Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,742 papers · 148 categories

Trend · papers per month

101202303404 · Jun 202019922001200920172026
48 results for polynomial-sized linear program

This paper shows neural networks can solve complex graph problems efficiently.

problem Solving exact maximum flow computation and minimum spanning tree problems.
method Introduces Max-Affine Arithmetic Programs and shows equivalence to neural networks.
result Two combinatorial optimization problems can be solved with polynomial-size neural networks.

Develops exact convex optimization formulations for neural networks.

problem Training two-layer neural networks with rectified linear units.
method Uses semi-infinite duality and minimum norm regularization to develop exact convex optimization formulations.
result Shows equivalence of ReLU networks trained with weight decay to block 1\ell_1 penalized convex models.

Study counterfactuals in combinatorial choice using a representative agent model.

problem Analyzing decision-making from aggregated binary polytope data.
method Nonparametric approach based on a representative agent model, solving polynomial and mixed-integer convex programs.
result Developed a method for counterfactual prediction that works even under model misspecification.

New formulation of MIL using shapelets for better classifier of bags.

problem Finding a good classifier of bags based on shapelets.
method Formulation using all possible shapelets, reduced to DC programs, and heuristic options.
result Richer class of classifiers with theoretical justification and empirical validation.

This work explores representation complexity in RL paradigms, revealing model-based RL as the easiest task.

problem Investigating the representation complexity gap among model-based, policy-based, and value-based RL.
method Demonstrated through analysis of Markov decision processes (MDPs) and introduced new classes of MDPs.
result Representation complexity hierarchy: model-based RL > policy-based RL > value-based RL.

New algorithm learns sparse linear MDPs with polynomial interactions, improving sample complexity.

problem Learning optimal policies in sparse linear MDPs with limited interactions and unknown features.
method Developed a polynomial-time algorithm using feature selection and emulator for sparse linear MDPs.
result First polynomial-time algorithm for learning near-optimal policies in k-sparse linear MDPs.

New insights into natural exponential families improve regret bounds for bandit problems.

problem Improving regret bounds for bandit problems with subexponential tails.
method Proving self-concordance for natural exponential families and applying to bandits.
result Optimistic algorithms for generalized linear bandits have second-order regret bounds that are free of an exponential dependence on problem parameters.

Solving linear programs by using entropic penalization has recently attracted new interest in the optimization community, since this strategy forms the basis for the fastest-known algorithms for the optimal transport problem, with many applications in modern large-scale machine learning. Crucial to these applications h…

2018-06-05abs ↗pdf ↗

This paper presents an acceleration framework for packing linear programming problems where the amount of data available is limited, i.e., where the number of constraints m is small compared to the variable dimension n. The framework can be used as a black box to speed up linear programming solvers dramatically, by two…

2017-11-17abs ↗pdf ↗

The paper proves barriers to approximating functions with small weights and depth in neural networks.

problem Proving barriers to approximating functions with constant depth neural networks.
method Reduction to open problems and natural-proof barriers in circuit complexity, and a new approach to polynomially-bounded functions.
result There are fundamental barriers to proving results beyond depth 4 for constant-depth neural networks.

Unified approach for optimizing predictions in linear programming and inverse problems.

problem Optimizing predictions in linear programming and inverse problems.
method Maximum optimality margin approach.
result Unified approach that balances computational efficiency and theoretical properties.

We obtain the first positive results for bounded sample compression in the agnostic regression setting with the p\ell_p loss, where p[1,]p\in [1,\infty]. We construct a generic approximate sample compression scheme for real-valued function classes exhibiting exponential size in the fat-shattering dimension but independen…

2018-10-03abs ↗pdf ↗

Faster algorithms for structured SVMs reduce computation time.

problem Efficiently solving quadratic programming problems with specific structures.
method Designing nearly-linear time algorithms for quadratic programs with low-rank factorizations and few linear constraints.
result First nearly-linear time algorithms for solving quadratic programs with specific structures.

We give the first polynomial-time algorithm for performing linear or polynomial regression resilient to adversarial corruptions in both examples and labels. Given a sufficiently large (polynomial-size) training set drawn i.i.d. from distribution D and subsequently corrupted on some fraction of points, our algorithm out…

2018-03-08abs ↗pdf ↗

Maximum entropy distributions with discrete support in mm dimensions arise in machine learning, statistics, information theory, and theoretical computer science. While structural and computational properties of max-entropy distributions have been extensively studied, basic questions such as: Do max-entropy distributio…

2017-11-06abs ↗pdf ↗

This study optimizes cycle representatives in persistent homology using linear programming.

problem Non-uniqueness of cycle representatives in persistent homology creates ambiguity.
method Optimization of cycle representatives using linear programming methods.
result Optimization reduces the size of cycle representatives and is effective in most data sets.

A classification algorithm, called the Linear Centralization Classifier (LCC), is introduced. The algorithm seeks to find a transformation that best maps instances from the feature space to a space where they concentrate towards the center of their own classes, while maximimizing the distance between class centers. We …

2017-12-22abs ↗pdf ↗

This paper improves online learning algorithms for LP problems, achieving better regret bounds.

problem Achieving optimal regret bounds in online linear programming.
method Develops a new framework for first-order online learning algorithms under certain error bound conditions.
result First-order learning algorithms achieve o(T)o(\sqrt{T}) regret in continuous support and O(logT)\mathcal{O}(\log T) regret in finite support, improving over O(T)\mathcal{O}(\sqrt{T}).

This dissertation uses ILP to learn Bayesian network structures efficiently.

problem Learning the structure of Bayesian networks from data.
method Integer Linear Programming formulation with cluster constraints and cutting planes.
result The approach finds feasible solutions for Bayesian network structures efficiently.

Neural network discovers exact solutions to QP with linear constraints.

problem Discovering exact solutions to Quadratic Programs (QP) with linear constraints using neural networks.
method Proposes a neural network modeling approach that analytically derives model parameters from problem coefficients, ensuring closed-form solutions without training.
result The closed-form NN model produces exact solutions for every critical region of the QP solution function, outperforming DNNs and commercial solvers in terms of optimality and feasibility.

SurvLIME-Inf simplifies explanation of survival models using a linear programming approach.

problem Explain complex survival models using simple linear programming.
method Uses LL_{\infty }-norm for feature importance and explains black-box models.
result SurvLIME-Inf outperforms SurvLIME in small training set scenarios.

Study tests feasibility of linear programs with bandit feedback.

problem Testing feasibility of unknown linear programs with bandit feedback.
method Developed a novel test based on low-regret algorithms and a nonasymptotic law of iterated logarithms.
result Proved that the test is reliable and adapts to the signal level, with mean sample costs scaling as \( \widetilde{O}(d^2/Γ^2) \).

New method for identifying best arm in batched multi-armed bandit problems.

problem Identifying the best arm in multi-armed bandit problems where arms are sampled in batches.
method General linear programming framework for best arm identification in batched multi-armed bandit problems.
result Demonstrated good performance in numerical studies compared to UCB-type or Thompson sampling methods.

Eigen-decomposition simplifies quadratic programming with equality constraints.

problem Optimizing solutions under linear equality constraints in quadratic programming.
method Eigenvalue decomposition of the quadratic term matrix to project optimal solutions.
result Established a linear mapping between EQP formulations with and without diagonalized QQ.