activity
20242026
collaborators

7 papers

math.OC2026

Convergence guarantees for stochastic algorithms solving non-unique problems in metric spaces

Nicholas Pischke, Thomas Powell

We prove a general quantitative theorem on the asymptotic behavior of stochastic quasi-Fejér monotone sequences in a broad metric context. Concretely, our result explicitly constru…

math.OC2026

Generalized fluctuation bounds for stochastic algorithms in the presence of compactness

Morenikeji Neri, Nicholas Pischke, Thomas Powell

We provide a convergence result for sequences of random variables taking values in a metric space that satisfy a stochastic quasi-Fejér monotonicity condition, in the context of a…

math.LO2025

An approximate zero-one law via the Dialectica interpretation

Thomas Powell, Alex Wan

Zero-one laws state that probabilistic events of a certain type must occur with probability either or , and nothing in between. We formulate a syntactic zero-one law, which…

math.OC2025

An abstract effective convergence theorem for stochastic processes, with applications to stochastic approximation

Morenikeji Neri, Nicholas Pischke, Thomas Powell

We provide a general theorem on the asymptotic behavior of stochastic processes that conform to a relaxed supermartingale condition. The distinguishing feature of our result is tha…

math.OC2024

Asymptotic regularity of a generalised stochastic Halpern scheme

Nicholas Pischke, Thomas Powell

We provide abstract, general and highly uniform rates of asymptotic regularity for a generalized stochastic Halpern-style iteration, which incorporates a second mapping in the styl…

math.OC2024

A quantitative Robbins-Siegmund theorem

Morenikeji Neri, Thomas Powell

The Robbins-Siegmund theorem is one of the most important results in stochastic optimization, where it is widely used to prove the convergence of stochastic algorithms. We provide…

math.PR2024

On quantitative convergence for stochastic processes: Crossings, fluctuations and martingales

Morenikeji Neri, Thomas Powell

We develop a general framework for extracting highly uniform bounds on local stability for stochastic processes in terms of information on fluctuations or crossings. This includes…