Recent results in non-convex stochastic optimization demonstrate the convergence of popular adaptive algorithms (e.g., AdaGrad) under the $(L_0, L_1)$-smoothness condition, but the rate of convergence is a higher-order polynomial in terms of problem parameters like the smoothness constants. The complexity guaranteed by such algorithms to find an $\epsilon$-stationary point may be significantly larger than the optimal complexity of $\Theta \left( \Delta L \sigma^2 \epsilon^{-4} \right)$ achieved by SGD in the $L$-smooth setting, where $\Delta$ is the initial optimality gap, $\sigma^2$ is the variance of stochastic gradient. However, it is currently not known whether these higher-order dependencies can be tightened. To answer this question, we investigate complexity lower bounds for several adaptive optimization algorithms in the $(L_0, L_1)$-smooth setting, with a focus on the dependence in terms of problem parameters $\Delta, L_0, L_1$. We provide complexity bounds for three variations of AdaGrad, which show at least a quadratic dependence on problem parameters $\Delta, L_0, L_1$. Notably, we show that the decorrelated variant of AdaGrad-Norm requires at least $\Omega \left( \Delta^2 L_1^2 \sigma^2 \epsilon^{-4} \right)$ stochastic gradient queries to find an $\epsilon$-stationary point. We also provide a lower bound for SGD with a broad class of adaptive stepsizes. Our results show that, for certain adaptive algorithms, the $(L_0, L_1)$-smooth setting is fundamentally more difficult than the standard smooth setting, in terms of the initial optimality gap and the smoothness constants.
Concentrated liquidity automated market makers (AMMs), such as Uniswap v3, enable liquidity providers (LPs) to earn liquidity rewards by depositing tokens into liquidity pools. However, LPs often face significant financial losses driven by poorly selected liquidity provision intervals and high costs associated with frequent liquidity reallocation. To support LPs in achieving more profitable liquidity concentration, we developed a tractable stochastic optimization problem that can be used to compute optimal liquidity provision intervals for profitable liquidity provision. The developed problem accounts for the relationships between liquidity rewards, divergence loss, and reallocation costs. By formalizing optimal liquidity provision as a tractable stochastic optimization problem, we support a better understanding of the relationship between liquidity rewards, divergence loss, and reallocation costs. Moreover, the stochastic optimization problem offers a foundation for more profitable liquidity concentration.
Stacked intelligent metasurface (SIM) is an emerging technology that uses multiple reconfigurable surface layers to enable flexible wave-based beamforming. In this paper, we focus on an \ac{SIM}-assisted multi-user multiple-input single-output system, where it is essential to ensure that all users receive a fair and reliable service level. To this end, we develop two max-min fairness algorithms based on instantaneous channel state information (CSI) and statistical CSI. For the instantaneous CSI case, we propose an alternating optimization algorithm that jointly optimizes power allocation using geometric programming and wave-based beamforming coefficients using the gradient descent-ascent method. For the statistical CSI case, since deriving an exact expression for the average minimum achievable rate is analytically intractable, we derive a tight upper bound and thereby formulate a stochastic optimization problem. This problem is then solved, capitalizing on an alternating approach combining geometric programming and gradient descent algorithms, to obtain the optimal policies. Our numerical results show significant improvements in the minimum achievable rate compared to the benchmark schemes. In particular, for the instantaneous CSI scenario, the individual impact of the optimal wave-based beamforming is significantly higher than that of the power allocation strategy. Moreover, the proposed upper bound is shown to be tight in the low signal-to-noise ratio regime under the statistical CSI.
