixing the Loose Brake: Exponential-Tailed Stopping Time in Best Arm Identification ICML 2025 For Universal Multiclass Online Learning, Bandit Feedback and Full Supervision are Equivalent ALT 2025 From Sparse to Dense Functional Data in High Dimensions: Revisiting Phase Transitions from a Non-Asymptotic Perspective JMLR 2025 Gaussian Graphical Modelling Without Independence Assumptions for Uncentered Data AAAI 2025 General framework for online-to-nonconvex conversion: Schedule-free SGD is also effective for nonconvex optimization ICML 2025