arXiv subjects

Nicholas Di

Publications and source records attributed to Nicholas Di.

3 recordsLinked to original sources

arXiv2026

IFlowNets: Extending Generative Samplers to Learn Strategies in Incomplete Information Games

While many algorithms blend reinforcement learning (RL) with counterfactual regret (CFR) methods to leverage tradeoffs in computational speed and performance, there are fewer investigations into generative sampling frameworks in game theoretic applications in incomplete information games. We extend a generative flow network framework, Adversarial Flow Networks (AFlowNets), to incomplete information games, called Information Flow Networks (IFNs). We prove that previously established constraints for generative flow networks in complete information games are inadmissible for obtaining valid densities (corresponding to player strategies) and a valid training objective. We show that our proposed generalization, IFlowNets, alleviates this issue and strictly generalizes AFlowNets. In preliminary results for three standard game environments, IFlowNets perform comparably to or better than Outcome Sampling Monte Carlo Counterfactual Regret (OSMCCFR) and standard RL-based methods in performance and speed.

cs.LG↗

arXiv2026

Operator Splitting with Hamilton-Jacobi-based Proximals

Operator splitting algorithms are a cornerstone of modern first-order optimization, decomposing complex problems into simpler subproblems solved via proximal operators. However, most functions lack closed-form proximal operators, which has long restricted these methods to a narrow set of problems. Hamilton-Jacobi-based proximal operator (HJ-Prox) is a recent derivative-free Monte Carlo technique based on Hamilton-Jacobi PDE theory, that approximates proximal operators numerically. In this work, we introduce a unified framework for operator splitting via HJ-Prox, which allows for deployment of operator splitting even when functions are not proximable. We prove that replacing exact proximal steps with HJ-Prox in algorithms such as proximal point, proximal gradient descent, Douglas-Rachford splitting, Davis-Yin splitting, and primal-dual hybrid gradient preserves convergence guarantees under mild assumptions. Numerical experiments demonstrate HJ-Prox is competitive and effective on a wide variety of statistical learning tasks.

math.OC↗

arXiv2025

A Monte Carlo Approach for Nonsmooth Convex Optimization via Proximal Splitting Algorithms

Operator splitting algorithms are a cornerstone of modern first-order optimization, relying critically on proximal operators as their fundamental building blocks. However, explicit formulas for proximal operators are available only for limited classes of functions, restricting the applicability of these methods. Recent work introduced HJ-Prox, a zeroth-order Monte Carlo approximation of the proximal operator derived from Hamilton-Jacobi PDEs, which circumvents the need for closed-form solutions. In this work, we extend the scope of HJ-Prox by establishing that it can be seamlessly incorporated into operator splitting schemes while preserving convergence guarantees. In particular, we show that replacing exact proximal steps with HJ-Prox approximations in algorithms such as proximal gradient descent, Douglas-Rachford splitting, Davis-Yin splitting, and the primal-dual hybrid gradient method still ensures convergence under mild conditions.

math.OC↗