arXiv subjects

Shuvomoy Das Gupta

Publications and source records attributed to Shuvomoy Das Gupta.

13 recordsLinked to original sources

arXiv2026

A Domain-Specific Harness for End-to-End Automation of Optimization Research

We present AutoOPT, a domain-specific harness for end-to-end automation of optimization research. AutoOPT organizes the discovery of optimal first-order methods into four stages: numerical design through the BnB-PEP methodology; symbolic discovery of the analytic description and a convergence proof through frontier large language models (LLMs); formal verification in the Lean 4 proof assistant; and human interpretation and write-up. We demonstrate the framework on two case studies, each of independent interest. The first, lemniscate acceleration, is a new accelerated gradient method for minimizing the gradient norm of a smooth convex function: after $N$ gradient steps it reduces the squared gradient norm at the optimal $O(1/N^{4})$ rate, with a constant governed by the lemniscate constant $\varpi$, a classical elliptic-integral constant. The second is the analytic description of ITEM-f, a method previously known only numerically: for $L$-smooth, $μ$-strongly convex minimization it contracts the function-value gap at an accelerated linear rate with a per-step factor $(1-\sqrt{μ/L})^{2}$. The convergence theorems of both case studies are formalized and machine-checked in Lean 4.

math.OC↗

arXiv2026

The AutoLyap software suite for computer-assisted Lyapunov analyses of first-order methods

We introduce AutoLyap, a software suite that assists with Lyapunov analyses of a wide class of first-order methods for structured optimization and inclusion problems. Lyapunov analyses are structured proof patterns, with historical roots in the study of dynamical systems, commonly used to establish convergence results for first-order methods. Building on previous work, the core idea behind AutoLyap is to recast the verification of the existence of a Lyapunov analysis as a semidefinite program (SDP), which can then be solved numerically using standard SDP solvers. Users of the package specify (i) the class of optimization or inclusion problems, (ii) the first-order method in question, and (iii) the type of Lyapunov analysis they wish to test. Once these inputs are provided, AutoLyap handles the SDP modeling and proceeds to solve the SDP numerically. We use the package to numerically verify and extend several convergence results. AutoLyap is currently available in Python and Julia.

math.OC↗

arXiv2026

On the $O(1/T)$ Convergence of Alternating Gradient Descent-Ascent in Bilinear Games

We study the alternating gradient descent-ascent (AltGDA) algorithm in two-player zero-sum games. Alternating methods, where players take turns to update their strategies, have long been recognized as simple and practical approaches for learning in games, exhibiting much better numerical performance than their simultaneous counterparts. However, our theoretical understanding of alternating algorithms remains limited, and results are mostly restricted to the unconstrained setting. We show that for two-player zero-sum games that admit an interior Nash equilibrium, AltGDA converges at an $O(1/T)$ ergodic convergence rate when employing a small constant stepsize. This is the first result showing that alternation improves over the simultaneous counterpart of GDA in the constrained setting. For games without an interior equilibrium, we show an $O(1/T)$ local convergence rate with a constant stepsize that is independent of any game-specific constants. In a more general setting, we develop a performance estimation programming (PEP) framework to jointly optimize the AltGDA stepsize along with its worst-case convergence rate. The PEP results indicate that AltGDA may achieve an $O(1/T)$ convergence rate for a finite horizon $T$, whereas its simultaneous counterpart appears limited to an $O(1/\sqrt{T})$ rate.

cs.GT↗

arXiv2025

Computer-Assisted Design of Accelerated Composite Optimization Methods: OptISTA

The accelerated composite optimization method FISTA (Beck, Teboulle 2009) is suboptimal by a constant factor, and we present a new method OptISTA that improves FISTA by a constant factor of 2. The performance estimation problem (PEP) has recently been introduced as a new computer-assisted paradigm for designing optimal first-order methods. In this work, we present a double-function stepsize-optimization PEP methodology that poses the optimization over fixed-step first-order methods for composite optimization as a finite-dimensional nonconvex QCQP, which can be practically solved through spatial branch-and-bound algorithms, and use it to design the exact optimal method OptISTA for the composite optimization setup. We then establish the exact optimality of OptISTA under the large-scale assumption with a lower-bound construction that extends the semi-interpolated zero-chain construction (Drori, Taylor 2022) to the double-function setup of composite optimization. By establishing exact optimality, our work concludes the search for the fastest first-order methods, with respect to the performance measure of worst-case function value suboptimality, for the proximal, projected-gradient, and proximal-gradient setups involving a smooth convex function and a closed proper convex function.

