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.

168,695 papers · 148 categories

Trend · papers per month

8.4%16.7%25.1%33.4% · Jun 202019922001200920172026
48 results for Mixed Constrained Optimization

Adapts Bayesian optimization for mixed constraints in aircraft design.

problem Optimizing expensive black box functions with mixed constraints.
method Super efficient global optimization with upper trust bound for constraints, Gaussian process uncertainty, refinement procedure.
result Superior performance on aircraft design problem compared to state-of-the-art solvers.

CPP solves chance constrained optimization problems with a framework that combines samples and quantile lemma.

problem Chance constrained optimization problems with constraints on random variables.
method CPP framework using samples and quantile lemma to transform into deterministic problem.
result CPP provides a posteriori guarantees on constraint satisfaction and can handle different types of chance constraints.

Bayesian optimization reduces hyperparameters for mixed variable design problems.

problem Optimizing designs with a large number of mixed continuous, integer, and categorical variables.
method Adaptive dimension reduction using partial least squares for fewer hyperparameters.
result Significant improvement in performance compared to genetic algorithms.

Paper tackles best mixed arm identification with cost constraints in bandit models.

problem Finding the best mixed arm with cost constraints in a stochastic bandit model.
method Proposes SFSR algorithm combining successive reject and score-function-based rejection criteria.
result Upper and lower bounds on mis-identification probability show exponential decay with budget.

Improves decentralized learning by optimizing graph mixing for data heterogeneity.

problem Data heterogeneity impacts convergence in decentralized learning, but existing methods ignore this.
method Characterized and quantified the relationship between graph mixing and data heterogeneity. Proposed an optimization approach to improve convergence.
result Our approach leads to improved test performance across various tasks.

Unified framework for constrained diffusion models on nonconvex sets with efficient landing mechanism.

problem Efficiently modeling generative models under nonconvex constraints.
method Unified framework with overdamped and underdamped dynamics, landing mechanism.
result Significantly reduces computational cost while maintaining sample quality.

Joint sparsity offers powerful structural cues for feature selection, especially for variables that are expected to demonstrate a "grouped" behavior. Such behavior is commonly modeled via group-lasso, multitask lasso, and related methods where feature selection is effected via mixed-norms. Several mixed-norm based spar…

2012-04-06abs ↗pdf ↗

A new portfolio optimization model minimizes maximum drawdown, offering faster and more robust solutions.

problem Optimizing portfolios during financial distress, especially during crises.
method Linearization of Markowitz model based on maximum drawdown, with a Mixed-Integer Linear Programming variation.
result 200 times faster solving time with a more profitable and robust solution.

A new framework uses an Incremental Transformer to design geopolymer mixtures efficiently.

problem Designing geopolymer mixtures with limited data and physical constraints.
method Topology-aware surrogate framework guided by Incremental Transformer.
result The design space is redundant, with fewer effective mixture regimes.

Improved convergence for nonconvex optimization with dependent data.

problem Constrained smooth nonconvex optimization with dependent data.
method Stochastic projected gradient methods under a general dependent data sampling scheme.
result Achieved worst-case rate of convergence ildeO(t1/4) ilde{O}(t^{-1/4}) and complexity ildeO(ε4) ilde{O}(\varepsilon^{-4}).

New MMM captures hierarchical marketing effects and sign restrictions.

problem Measuring effectiveness of marketing activities with hierarchical structure and sign constraints.
method Proposes a constrained maximum likelihood approach using Hamiltonian Monte Carlo algorithm.
result Demonstrates superior performance on real datasets compared to multi-stage methods.

This paper proposes a new randomized strategy for adaptive MCMC using Bayesian optimization. This approach applies to non-differentiable objective functions and trades off exploration and exploitation to reduce the number of potentially costly objective function evaluations. We demonstrate the strategy in the complex s…

2011-10-29abs ↗pdf ↗

MOMENT selects and estimates mixed-effects models using moment identities.

problem Selecting and estimating random-effects covariance matrix and fixed-effects coefficients in multiresponse linear mixed-effects models.
method MOMENT is a stage-wise moment-based framework that reduces the random-effects selection problem to a smooth constrained convex optimization problem.
result MOMENT performs competitively and can outperform separate univariate analyses for correlated responses.

Paper proposes a novel optimization method for disaggregating smart meter data.

problem Energy disaggregation, inferring appliance-specific energy consumption from aggregate meter data.
method Two-stage optimization approach: first phase uses mixed integer programming, second phase binary quadratic optimization with penalty terms and appliance constraints.
result Proposed method successfully reconstructs appliance signatures, overcoming previous optimization-based methods' limitations.

Unified framework for solving MDPs with stochastic mirror descent.

problem Approximately solving infinite-horizon Markov decision processes (MDPs).
method Primal-dual stochastic mirror descent for MDPs with a unified framework.
result Computes ε-optimal policies with expected samples for both average-reward and discounted MDPs.