We address the problem of zero-order optimization from noisy observations for an objective function satisfying the Polyak-{\L}ojasiewicz or the strong convexity condition. Additionally, we assume that the objective function has an additive structure and satisfies a higher-order smoothness property, characterized by the H\"older family of functions. The additive model for H\"older classes of functions is well-studied in the literature on nonparametric function estimation, where it is shown that such a model benefits from a substantial improvement of the estimation accuracy compared to the H\"older model without additive structure. We study this established framework in the context of gradient-free optimization. We propose a randomized gradient estimator that, when plugged into a gradient descent algorithm, allows one to achieve minimax optimal optimization error of the order $dT^{-(\beta-1)/\beta}$, where $d$ is the dimension of the problem, $T$ is the number of queries and $\beta\ge 2$ is the H\"older degree of smoothness. We conclude that, in contrast to nonparametric estimation problems, no substantial gain of accuracy can be achieved when using additive models in gradient-free optimization.
We revisit a classical assumption for analyzing stochastic gradient algorithms where the squared norm of the stochastic subgradient (or the variance for smooth problems) is allowed to grow as fast as the squared norm of the optimization variable. We contextualize this assumption in view of its inception in the 1960s, its seemingly independent appearance in the recent literature, its relationship to weakest-known variance assumptions for analyzing stochastic gradient algorithms, and its relevance in deterministic problems for non-Lipschitz nonsmooth convex optimization. We build on and extend a connection recently made between this assumption and the Halpern iteration. For convex nonsmooth, and potentially stochastic, optimization, we analyze horizon-free, anytime algorithms with last-iterate rates. For problems beyond simple constrained optimization, such as convex problems with functional constraints or regularized convex-concave min-max problems, we obtain rates for optimality measures that do not require boundedness of the feasible set.
Over-the-air (OTA) federated learning (FL) effectively utilizes communication bandwidth, yet it is vulnerable to errors during analog aggregation. While removing users with unfavorable channel conditions can mitigate these errors, it also reduces the available local training data for FL, which in turn hinders the convergence rate of the training process. To tackle this issue, we propose using fluid antenna (FA) techniques to enhance the degrees of freedom within the channel space, ultimately boosting the convergence speed of FL training. Moreover, we develop a novel approach that effectively coordinates uplink receiver beamforming, user selection, and FA positioning to optimize the convergence rate of OTA FL training in dynamic wireless environments. We address this challenging stochastic optimization by reformulating it as a mixed-integer programming problem by utilizing the training loss upper bound. We then introduce a penalty dual decomposition (PDD) method to solve the mixed-integer mixed programming problem. Experimental results indicate that incorporating FA techniques significantly accelerates the training convergence of FL and greatly surpasses conventional methods.
This study focuses on mixed-variable black-box optimization (MV-BBO), addressing continuous, integer, and categorical variables. Many real-world MV-BBO problems involve dependencies among these different types of variables, requiring efficient methods to optimize them simultaneously. Recently, stochastic optimization methods leveraging the mechanism of the covariance matrix adaptation evolution strategy have shown promising results in mixed-integer or mixed-category optimization. However, such methods cannot handle the three types of variables simultaneously. In this study, we propose CatCMA with Margin (CatCMAwM), a stochastic optimization method for MV-BBO that jointly optimizes continuous, integer, and categorical variables. CatCMAwM is developed by incorporating a novel integer handling into CatCMA, a mixed-category black-box optimization method employing a joint distribution of multivariate Gaussian and categorical distributions. The proposed integer handling is carefully designed by reviewing existing integer handlings and following the design principles of CatCMA. Even when applied to mixed-integer problems, it stabilizes the marginal probability and improves the convergence performance of continuous variables. Numerical experiments show that CatCMAwM effectively handles the three types of variables, outperforming state-of-the-art Bayesian optimization methods and baselines that simply incorporate existing integer handlings into CatCMA.
