arXiv subjects

Yinyu Ye

Publications and source records attributed to Yinyu Ye.

At least 19 recordsLinked to original sources

arXiv2026

Token-Level Advertising

Generative AI is transforming how people access information, challenging traditional advertising mechanisms built around predefined slots. Towards generation-native advertising, we propose the Latent Advertiser Mixture Auction (LAMA), a token-level advertising mechanism that embeds advertiser influence directly into the generation process. Advertisers report local continuation values that induce advertiser-specific next-token policies, from which the platform decodes through a latent mixture while updating an allocation posterior. We show that LAMA satisfies Markov DSIC and IR, and achieves near-optimal KL-regularized welfare. We further develop a learning-based implementation that reconstructs the required reports online from learned local advantages and root values. Proof-of-concept experiments on real-world commercial-search query splits show that LAMA improves platform welfare and revenue while maintaining user-facing response quality, providing initial evidence for the feasibility of generation-native advertising.

cs.GT↗

arXiv2026

Toward the Optimal Regret-Instability Trade-off in Multi-Armed Bandits

Multi-armed bandit algorithms are evaluated by regret, yet comparable regret can coexist with different allocations across independent runs. We study the trade-off between worst-case regret $\mathcal{R}_{K,T}$ and instability $\mathcal S_{K,T}$, defined as the largest standard deviation of a terminal pull count, for $K$ arms and $T$ rounds. We prove the finite-time lower bound $\mathcal R_{K,T}\mathcal S_{K,T}\ge C T^{3/2}$, where $C$ is independent of $K$ and $T$, under a finite-time regret condition and without the regularity assumptions imposed in the prior asymptotic analysis. We also introduce Stabilized Lower-Envelope UCB (\textup{\textsc{SLE-UCB}}), a new tunable algorithm combining a running lower-envelope index with a decreasing pull-count stabilizer. \textup{\textsc{SLE-UCB}} satisfies $\mathcal R_{K,T}\mathcal S_{K,T}=O(T^{3/2}\log K)$, with an implicit constant independent of $K$ and $T$, matching the lower bound exactly in $T$ and within a logarithmic factor in $K$. To prove the instability bound, we develop a new offline top-prefix representation that removes path dependence from online decisions. Together with single-reward perturbations and the Efron--Stein inequality, this representation controls pull-count variance. Thus, regret and instability depend reciprocally on $K$, while their product has no polynomial dependence on $K$. These results resolve the open question raised in the literature concerning the sharp arm-dependent regret--instability frontier.

stat.ML↗

arXiv2026

Tight Nonasymptotic Local Convergence of Sinkhorn-Knopp

We revisit the Sinkhorn-Knopp (SK) algorithm for the matrix scaling problem. Despite extensive literature on the global convergence of SK and its variants, its local linear convergence behavior remains less understood. We address this gap by providing the first nonasymptotic local analysis of SK that matches the rate obtained from existing asymptotic Jacobian-based arguments. We show that under certain connectivity conditions, SK is a polynomial-time algorithm for doubly stochastic matrix scaling. With the developed tools, we showcase the local suboptimality of SK and provide accelerated variants. Finally, for dense matrices, we improve the complexity of existing first-order matrix scaling algorithms from $O(\tfrac{n^{7/3}}{\varepsilon^{2/3}})$ to $O(\tfrac{n^{9/4}}{\sqrt{\varepsilon}})$.

math.OC↗

arXiv2026

GPU-Accelerated Conic Quadratic Programming with Local Linear Convergence under Strict Complementarity

We present PDHCG-CQP, a GPU-accelerated first-order solver for large-scale conic convex quadratic programming. PDHCG-CQP supports affine constraints and Cartesian products of nonnegative, second-order, rotated second-order, exponential, and three-dimensional power cones. At its core is a restarted averaged primal-dual hybrid gradient (PDHG) method, whose primal update is computed inexactly by solving a conic quadratic proximal subproblem with projected gradient iterations. We establish local linear convergence of the restarted averaged scheme with both exact and inexact primal proximal evaluations under a uniform local quadratic-growth condition on the smoothed primal-dual gap. We further show that this condition holds under strict complementarity by exploiting a rotated second-order-cone lifting together with local primal and dual regularity conditions. Our C/CUDA implementation combines matrix-free linear algebra, batched cone projections, adaptive inner solves, reflected-Halpern acceleration, and fully device-resident KKT residual computations. It also supports multi-GPU execution through a two-dimensional partitioning of the problem data. Extensive experiments on standard and large-scale quadratic programming (QP), convex quadratically constrained quadratic programming (QCQP), second-order cone programming (SOCP), and quasilinear Fisher equilibrium benchmarks demonstrate that PDHCG-CQP achieves state-of-the-art robustness among first-order solvers while scaling efficiently to 8 GPUs and instances with up to $4.4\times10^8$ stored primal coordinates. PDHCG-CQP is open source and available at https://github.com/Lhongpei/PDHCG.