math.OC↗

arXiv2025

Spatial Branch-and-Bound for Computing Multiplayer Nash Equilibrium

Equilibria of realistic multiplayer games constitute a key solution concept both in practical applications, such as online advertising auctions and electricity markets, and in analytical frameworks used to study strategic voting in elections or assess policy impacts in integrated assessment models. However, efficiently computing these equilibria requires games to have a carefully designed structure and satisfy numerous restrictions; otherwise, the computational complexity becomes prohibitive. In particular, finding even approximate Nash equilibria in general-sum normal-form games with two or more players is known to be PPAD-complete. Current state-of-the-art algorithms for computing Nash equilibria in multiplayer normal-form games either suffer from poor scalability due to their reliance on non-convex optimization solvers, or lack guarantees of convergence to a true equilibrium. In this paper, we propose a formulation of the Nash equilibrium computation problem as a polynomial complementarity problem and develop a complete and sound spatial branch-and-bound algorithm based on this formulation. We provide a qualitative analysis arguing why one should expect our approach to perform well, and show the relationship between approximate solutions to our formulation and that of computing an approximate Nash equilibrium. Empirical evaluations demonstrate that our algorithm substantially outperforms existing complete methods.

cs.GT↗

arXiv2024

Nonlinear conjugate gradient methods: worst-case convergence rates via computer-assisted analyses

We propose a computer-assisted approach to the analysis of the worst-case convergence of nonlinear conjugate gradient methods (NCGMs). Those methods are known for their generally good empirical performances for large-scale optimization, while having relatively incomplete analyses. Using our computer-assisted approach, we establish novel complexity bounds for the Polak-Ribière-Polyak (PRP) and the Fletcher-Reeves (FR) NCGMs for smooth strongly convex minimization. In particular, we construct mathematical proofs that establish the first non-asymptotic convergence bound for FR (which is historically the first developed NCGM), and a much improved non-asymptotic convergence bound for PRP. Additionally, we provide simple adversarial examples on which these methods do not perform better than gradient descent with exact line search, leaving very little room for improvements on the same class of problems.

math.OC↗

arXiv2024

Exterior-point Optimization for Sparse and Low-rank Optimization

Many problems of substantial current interest in machine learning, statistics, and data science can be formulated as sparse and low-rank optimization problems. In this paper, we present the nonconvex exterior-point optimization solver NExOS -- a first-order algorithm tailored to sparse and low-rank optimization problems. We consider the problem of minimizing a convex function over a nonconvex constraint set, where the set can be decomposed as the intersection of a compact convex set and a nonconvex set involving sparse or low-rank constraints. Unlike the convex relaxation approaches, NExOS finds a locally optimal point of the original problem by solving a sequence of penalized problems with strictly decreasing penalty parameters by exploiting the nonconvex geometry. NExOS solves each penalized problem by applying a first-order algorithm, which converges linearly to a local minimum of the corresponding penalized formulation under regularity conditions. Furthermore, the local minima of the penalized problems converge to a local minimum of the original problem as the penalty parameter goes to zero. We then implement and test NExOS on many instances from a wide variety of sparse and low-rank optimization problems, empirically demonstrating that our algorithm outperforms specialized methods.

math.OC↗

arXiv2024

Energy-optimal Timetable Design for Sustainable Metro Railway Networks

We present our collaboration with Thales Canada Inc, the largest provider of communication-based train control (CBTC) systems worldwide. We study the problem of designing energy-optimal timetables in metro railway networks to minimize the effective energy consumption of the network, which corresponds to simultaneously minimizing total energy consumed by all the trains and maximizing the transfer of regenerative braking energy from suitable braking trains to accelerating trains. We propose a novel data-driven linear programming model that minimizes the total effective energy consumption in a metro railway network, capable of computing the optimal timetable in real-time, even for some of the largest CBTC systems in the world. In contrast with existing works, which are either NP-hard or involve multiple stages requiring extensive simulation, our model is a single linear programming model capable of computing the energy-optimal timetable subject to the constraints present in the railway network. Furthermore, our model can predict the total energy consumption of the network without requiring time-consuming simulations, making it suitable for widespread use in managerial settings. We apply our model to Shanghai Railway Network's Metro Line 8 -- one of the largest and busiest railway services in the world -- and empirically demonstrate that our model computes energy-optimal timetables for thousands of active trains spanning an entire service period of one day in real-time (solution time less than one second on a standard desktop), achieving energy savings between approximately 20.93% and 28.68%. Given the compelling advantages, our model is in the process of being integrated into Thales Canada Inc's industrial timetable compiler.