Outlier detection in high-dimensional tabular data is challenging since data is often distributed across multiple lower-dimensional subspaces -- a phenomenon known as the Multiple Views effect (MV). This effect led to a large body of research focused on mining such subspaces, known as subspace selection. However, as the precise nature of the MV effect was not well understood, traditional methods had to rely on heuristic-driven search schemes that struggle to accurately capture the true structure of the data. Properly identifying these subspaces is critical for unsupervised tasks such as outlier detection or clustering, where misrepresenting the underlying data structure can hinder the performance. We introduce Myopic Subspace Theory (MST), a new theoretical framework that mathematically formulates the Multiple Views effect and writes subspace selection as a stochastic optimization problem. Based on MST, we introduce V-GAN, a generative method trained to solve such an optimization problem. This approach avoids any exhaustive search over the feature space while ensuring that the intrinsic data structure is preserved. Experiments on 42 real-world datasets show that using V-GAN subspaces to build ensemble methods leads to a significant increase in one-class classification performance -- compared to existing subspace selection, feature selection, and embedding methods. Further experiments on synthetic data show that V-GAN identifies subspaces more accurately while scaling better than other relevant subspace selection methods. These results confirm the theoretical guarantees of our approach and also highlight its practical viability in high-dimensional settings.
We consider the problem of optimal decision referrals in human-automation teams performing binary classification tasks. The automation, which includes a pre-trained classifier, observes data for a batch of independent tasks, analyzes them, and may refer a subset of tasks to a human operator for fresh and final analysis. Our key modeling assumption is that human performance degrades with task load. We model the problem of choosing which tasks to refer as a stochastic optimization problem and show that, for a given task load, it is optimal to myopically refer tasks that yield the largest reduction in expected cost, conditional on the observed data. This provides a ranking scheme and a policy to determine the optimal set of tasks for referral. We evaluate this policy against a baseline through an experimental study with human participants. Using a radar screen simulator, participants made binary target classification decisions under time constraint. They were guided by a decision rule provided to them, but were still prone to errors under time pressure. An initial experiment estimated human performance model parameters, while a second experiment compared two referral policies. Results show statistically significant gains for the proposed optimal referral policy over a blind policy that determines referrals using the automation and human-performance models but not based on the observed data.
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 applications. Despite its power, the performance of IS is often highly sensitive to the choice of the proposal distribution and frequently requires stochastic calibration techniques. While the design and analysis of IS have been extensively studied in estimation settings, applying IS within stochastic optimization introduces a unique challenge: the decision and the IS distribution are mutually dependent, creating a circular optimization structure. This interdependence complicates both the analysis of convergence for decision iterates and the efficiency of the IS scheme. In this paper, we propose an iterative gradient-based algorithm that jointly updates the decision variable and the IS distribution without requiring time-scale separation between the two. Our method achieves the lowest possible asymptotic variance and guarantees global convergence under convexity of the objective and mild assumptions on the IS distribution family. Furthermore, we show that these properties are preserved under linear constraints by incorporating a recent variant of Nesterov's dual averaging method.
Order-Preserving (OP) GFlowNets have demonstrated remarkable success in tackling complex multi-objective (MOO) black-box optimization problems using stochastic optimization techniques. Specifically, they can be trained online to efficiently sample diverse candidates near the Pareto front. A key advantage of OP GFlowNets is their ability to impose a local order on training samples based on Pareto dominance, eliminating the need for scalarization - a common requirement in other approaches like Preference-Conditional GFlowNets. However, we identify an important limitation of OP GFlowNets: imposing a local order on training samples can lead to conflicting optimization objectives. To address this issue, we introduce Global-Order GFlowNets, which transform the local order into a global one, thereby resolving these conflicts. Our experimental evaluations on various benchmarks demonstrate the efficacy and promise of our proposed method.
We study stochastic optimization with data-adaptive sampling schemes to train pairwise learning models. Pairwise learning is ubiquitous, and it covers several popular learning tasks such as ranking, metric learning and AUC maximization. A notable difference of pairwise learning from pointwise learning is the statistical dependencies among input pairs, for which existing analyses have not been able to handle in the general setting considered in this paper. To this end, we extend recent results that blend together two algorithm-dependent frameworks of analysis -- algorithmic stability and PAC-Bayes -- which allow us to deal with any data-adaptive sampling scheme in the optimizer. We instantiate this framework to analyze (1) pairwise stochastic gradient descent, which is a default workhorse in many machine learning problems, and (2) pairwise stochastic gradient descent ascent, which is a method used in adversarial training. All of these algorithms make use of a stochastic sampling from a discrete distribution (sample indices) before each update. Non-uniform sampling of these indices has been already suggested in the recent literature, to which our work provides generalization guarantees in both smooth and non-smooth convex problems.
