arXiv subjects

Taotao He

Publications and source records attributed to Taotao He.

10 recordsLinked to original sources

arXiv2026

Assortment Optimization under Logit-Based Multi-Purchase Choice Models

Problem definition: We study assortment optimization under logit-based multi-purchase choice models. Because customers frequently purchase multiple distinct products together in a single transaction, incorporating such behavior into assortment decisions can unlock additional revenue opportunities. However, doing so is computationally challenging because the offered assortment induces a combinatorial set of feasible bundles that compete nonlinearly for customer demand. Methodology/results: We develop an exact assortment optimization framework for general multi-purchase patterns. We first introduce a hypergraph representation of Logit-MP models that unifies several models in the literature, including BundleMVL-K and Multivariate-MNL, and can be estimated from transaction data using a sparsity-based procedure. Building on this representation, we develop strong mixed-integer programming formulations that leverage recent advances from multilinear optimization and a perspective reformulation. The resulting formulations provide tighter linear programming relaxations than the prevalent Big-M approach. We further characterize classes of multi-purchase patterns, represented by different hypergraph structures, under which the formulations reduce to linear programs. Computational experiments demonstrate substantial improvements in both solution quality and scalability. Managerial implications: Using real transaction data, we show that a sparse hypergraph captures the dominant multi-purchase patterns while generating higher revenues. We also show that our formulations extend to heterogeneous customer populations and remain computationally viable, making the framework practical for large-scale retail assortment planning.

math.OC↗

arXiv2026

Axis-Aligned Relaxations for Mixed-Integer Nonlinear Programming

We present a novel relaxation framework for general mixed-integer nonlinear programming (MINLP) grounded in computational geometry. Our approach constructs polyhedral relaxations by convexifying finite sets of strategically chosen points, iteratively refining the approximation to converge toward the simultaneous convex hull of factorable function graphs. The framework is underpinned by three key contributions: (i) a new class of explicit inequalities for products of functions that strictly improve upon standard factorable and composite relaxation schemes; (ii) a proof establishing that the simultaneous convex hull of multilinear functions over axis-aligned regions is fully determined by their values at corner points, thereby generalizing existing results from hypercubes to arbitrary axis-aligned domains; and (iii) the integration of computational geometry tools, specifically voxelization and QuickHull, to efficiently approximate feasible regions and function graphs. We implement this framework and evaluate it on randomly generated polynomial optimization problems and a suite of 619 instances from \texttt{MINLPLib}. Numerical results demonstrate significant improvements over state-of-the-art benchmarks: on polynomial instances, our relaxation closes an additional 20--25\% of the optimality gap relative to standard methods on half the instances. Furthermore, compared against an enhanced factorable programming baseline and Gurobi's root-node bounds, our approach yields superior dual bounds on approximately 30\% of \texttt{MINLPLib} instances, with roughly 10\% of cases exhibiting a gap reduction exceeding 50\%.

math.OC↗

arXiv2026

Discreteness to Convexity: Promotion Planning via Simplotope Triangulation

Price promotion optimization is a computationally challenging problem central to supermarket operations, requiring simultaneous pricing decisions across multiple products and periods. This paper introduces a novel formulation for supermodular functions and univariate compositions using explicit convex hull descriptions derived from simplotope triangulations, departing from prior reliance on rectangular domains. Leveraging this reformulation with Gurobi, we achieve substantial performance gains, with average solve times for problems with 10 products and 5 price levels reducing from 434 to 0.06 seconds, enabling significant instance scaling. We demonstrate conditions for a tight linear programming relaxation extending previous results from two to multiple price levels and from additive to multiplicative historical effects. Our approach is broadly applicable to nonlinear discrete optimization, and we contribute techniques for convexifying compositions of arbitrary univariate functions and a framework for convexifying a superclass of L natural functions, providing powerful tools for revenue management. This work advances the tractability of price promotion optimization, offering a practical and theoretically grounded solution for large-scale supermarket operations.

math.OC↗

arXiv2025

Optimal Data Reduction under Information-Theoretic Criteria

Selecting an optimal subset of features or instances under an information theoretic criterion has become an effective preprocessing strategy for reducing data complexity while preserving essential information. This study investigates two representative problems within this paradigm: feature selection based on the maximum relevance minimum redundancy criterion, and instance selection grounded in the Kullback Leibler divergence. To address the intrinsic nonconvexities of these problems, we develop polyhedral relaxations that yield exact mixed integer linear programming formulations, thereby enabling globally optimal data reduction. By leveraging modern optimization techniques, we further design efficient algorithmic implementations capable of solving practically sized instances. Extensive numerical experiments on both real world and synthetic datasets demonstrate that our method efficiently solves data reduction problems to global optimality, significantly outperforming existing benchmark approaches.