math.OC↗

arXiv2023

Branch-and-Bound Performance Estimation Programming: A Unified Methodology for Constructing Optimal Optimization Methods

We present the Branch-and-Bound Performance Estimation Programming (BnB-PEP), a unified methodology for constructing optimal first-order methods for convex and nonconvex optimization. BnB-PEP poses the problem of finding the optimal optimization method as a nonconvex but practically tractable quadratically constrained quadratic optimization problem and solves it to certifiable global optimality using a customized branch-and-bound algorithm. By directly confronting the nonconvexity, BnB-PEP offers significantly more flexibility and removes the many limitations of the prior methodologies. Our customized branch-and-bound algorithm, through exploiting specific problem structures, outperforms the latest off-the-shelf implementations by orders of magnitude, accelerating the solution time from hours to seconds and weeks to minutes. We apply BnB-PEP to several setups for which the prior methodologies do not apply and obtain methods with bounds that improve upon prior state-of-the-art results. Finally, we use the BnB-PEP methodology to find proofs with potential function structures, thereby systematically generating analytical convergence proofs.

math.OC↗

arXiv2019

On seeking efficient Pareto optimal points in multi-player minimum cost flow problems with application to transportation systems

In this paper, we propose a multi-player extension of the minimum cost flow problem inspired by a transportation problem that arises in modern transportation industry. We associate one player with each arc of a directed network, each trying to minimize its cost function subject to the network flow constraints. In our model, the cost function can be any general nonlinear function, and the flow through each arc is an integer. We present algorithms to compute efficient Pareto optimal point(s), where the maximum possible number of players (but not all) minimize their cost functions simultaneously. The computed Pareto optimal points are Nash equilibriums if the problem is transformed into a finite static game in normal form.

math.OC↗

arXiv2019

On Convergence of Heuristics Based on Douglas-Rachford Splitting and ADMM to Minimize Convex Functions over Nonconvex Sets

Recently, heuristics based on the Douglas-Rachford splitting algorithm and the alternating direction method of multipliers (ADMM) have found empirical success in minimizing convex functions over nonconvex sets, but not much has been done to improve the theoretical understanding of them. In this paper, we investigate convergence of these heuristics. First, we characterize optimal solutions of minimization problems involving convex cost functions over nonconvex constraint sets. We show that these optimal solutions are related to the fixed point set of the underlying nonconvex Douglas-Rachford operator. Next, we establish sufficient conditions under which the Douglas-Rachford splitting heuristic either converges to a point or its cluster points form a nonempty compact connected set. In the case where the heuristic converges to a point, we establish sufficient conditions for that point to be an optimal solution. Then, we discuss how the ADMM heuristic can be constructed from the Douglas-Rachford splitting algorithm. We show that, unlike in the convex case, the algorithms in our nonconvex setup are not equivalent to each other and have a rather involved relationship between them. Finally, we comment on convergence of the ADMM heuristic and compare it with the Douglas-Rachford splitting heuristic.

math.OC↗

arXiv2018

A Two-Step Linear Programming Model for Energy-Efficient Timetables in Metro Railway Networks

In this paper we propose a novel two-step linear optimization model to calculate energy-efficient timetables in metro railway networks. The resultant timetable minimizes the total energy consumed by all trains and maximizes the utilization of regenerative energy produced by braking trains, subject to the constraints in the railway network. In contrast to other existing models, which are NP-hard, our model is computationally the most tractable one being a linear program. We apply our optimization model to different instances of service PES2-SFM2 of line 8 of Shanghai Metro network spanning a full service period of one day (18 hours) with thousands of active trains. For every instance, our model finds an optimal timetable very quickly (largest runtime being less than 13s) with significant reduction in effective energy consumption (the worst case being 19.27%). Code based on the model has been integrated with Thales Timetable Compiler - the industrial timetable compiler of Thales Inc that has the largest installed base of communication-based train control systems worldwide.

math.OC↗

arXiv2015

A Robust Mixed Integer Optimization Model to Utilize Regenerative Energy of Trains in a Railway Network

In this paper we present a robust mixed integer optimization model to utilize regenerative braking energy produced by trains in a railway network. An electric train produces regenerative energy during braking, which is often lost in present technology. To utilize this energy we calculate a timetable which maximizes the total overlapping time between the braking and accelerating phases of suitable train pairs, so that the regenerative energy of a braking train can be transferred to a suitable accelerating one. We apply our optimization model to different instances of a railway network for a time horizon spanning six hours. For each instance, our model finds an optimal timetable very quickly (largest running time being 86.64 seconds). Compared to the existing timetables, we observe significant increase in utilization of regenerative energy for every instance.

math.OC↗