In this paper, we aim to mitigate congestion in traffic management systems by guiding travelers along system-optimal (SO) routes. However, we recognize that most theoretical approaches assume perfect driver compliance, which often does not reflect reality, as drivers tend to deviate from recommendations to fulfill their personal objectives. Therefore, we propose a route recommendation framework that explicitly learns partial driver compliance and optimizes traffic flow under realistic adherence. We first compute an SO edge flow through flow optimization techniques. Next, we train a compliance model based on historical driver decisions to capture individual responses to our recommendations. Finally, we formulate a stochastic optimization problem that minimizes the gap between the target SO flow and the realized flow under conditions of imperfect adherence. Our simulations conducted on a grid network reveal that our approach significantly reduces travel time compared to baseline strategies, demonstrating the practical advantage of incorporating learned compliance into traffic management.
We study counterfactual regression, which aims to map input features to outcomes under hypothetical scenarios that differ from those observed in the data. This is particularly useful for decision-making when adapting to sudden shifts in treatment patterns is essential. We propose a doubly robust-style estimator for counterfactual regression within a generalizable framework that accommodates a broad class of risk functions and flexible constraints, drawing on tools from semiparametric theory and stochastic optimization. Our approach uses incremental interventions to enhance adaptability while maintaining consistency with standard methods. We formulate the target estimand as the optimal solution to a stochastic optimization problem and develop an efficient estimation strategy, where we can leverage rapid development of modern optimization algorithms. We go on to analyze the rates of convergence and characterize the asymptotic distributions. Our analysis shows that the proposed estimators can achieve $\sqrt{n}$-consistency and asymptotic normality for a broad class of problems. Numerical illustrations highlight their effectiveness in adapting to unseen counterfactual scenarios while maintaining parametric convergence rates.
Large language models (LLMs) possess impressive linguistic capabilities but often fail to faithfully retain factual knowledge, leading to hallucinations and unreliable outputs. Understanding LLMs' knowledge deficiencies by exhaustively evaluating against full-scale knowledge bases is computationally prohibitive, especially for closed-weight models. We propose stochastic error ascent (SEA), a scalable and efficient framework for discovering knowledge deficiencies (errors) in closed-weight LLMs under a strict query budget. Rather than naively probing all knowledge candidates, SEA formulates error discovery as a stochastic optimization process: it iteratively retrieves new high-error candidates by leveraging the semantic similarity to previously observed failures. To further enhance search efficiency and coverage, SEA employs hierarchical retrieval across document and paragraph levels, and constructs a relation directed acyclic graph to model error propagation and identify systematic failure modes. Empirically, SEA uncovers 40.7x more knowledge errors than Automated Capability Discovery and 26.7% more than AutoBencher, while reducing the cost-per-error by 599x and 9x, respectively. Human evaluation confirms the high quality of generated questions, while ablation and convergence analyses validate the contribution of each component in SEA. Further analysis on the discovered errors reveals correlated failure patterns across LLM families and recurring deficits, highlighting the need for better data coverage and targeted fine-tuning in future LLM development.
The Mean-Field Schrodinger Bridge (MFSB) problem is an optimization problem aiming to find the minimum effort control policy to drive a McKean-Vlassov stochastic differential equation from one probability measure to another. In the context of multiagent control, the objective is to control the configuration of a swarm of identical, interacting cooperative agents, as captured by the time-varying probability measure of their state. Available methods for solving this problem for distributions with continuous support rely either on spatial discretizations of the problem's domain or on approximating optimal solutions using neural networks trained through stochastic optimization schemes. For agents following Linear Time-Varying dynamics, and for Gaussian Mixture Model boundary distributions, we propose a highly efficient parameterization to approximate the solutions of the corresponding MFSB in closed form, without any learning steps. Our proposed approach consists of a mixture of elementary policies, each solving a Gaussian-to-Gaussian Covariance Steering problem from the components of the initial to the components of the terminal mixture. Leveraging the semidefinite formulation of the Covariance Steering problem, our proposed solver can handle probabilistic hard constraints on the system's state, while maintaining numerical tractability. We illustrate our approach on a variety of numerical examples.