math.OC↗

arXiv2025

An integer programming approach for quick-commerce assortment planning

In this paper, we explore the challenge of assortment planning in the context of quick-commerce, a rapidly-growing business model that aims to deliver time-sensitive products. In order to achieve quick delivery to satisfy the immediate demands of online customers in close proximity, personalized online assortments need to be included in brick-and-mortar store offerings. With the presence of this physical linkage requirement and distinct multinomial logit choice models for online consumer segments, the firm seeks to maximize overall revenue by selecting an optimal assortment of products for local stores and by tailoring a personalized assortment for each online consumer segment. We employ an integer programming approach to solve this NP-hard problem to global optimality. In particular, we derive convex hull results to represent the consumer choice of each online segment under a general class of operational constraints, and to characterize the relation between assortment decisions and choice probabilities of products. Our convex hull results, coupled with a modified choice probability ordered separation algorithm, yield formulations that provide a significant computational advantage over existing methods. Finally, we illustrate how our convex hull results can be used to address other assortment optimization problems.

math.OC↗

arXiv2025

Assortment Optimization Under History-Dependent Effects

This paper examines how to plan multi-period assortments when customer utility depends on historical assortments. We formulate this problem as a nonlinear integer programming model and show it is NP-hard in the presence of a negative history-dependent effect (such as a satiation effect). We build solution methodologies for obtaining global optimal solutions under a general setting that the history-dependent effects could be a mixture of positive and negative. We propose using a lifting-based framework to reformulate the problem as a mixed-integer exponential cone program that state-of-the-art solvers can solve. We also design a sequential revenue-ordered policy and show that it solves our problem to optimality in polynomial time when historical assortments positively affect customer utility (such as an addiction effect). Additionally, we identify an optimal cyclic policy for an asymptotic regime, and we also relate its length to the customer's memory length. Finally, we present a case study using a catering service dataset, showing that our model demonstrates good fitness and can effectively balance variety and revenue.

math.OC↗

arXiv2024

MIP Relaxations in Factorable Programming

In this paper, we develop new discrete relaxations for nonlinear expressions in factorable programming. We utilize specialized convexification results as well as composite relaxations to develop mixed-integer programming (MIP) relaxations. Our relaxations rely on ideal formulations of convex hulls of outer-functions over a combinatorial structure that captures local inner-function structure. The resulting relaxations often require fewer variables and are tighter than currently prevalent ones. Finally, we provide computational evidence to demonstrate that our relaxations close approximately 60-70% of the gap relative to McCormick relaxations and significantly improves the relaxations used in a state-of-the-art solver on various instances involving polynomial functions.

math.OC↗

arXiv2024

Convexification Techniques for Fractional Programs

This paper develops a correspondence relating convex hulls of fractional functions with those of polynomial functions over the same domain. Using this result, we develop a number of new reformulations and relaxations for fractional programming problems. First, we relate 0-1 problems involving a ratio of affine functions with the boolean quadric polytope, and use inequalities for the latter to develop tighter formulations for the former. Second, we derive a new formulation to optimize a ratio of quadratic functions over a polytope using copositive programming. Third, we show that univariate fractional functions can be convexified using moment hulls. Fourth, we develop a new hierarchy of relaxations that converges finitely to the simultaneous convex hull of a collection of ratios of affine functions of 0-1 variables. Finally, we demonstrate theoretically and computationally that our techniques close a significant gap relative to state-of-the-art relaxations, require much less computational effort, and can solve larger problem instances.

math.OC↗

arXiv2022

Extracting structure from functional expressions for continuous and discrete relaxations of MINLP

In this paper, we develop new continuous and discrete relaxations for nonlinear expressions in an MINLP. In contrast to factorable programming, our techniques utilize the inner-function structure by encapsulating it in a polyhedral set, using a technique first proposed in [12]. We tighten the relaxations derived in [33,13] and obtain new relaxations for functions that could not be treated using prior techniques. We develop new discretization-based mixed-integer programming relaxations that yield tighter relaxations than similar relaxations in the literature. These relaxations utilize the simplotope that captures inner-function structure to generalize the incremental formulation of [8] to multivariate functions. In particular, when the outer-function is supermodular, our formulations require exponentially fewer continuous variables than any previously known formulation.

math.OC↗

arXiv2019

Reconfigurable continuous-zoom metalens in visible

Design of a conventional zoom lens is always challengeable because it requires not only sophisticated optical design strategy, but also complex and precise mechanical structures for lens adjustment. In this paper, we propose a continuous zoom lens consisting of two chiral geometric metasurfaces with dielectric nanobrick arrays sitting on a transparent substrate. The metalens can continuously vary the focal length by rotating either of the two metasurfaces along its optical axis without changing any other conditions. More importantly, because of the polarization dependence of the geometric metasurface, the positive and negative polarities are interchangeable in one identical metalens only by changing the handedness of the incident circularly polarized light, which can generate varyingfocal lengths ranging from negative infinity to positive infinity in principle. On account of its advantages of compactness, flexibility and easiness in design, the proposed zoom metalens can provide new perspectives for the development of continuous-zoom optical system and it can find applications in fields which require ultracompact and continuous-zoom imaging and reconfigurable beam wavefront steering.

physics.optics↗