math.OC↗

arXiv2026

A Curvature-Aware Rank-Adaptive Distributed Augmented-Lagrangian Solver for Large-Scale SDPs

We present CARDAL (Curvature-Aware Rank-Adaptive Distributed Augmented Lagrangian), a distributed multi-GPU solver for large-scale semidefinite programs (SDPs) based on a rank-adaptive Burer-Monteiro factorization and an augmented Lagrangian method. At fixed ranks, a matrix-free L-BFGS method with negative-curvature corrections targets an approximate Euclidean second-order stationary point of the factored augmented Lagrangian. A reverse multiplier shift turns a negative dual-slack direction into exact negative curvature after rank expansion, and a small joint rank-lift problem selects a batched low-rank correction. A verified slack lower bound provides an a posteriori approximate KKT certificate. Our analysis establishes generic global-optimality guarantees for heterogeneous products of PSD cones at per-block ranks near the Barvinok-Pataki scale, together with a finite-accuracy counterpart under blockwise cost smoothing. For scalable execution, CARDAL distributes constraint rows, factor columns, and PSD blocks over a Constraint x Rank x Cone device mesh. The primal residual, gradient, Hessian-vector products, and slack matrix-vector products are evaluated using device-local operations and axis-wise collectives. On the Mittelmann benchmark, CARDAL exhibits stronger robustness than existing low-rank GPU approaches under a uniform accuracy standard. Experiments on large-scale SDP relaxations from robotics, electronic structure, and Max-Cut demonstrate the complementary scaling regimes of the three distribution axes, with observed wall-clock speedups of up to 4x on four H100 GPUs.

math.OC↗

arXiv2026

Online Linear Programming for Multi-Objective Routing in LLM Serving

We study the online routing problem in large language model serving, where requests arrive sequentially and must be dispatched to parallel decode workers under tight batch-size and KV-cache constraints. Unlike widely used routing heuristics that are not tied to explicit service-level objectives (SLOs) and offer limited control over latency-throughput trade-offs, we introduce a multi-objective optimization framework that formulates routing as an online linear programming with interpretable decision rewards. We apply an efficient bid-price control policy based on the online linear programming that admits requests when their SLO-weighted benefit exceeds their shadow prices. To meet millisecond decision requirements, we develop a warm-started, projected first-order updates that track the evolving dual shadow prices online with predictable runtime. We integrate our router into the Vidur simulator and demonstrate substantial improvements over standard baselines across multiple SLO regimes, including end-to-end latency, time-to-first-token, throughput, and tail performance. A big picture from our result: a science-based approach outperforms others based on heuristics.

cs.AI↗

arXiv2026

The Simple Strategy-Iteration Method is Strongly Polynomial for the Turn-Based Deterministic Forward Game

We study Turn-Based Deterministic Forward Games (TBDFGs), the subclass of turn-based deterministic zero-sum games in which no directed cycle contains actions controlled by both players. This forward condition is strictly weaker than acyclicity: recurrent behavior may be arbitrarily rich within one player's states, while mixed-player feedback cycles are excluded. Our main contribution separates two algorithmic consequences of this structure. First, we analyze the simple strategy-iteration method of [11,14], a generic method for TBSGs whose execution neither tests for nor uses the TBDFG property. We prove that this structure-oblivious algorithm nevertheless has a strongly polynomial guarantee on every TBDFG. In particular, it terminates after at most $O(n^6m^4\log^4 n)$ simplex pivot steps. Thus, the forward property acts as a structural certificate for convergence even when the algorithm is not informed that the input has this property. Second, when the TBDFG structure is known in advance, a backward SCC propagation algorithm is proposed that solves a sequence of deterministic-MDP subproblems and improves the bound to $O(n^3m^2\log^2 n)$ simplex pivot steps. Together, these results show that forward structure both regularizes the convergence of a general strategy-iteration method and supports a sharper structure-aware algorithm.

math.OC↗

arXiv2026

Rationalizing collective revealed preferences with an application in fair resource allocation