In the face of deeply exploring and exploiting marine resources, the Internet of Underwater Things (IoUT) networks have drawn great attention considering its widely distributed low-cost and easy-deployment smart sensing nodes. However, given the hostile underwater environment, it is critical to conceive energy-efficient information collection because of limited underwater energy supply and inefficient artificial recharge methods. Characterized by high flexibility and maneuverability, autonomous underwater vehicles (AUVs) are regarded as a promising solution for information collection in the IoUT relying upon delicate AUVs’ trajectory and information collection strategy design with the spirit of balancing their energy consumption and information processing capability. In this article, we propose a heterogeneous AUV-aided information collection system with the aim of maximizing the energy efficiency of IoUT nodes taking into account AUV trajectory, resource allocation, and the Age of Information (AoI). Moreover, based on the particle swarm optimization (PSO), we obtain the trajectory of AUVs with low time complexity. Additionally, a two-stage joint optimization algorithm based on the Lyapunov optimization is constructed to strike a tradeoff between energy efficiency and system queue backlog iteratively. Finally, simulation results validate the effectiveness and superiority of our proposed strategy.
In this paper, we establish tight lower bounds for Byzantine-robust distributed first-order stochastic optimization methods in both strongly convex and non-convex stochastic optimization. We reveal that when the distributed nodes have heterogeneous data, the convergence error comprises two components: a non-vanishing Byzantine error and a vanishing optimization error. We establish the lower bounds on the Byzantine error and on the minimum number of queries to a stochastic gradient oracle required to achieve an arbitrarily small optimization error. Nevertheless, we identify significant discrepancies between our established lower bounds and the existing upper bounds. To fill this gap, we leverage the techniques of Nesterov's acceleration and variance reduction to develop novel Byzantine-robust distributed stochastic optimization methods that provably match these lower bounds, up to logarithmic factors, implying that our established lower bounds are tight.
Contextual stochastic optimization provides a framework for decision-making under uncertainty incorporating observable contextual information through covariates. We analyze statistical inference for weighted sample average approximation (wSAA), a widely-used method for solving contextual stochastic optimization problems. We first establish central limit theorems for wSAA estimates of optimal values when problems can be solved exactly, characterizing how estimation uncertainty scales with covariate sample size. We then investigate practical scenarios with computational budget constraints, revealing a fundamental tradeoff between statistical accuracy and computational cost as sample sizes increase. Through central limit theorems for budget-constrained wSAA estimates, we precisely characterize this statistical-computational tradeoff. We also develop "over-optimizing" strategies for solving wSAA problems that ensure valid statistical inference. Extensive numerical experiments on both synthetic and real-world datasets validate our theoretical findings.
The learning rate in stochastic gradient methods is a critical hyperparameter that is notoriously costly to tune via standard grid search, especially for training modern large-scale models with billions of parameters. We identify a theoretical advantage of learning rate annealing schemes that decay the learning rate to zero at a polynomial rate, such as the widely-used cosine schedule, by demonstrating their increased robustness to initial parameter misspecification due to a coarse grid search. We present an analysis in a stochastic convex optimization setup demonstrating that the convergence rate of stochastic gradient descent with annealed schedules depends sublinearly on the multiplicative misspecification factor $\rho$ (i.e., the grid resolution), achieving a rate of $O(\rho^{1/(2p+1)}/\sqrt{T})$ where $p$ is the degree of polynomial decay and $T$ is the number of steps, in contrast to the $O(\rho/\sqrt{T})$ rate that arises with fixed stepsizes and exhibits a linear dependence on $\rho$. Experiments confirm the increased robustness compared to tuning with a fixed stepsize, that has significant implications for the computational overhead of hyperparameter search in practical training scenarios.