Proposes r2SGLD for efficient constrained exploration in non-convex learning.

problem Stagnation in high-temperature chains of reSGLD in distribution tails.
method r2SGLD: replica exchange with reflection steps in a bounded domain.
result Reflection steps enhance mixing rates with quadratic improvement in domain diameter.

We consider the maximum likelihood estimation of sparse inverse covariance matrices. We demonstrate that current heuristic approaches primarily encourage robustness, instead of the desired sparsity. We give a novel approach that solves the cardinality constrained likelihood problem to certifiable optimality. The approa…

2019-06-25abs ↗pdf ↗

A Ph.D. thesis proposes an efficient approach for optimizing aircraft eco-design with high-dimensional mixed integer variables.

problem Optimizing aircraft eco-design with high-dimensional mixed integer variables.
method EGO optimization approach based on sequential enrichment of adaptive surrogate models, adapted for high-dimensional and mixed variable spaces.
result Effective parameterization tools significantly reduce the number of design variables, enabling optimization of complex aircraft concepts.

The study examines robustness auditing for linear regression, improving existing methods and identifying computational challenges.

problem Detecting small subsets of data that can reverse regression coefficients.
method Empirical study of mixed integer quadratically constrained optimization and exact greedy methods, combined with a spectral algorithm.
result Existing methods largely outperform state of the art, but computational bottlenecks remain, especially for higher dimensions.

A new sampling method for log-concave distributions with warm starts and barriers.

problem Sampling from log-concave distributions constrained by convex bodies with barriers.
method Robust sampling framework using spectral approximations to Hessian of barrier functions.
result Improved mixing times for polytopes and spectrahedra, faster than previous methods.

This work tackles sparse coding in DLRA for interpretable multiway data.

problem Sparse coding in DLRA for interpretable multiway data.
method Proposes a new sparse-coding subproblem (MSC) and several algorithms to solve it.
result DLRA extends low-rank approximations, reducing variance and enhancing interpretability.

SBMs learn manifold-like structures by mixing samples with a non-conservative field.

problem How SBMs learn data distributions on low-dimensional manifolds.
method Investigating linear approximations and subspaces of local feature vectors during diffusion.
result SBMs mix samples by a non-conservative field within the manifold, maintaining manifold-like structure.

Regularized empirical risk minimization with constrained labels (in contrast to fixed labels) is a remarkably general abstraction of learning. For common loss and regularization functions, this optimization problem assumes the form of a mixed integer program (MIP) whose objective function is non-convex. In this form, t…

2016-02-22abs ↗pdf ↗

Bayesian optimization tackles mixed discrete-continuous problems with Gaussian processes.

problem Optimizing problems with both discrete and continuous variables using costly simulations.
method Relaxing discrete variables into continuous latent variables, using Bayesian optimization, and incorporating compatibility constraints with Lagrangians.
result Comparative analysis of different mixed Bayesian optimization approaches.

MOCA-HESP optimizes high-dimensional combinatorial and mixed spaces using hyper-ellipsoid partitioning.

problem Challenges in optimizing high-dimensional, combinatorial and mixed spaces.
method MOCA-HESP uses hyper-ellipsoid space partitioning with different categorical encoders and multi-armed bandit for adaptive selection.
result MOCA-HESP outperforms existing methods on various synthetic and real-world benchmarks.

Study improves Bayesian optimisation with ensemble transfer learning.

problem Improving sample efficiency in Bayesian optimisation of expensive functions.
method Empirical analysis of ensemble-based transfer learning methods and pipeline components.
result Two components (warm start initialisation and positive weight constraint) improve transfer learning Bayesian optimisation performance.

Determinantal Point Processes (DPPs) are probabilistic models that arise in quantum physics and random matrix theory and have recently found numerous applications in computer science. DPPs define distributions over subsets of a given ground set, they exhibit interesting properties such as negative correlation, and, unl…

2016-08-01abs ↗pdf ↗

Value-based reinforcement learning (RL) methods like Q-learning have shown success in a variety of domains. One challenge in applying Q-learning to continuous-action RL problems, however, is the continuous action maximization (max-Q) required for optimal Bellman backup. In this work, we develop CAQL, a (class of) algor…

2019-09-26abs ↗pdf ↗

We introduce Deep Reasoning Networks (DRNets), an end-to-end framework that combines deep learning with reasoning for solving complex tasks, typically in an unsupervised or weakly-supervised setting. DRNets exploit problem structure and prior knowledge by tightly combining logic and constraint reasoning with stochastic…

2019-06-03abs ↗pdf ↗

We define new Riemannian structures on 7-manifolds by a differential form of mixed degree which is the critical point of a (possibly constrained) variational problem over a fixed cohomology class. The unconstrained critical points generalise the notion of a manifold of holonomy G2G_2, while the constrained ones give ri…

2004-11-29abs ↗pdf ↗