This paper presents a revealed preference approach for rationalizing collective consumption behavior. We introduce the Constructive Rationalization Method (CRM), which approximates the real market via a surrogate market of artificial consumers, called androids, with easy-to-compute demand functions. CRM uses observed aggregate demand and adds artificial consumers on the fly, while redistributing wealth under an empirical risk minimization principle. Unlike classical revealed preference approaches, CRM provides guarantees on the generalization risk for learning the aggregate demand function, while respecting the privacy of the underlying consumers in the real market. As an application, CRM can be used to provide reliable predictions for collective consumption behavior. Specifically, we show how to apply CRM to approximate allocations that are proportionally fair without requiring the knowledge of individual utilities.

cs.GT↗

arXiv2026

Geometry-Aware Online Scheduling for LLM Serving: From Theoretical Bound to System Practice

The explosive demand for interactive Large Language Model serving has highlighted the management of the Key-Value cache's dynamic memory footprint as a critical area for performance optimization in inference engines. Modern inference systems overwhelmingly rely on time-centric scheduling heuristics, such as Shortest Job First. However, their theoretical optimality is rooted in traditional schedule modeling, failing to capture the highly dynamic, 2D spatio-temporal geometric growth specific to LLM inference mechanisms. To resolve this, we propose the geometry-aware online scheduling by introducing the Smallest Volume First (SVF) algorithm and its highly efficient variant, 1-bit SVF. Theoretically, we provide a rigorous mathematical foundation for our approach. Via a novel volume-certificate proof, we sharpen SVF's worst-case competitive ratio from the prior best of 48 towards \textbf{3} in the high-concurrency regime of LLM serving. Building upon this core breakthrough, we complete a comprehensive theoretical taxonomy analyzing our algorithms across different traffic scenarios and information availability. Practically, we seamlessly integrate our approach as a plug-and-play layer in vLLM. Extensive evaluations on Llama-3.1 models demonstrate comprehensive performance gains: SVF delivers strong reductions in both average and tail latency, while 1-bit SVF, with merely a single bit information, achieves competitive throughput and latency. This work establishes a theoretically sound and empirically proven approach for resolving memory-constrained scheduling in modern LLM deployments. To facilitate future research, our code is available at https://github.com/Aurora-Kl/Geometry-Aware-Online-Scheduling.git.

cs.AI↗

arXiv2026

OR-Space: A Full-Lifecycle Workspace Benchmark for Industrial Optimization Agents

Large language model (LLM) agents are increasingly used to assist with operations research (OR) modeling, yet existing OR-oriented benchmarks often reduce evaluation to one-shot translation from a self-contained problem statement into a mathematical formulation or solver program. Such settings abstract away two characteristics of real industrial OR workflows: persistent multi-artifact workspaces and multi-stage task lifecycles. We introduce OR-Space, a full-lifecycle workspace benchmark for evaluating industrial optimization agents across model construction, model revision, and grounded explanation. Each instance is an executable workspace containing business documents, structured data, optional code artifacts, solver outputs, and task-specific evaluators distributed across interdependent files. OR-Space defines three task modes: Build, where agents construct solver-ready optimization models from heterogeneous artifacts; Revise, where agents modify existing models under changing requirements or solver feedback while preserving valid prior logic; and Explain, where agents answer grounded questions about solutions, constraints, and business implications using evidence spread across workspace artifacts. By combining persistent workspaces with lifecycle-oriented tasks, OR-Space evaluates whether agents can perform reliable optimization work beyond end-to-end text generation. We describe the benchmark design, evaluation protocol, and quality-control pipeline, and position OR-Space as a benchmark for studying the reliability, failure modes, and practical readiness of LLM agents in industrial OR workflows.

cs.AI↗

arXiv2026

OSDN: Improving Delta Rule with Provable Online Preconditioning in Linear Attention

Linear attention and state-space models offer constant-memory alternatives to softmax attention, but often struggle with in-context associative recall. The Delta Rule mitigates this by writing each token via one step of online gradient descent. However, its step size relies on a single scalar gate that ignores the feature-wise curvature of the inner objective. We propose Online Scaled DeltaNet (OSDN), which augments the scalar gate with a diagonal preconditioner updated online via hypergradient feedback. Crucially, this right-preconditioning is algebraically equivalent to a per-feature scaling of the write-side key. This equivalence allows OSDN to strictly preserve the hardware-friendly chunkwise parallel pipeline of DeltaNet without incurring high-dimensional state overhead. Theoretically, by exploiting the exact-quadratic structure of the inner regression loss, we establish super-geometric convergence against a right-Newton comparator and prove an algorithm-aligned token-local residual contraction bound. To handle non-stationary contexts, we further introduce Adaptive Preconditioner Forgetting (APF) to dynamically refresh stale calibration. Empirically, OSDN demonstrates strong performance across scales. At the 340M-parameter scale, OSDN improves JRT-style in-context recall by 32% over DeltaNet. Scaling to 1.3B parameters, it achieves a 39% reduction in the recall residual ratio while maintaining parity on general downstream tasks (e.g., perplexity and LongBench) -- demonstrating that our online-preconditioning mechanism effectively transfers and amplifies at the billion-parameter scale.

