Nonlinear Stochastic Gradient Descent and Heavy-tailed Noise: A Unified Framework and High-probability Guaranteesby Aleksandar Armacki,…
An Online Learning Approach to Prompt-based Selection of Generative Modelsby Xiaoyan Hu, Ho-fung Leung, Farzan…
Matrix Sketching in Bandits: Current Pitfalls and New Frameworkby Dongxie Wen, Hanyan Yin, Xiao Zhang,…
Rewarding Progress: Scaling Automated Process Verifiers for LLM Reasoningby Amrith Setlur, Chirag Nagpal, Adam Fisch,…
Sequential Probability Assignment with Contexts: Minimax Regret, Contextual Shtarkov Sums, and Contextual Normalized Maximum Likelihoodby…
Optimal Strong Regret and Violation in Constrained MDPs via Policy Optimizationby Francesco Emanuele Stradi, Matteo…
Best-of-Both-Worlds Policy Optimization for CMDPs with Bandit Feedbackby Francesco Emanuele Stradi, Anna Lunghi, Matteo Castiglioni,…
Stochastic Gradient Descent with Adaptive Databy Ethan Che, Jing Dong, Xin T. TongFirst submitted to…
A Unified Framework for Neural Computation and Learning Over Timeby Stefano Melacci, Alessandro Betti, Michele…
OML-AD: Online Machine Learning for Anomaly Detection in Time Series Databy Sebastian Wette, Florian HeinrichsFirst…