8 papers
Valid Stopping in Adaptive Generator-Verifier Loops
Mahmoud Hegazy, Michael I. Jordan, Aymeric Dieuleveut
Numerous agentic workflows are based on a generator-verifier loop: a generator proposes candidates, a cheap verifier scores them, and the workflow terminates when a proposal is ver…
Beyond Optimal Rates in Stochastic Optimization: Trajectory-Adaptive Stopping Rules
Liviu Aolaritei, Lucas Lévy, Francis Bach +1
Stochastic gradient descent (SGD) is typically analyzed at a deterministic horizon chosen before the algorithm is run, even though practical stopping decisions are made adaptively…
Diffusion-Robust Optimization over Graphs
Liviu Aolaritei, Ricky Huang, Michael I. Jordan +1
We introduce a diffusion-based uncertainty model for robust optimization on directed graphs, in which perturbations of edge weights propagate along adjacent edges and satisfy conse…
Calibeating Made Simple
Yurong Chen, Zhiyi Huang, Michael I. Jordan +1
We study calibeating, the problem of post-processing external forecasts online to minimize cumulative losses and match an informativeness-based benchmark. Unlike prior work, which…
Stopping Rules for Stochastic Gradient Descent via Anytime-Valid Confidence Sequences
Liviu Aolaritei, Michael I. Jordan
The problem of stopping stochastic gradient descent (SGD) in an online manner, based solely on the observed trajectory, is a challenging theoretical problem with significant conseq…
Revisiting mean estimation over balls: Is the MLE optimal?
Liviu Aolaritei, Michael I. Jordan, Reese Pathak +1
We revisit the problem of mean estimation in the Gaussian sequence model with constraints for . We demonstrate two phenomena for the behavior of the max…
Valid Selection among Conformal Sets
Mahmoud Hegazy, Liviu Aolaritei, Michael I. Jordan +1
Conformal prediction offers a distribution-free framework for constructing prediction sets with coverage guarantees. In practice, multiple valid conformal prediction sets may be av…
Stochastic Optimization with Optimal Importance Sampling
Liviu Aolaritei, Bart P. G. Van Parys, Henry Lam +1
Importance Sampling (IS) is a widely used variance reduction technique for enhancing the efficiency of Monte Carlo methods, particularly in rare-event simulation and related applic…