cs.LG↗

arXiv2026

D-PDLP: Scaling PDLP to Distributed Multi-GPU Systems

We present a distributed framework of the Primal-Dual Hybrid Gradient (PDHG) algorithm for solving massive-scale linear programming (LP) problems. Although PDHG-based solvers demonstrate strong performance on single-node GPU architectures, their applicability to industrial-scale instances is often limited by single-GPU computational throughput. To overcome these challenges, we propose D-PDLP, the first Distributed PDLP framework, which extends PDHG to a multi-GPU setting via a practical two-dimensional grid partitioning of the constraint matrix. To improve load balance and computational efficiency, we introduce a block-wise random permutation strategy combined with nonzero-aware matrix partitioning. By distributing the intensive computation required in PDHG iterations, the proposed framework harnesses multi-GPU parallelism to achieve substantial speedups with relatively low communication overhead. Extensive experiments on standard LP benchmarks (including MIPLIB and Mittelmann instances) as well as huge-scale real-world datasets show that our distributed implementation, built upon cuPDLPx, achieves strong scalability and high performance while preserving full FP64 numerical accuracy.

math.OC↗

arXiv2026

Tackling the Data-Parallel Load Balancing Bottleneck in LLM Serving: Practical Online Routing at Scale

Data-parallel (DP) load balancing has emerged as a first-order bottleneck in large-scale LLM serving. When a model is sharded across devices via tensor parallelism (TP) or expert parallelism (EP) and replicated across many DP workers, every decode step ends in a synchronization barrier whose latency is set by the most heavily loaded worker; even modest persistent imbalance across DP workers compounds, step after step, into a substantial fraction of wasted compute. The problem is hard for reasons specific to LLM decoding: assignments are sticky (migrating KV caches has a high cost), per-request loads grow over time, arrivals are non-stationary, and the router must decide within a sub-100\,ms decode budget over hundreds of waiting requests and tens of workers. We present \textbf{BalanceRoute}, a family of practical online routing algorithms that target this bottleneck. The first, \textbf{BR-0}, requires no prediction infrastructure and uses a piecewise-linear F-score that captures the sharp asymmetry between admissions that fill safe margin and those that overflow into the envelope; a two-stage decomposition keeps per-step cost compatible with millisecond-scale scheduling. The second, \textbf{BR-H}, generalizes BR-0 with a short, constant lookahead $H$ and a lightweight termination-classifier interface, extending the F-score to a horizon-discounted form. We deploy BalanceRoute on a 144-NPU cluster and evaluate against vLLM baselines on both a proprietary production trace and the public Azure-2024 trace. Across both workloads, BalanceRoute substantially reduces average DP imbalance and improves end-to-end serving throughput.

cs.DC↗

arXiv2026

Scalable First-Order Interior Point Trust Region Algorithms for Linearly Constrained Optimization

Computing approximate Karush--Kuhn--Tucker (KKT) points for constrained nonconvex programs is a fundamental problem in mathematical programming. Interior-point trust-region (IPTR) methods are particularly attractive for such problems because they maintain strictly feasible iterates throughout the iterative process and converge to a first-order and second-order KKT solution. Their scalability, however, is limited by the repeated computation of trust-region search directions. In this paper, we propose an approximate first-order IPTR framework that addresses this bottleneck by replacing exact trust-region subproblem solves with an approximate projector maintained through low-rank updates. The resulting method preserves feasibility and the global convergence guarantees of standard IPTR schemes while substantially reducing the per-iteration cost. We further extend the framework to obtain approximate second-order KKT points using only first-order information by integrating a gradient-based negative-curvature routine, thus avoiding explicit Hessian computations. We conduct numerical experiments to demonstrate the scalability of our approximate first-order IPTR framework in large-scale settings, where it achieves up to a $2.48\times$ speedup over the existing first-order IPTR algorithm.

