The paper introduces Partially Informed Stochastic Optimization (PISO), a method that blends an available gradient component with a running estimate of the missing residual. By centering zeroth‑order observations on this estimate, PISO reduces variance to depend on tracking error, yielding a contraction‑based iteration with a clear momentum interpretation. For smooth nonconvex objectives, the authors prove convergence rates that rely only on the residual’s variation and initial magnitude, achieving state‑of‑the‑art function‑evaluation complexities with minimal probe directions and samples, and demonstrating empirical improvements across five benchmark settings.
Bilevel optimization (BLO) is fundamental to hierarchical decision-making but suffers from critical instability under heavy-tailed stochastic noise. Existing variance-reduction techniques typically rely on myopic magnitude checks, which fail to distinguish informative geometric signals from impulsive outliers.
arXiv:2606. 01081v1 Announce Type: new Abstract: Decision-focused learning (DFL) trains predictive models by optimizing downstream decision quality rather than standalone prediction accuracy.
The paper introduces DUCB-OGD, an algorithm that couples a Discounted Upper‑Confidence‑Bound sampler with Online Gradient Descent to address dynamic minimax regret in robust large‑language‑model post‑training. It operates under instantaneous mini‑batch‑only bandit feedback, tracking worst‑source performance without re‑evaluating historical data. Experiments on fine‑tuning, preference optimization, and reinforcement learning demonstrate that DUCB‑OGD improves worst‑group robustness with negligible computational overhead.
arXiv:2601. 15363v2 Announce Type: replace-cross Abstract: Functional bilevel optimization (FBO) provides a powerful framework for hierarchical learning in function spaces, yet current methods are limited to static offline settings and perform suboptimally in online, non-stationary scenarios.
arXiv:2606. 05888v1 Announce Type: new Abstract: Retry-based objectives such as pass@K and max@K optimize the best return obtained from multiple sampled trajectories, and recent work has shown that they can promote exploration without explicit exploration bonuses.
The paper introduces D$^3$Opt, a derivative‑free diffusion‑based framework that separates constraint modeling from objective optimization in chance‑constrained programs. It learns a risk‑conditioned diffusion model once on constraint‑filtered decisions, then uses an annealed, particle‑based Feynman–Kac correction to optimize any post‑specified objective without retraining. The method is proven to preserve feasibility and provides an error bound, and experiments show effective optimization across smooth, non‑smooth, and non‑convex objectives, including objective transfer tasks.
BCPPO is a new variant of Proximal Policy Optimization that uses Bachelier-inspired cost‑prediction networks to generate a smooth penalty based on disagreement among critics. The method keeps temporal‑difference learning unchanged, applies a saturation‑aware controller to manage cost penalties, and deploys only the policy network. Across extensive experiments, BCPPO outperforms comparators in achieving higher mean returns while maintaining lower or comparable CVaR in all tested tasks.
arXiv:2601. 07094v2 Announce Type: replace-cross Abstract: Bayesian optimization (BO) iteratively fits a Gaussian process (GP) surrogate to accumulated evaluations and selects new queries via an acquisition function.
The paper introduces Convex-Concave Reinforcement Learning (CCRL), showing that the exact per‑iteration objective in policy learning can be expressed as a difference‑of‑convex (DC) program in log‑density‑ratio coordinates. This formulation unifies existing methods such as CPI, NPG, TRPO, and AWR as special cases and enables a multi‑step axis that couples consecutive decisions. Using sequential convex programming, the authors provide convergence guarantees and demonstrate that CCRL outperforms or matches PPO on diagnostic MDPs, classic control tasks, and a stochastic mid‑horizon healthcare domain, achieving faster convergence and higher training‑curve area.
arXiv:2505.20817v3 Announce Type: replace-cross Abstract: Gradient clipping is widely used in language-model training to control heavy-tailed gradient noise and can improve convergence guarantees ove...
The paper presents a convergence framework for deep $V$‑learning over a finite horizon $H$, deriving explicit bounds on policy loss by decomposing the Bellman update error into six residuals. It shows how $L^s$ concentrability controls expected $L^1$ loss, quantifies the impact of shared sampling across horizon levels, and provides optimal and near‑optimal sample allocations for statistical error rates. The work also establishes sharp action‑gap bounds under a margin condition, transfers optimal‑gap results to frozen‑iterate gaps, and offers consistency guarantees for generative‑reset approximate‑ERM procedures with exact action scores.
arXiv:2609. 22833v1 Announce Type: new Abstract: We study personalized federated reinforcement learning, in which $n$ agents, each acting in its own Markov decision process, collaborate through a server to learn a shared MAML-style policy initialization that becomes effective for an individual agent once that agent adapts it with a single local policy-gradient step.