cs.DS↗

arXiv2026

A Practical GPU-Enhanced Matrix-Free Primal-Dual Method for Large-Scale Conic Programs

In this paper, we introduce a practical GPU-enhanced matrix-free first-order method for solving large-scale conic programming problems, which we refer to as PDCS, standing for the Primal-Dual Conic Programming Solver. Problems that it solves include linear programs, second-order cone programs, convex quadratic programs, and exponential cone programs. The method avoids matrix factorizations and leverages sparse matrix-vector multiplication as its core computational operation, which is both memory-efficient and well-suited for GPU acceleration. The method builds on the restarted primal-dual hybrid gradient method but further incorporates several enhancements. Additionally, it employs a bisection-based method to compute projections onto rescaled cones. Furthermore, cuPDCS is a GPU implementation of PDCS and it implements customized computational schemes that utilize different levels of GPU architecture to handle cones of different types and sizes. Numerical experiments demonstrate that cuPDCS is generally more efficient than state-of-the-art commercial solvers and other first-order methods on large-scale conic program applications, including Fisher market equilibrium problems, Lasso regression, and multi-period portfolio optimization. Furthermore, cuPDCS also exhibits better scalability, efficiency, and robustness compared to other first-order methods on the conic program benchmark dataset CBLIB. These advantages are more pronounced in large-scale, lower-accuracy settings.

math.OC↗

arXiv2026

A Technical Note on the Implementation and Use of PDCS

This technical note documents the implementation and use of the Primal-Dual Conic Programming Solver (PDCS), a first-order solver for large-scale conic optimization problems introduced by Lin et al. (arXiv:2505.00311). It describes the algorithmic and implementation details underlying PDCS, including the restarted primal-dual hybrid gradient method framework, adaptive step-size selection, adaptive reflected Halpern iterations, adaptive restarts, and diagonal preconditioning. It also provides practical instructions for using PDCS, including its interfaces with JuMP and CVXPY, solver options, and illustrative code examples. PDCS is available at https://github.com/ZikaiXiong/PDCS under the Apache License 2.0.

math.OC↗

arXiv2026

A Single-Sample Polylogarithmic Regret Bound for Nonstationary Online Linear Programming

We study nonstationary Online Linear Programming (OLP), where $n$ orders arrive sequentially with reward-resource consumption pairs that form a sequence of independent, but not necessarily identically distributed, random vectors. At the beginning of the planning horizon, the decision-maker is provided with a resource endowment that is sufficient to fulfill a significant portion of the requests. The decision-maker seeks to maximize the expected total reward by making immediate and irrevocable acceptance or rejection decisions for each order, subject to this resource endowment. We focus on the challenging single-sample setting, where only one sample from each of the $n$ distributions is available at the start of the planning horizon. We propose a novel re-solving algorithm that integrates a dynamic programming perspective with the dual-based frameworks traditionally employed in stationary environments. In the large-resource regime, where the resource endowment scales linearly with the number of orders, we prove that our algorithm achieves $O((\log n)^2)$ regret across a broad class of nonstationary distribution sequences. Our results demonstrate that polylogarithmic regret is attainable even under significant environmental shifts and minimal data availability, bridging the gap between stationary OLP and more volatile real-world resource allocation problems.

cs.DS↗

arXiv2026

FMIP: Joint Continuous-Integer Flow For Mixed-Integer Linear Programming

Mixed-Integer Linear Programming (MILP) is a foundational tool for complex decision-making problems. However, the NP-hard nature of MILP presents a significant computational challenge, motivating the development of machine learning-based heuristic solutions to accelerate downstream solvers. While recent generative models have shown promise in learning powerful heuristics, they suffer from a critical limitation. That is, they model the distribution of only the integer variables and fail to capture the intricate coupling between integer and continuous variables, creating an information bottleneck and ultimately leading to suboptimal solutions. To this end, we propose Joint Continuous-Integer Flow for Mixed-Integer Linear Programming (FMIP), which is the first generative framework that models the joint distribution of both integer and continuous variables for MILP solutions. Built upon the joint modeling paradigm, a holistic guidance mechanism is designed to steer the generative trajectory, actively refining solutions toward optimality and feasibility during the inference process. Extensive experiments on eight standard MILP benchmarks demonstrate the superior performance of FMIP against existing baselines, reducing the primal gap by 41.34% on average. Moreover, we show that FMIP is fully compatible with arbitrary backbone networks and various downstream solvers, making it well-suited for a broad range of real-world MILP applications.

math.OC↗