Improved Bayesian learning rule handles positive-definite constraints efficiently.
problem Bayesian learning rule struggles with positive-definite constraints.
method Proposes an improved rule using Riemannian gradient methods for block-coordinate natural parameterization.
result Outperforms existing methods without increased computation.
New loss function handles uncertain constraints in CSLO problems.
problem Handling uncertain inequality constraints in CSLO with machine learning predictions.
method Introduces SPO-RC loss and SPO-RC+ surrogate, trains on truncated datasets, corrects bias.
result SPO-RC+ effectively manages constraint uncertainty and improves performance.
ADMM solves constrained CASH problems by breaking them into smaller, manageable pieces.
problem Handling black-box constraints in CASH problems.
method Leverages ADMM optimization framework to decompose CASH problems.
result ADMM facilitates incorporation of black-box constraints.
We use the conformal method to obtain solutions of the Einstein-scalar field gravitational constraint equations. Handling scalar fields is a bit more challenging than handling matter fields such as fluids, Maxwell fields or Yang-Mills fields, because the scalar field introduces three extra terms into the Lichnerowicz e…
Additive Gaussian process framework handles monotonicity constraints in high dimensions.
problem Handling monotonicity constraints in high-dimensional data.
method Additive Gaussian process framework with MaxMod algorithm for dimension reduction.
result Framework enables to satisfy monotonicity constraints everywhere in the input space.
Safe reinforcement learning for autonomous vehicles using prediction constraints.
problem Safe reinforcement learning for safety-critical applications like autonomous vehicles.
method Use prediction to constrain exploration in reinforcement learning models.
result Successfully learned intersection handling behaviors on an autonomous vehicle.
A new RL method handles uncertainty and constraints in real-time optimization.
problem Real-time optimization under process uncertainty and constraints.
method Chance-constrained reinforcement learning to handle probabilistic state constraints.
result Satisfies process constraints with high probability in real-time.
Unified framework for hard affine SDP constraints in vRKHSs.
problem Incorporating shape constraints into predictive models for rich function classes.
method Unified convex optimization framework using second-order cone tightening.
result Unified and modular approach for handling multiple shape constraints.
We establish a general gluing theorem for constant mean curvature solutions of the vacuum Einstein constraint equations. This allows one to take connected sums of solutions or to glue a handle (wormhole) onto any given solution. Away from this handle region, the initial data sets we produce can be made as close as desi…
First-order method solves stochastic bilevel optimization with linear constraints.
problem Stochastic bilevel optimization with linear constraints and noise.
method Developed a novel framework using gradient-based techniques and smoothed penalty functions.
result Achieved finite-time convergence guarantees for (δ,ε)-Goldstein stationary points. Meta-gradient D4PG optimizes performance and constraint adherence in RL.
problem Balancing performance and adherence to complex constraints in RL.
method Uses meta-gradients to find a balance between expected return and minimizing constraint violations.
result Meta-gradient D4PG consistently outperforms baselines across MuJoCo domains.
Statistical models with constrained probability distributions are abundant in machine learning. Some examples include regression models with norm constraints (e.g., Lasso), probit, many copula models, and latent Dirichlet allocation (LDA). Bayesian inference involving probability distributions confined to constrained d…
In urban environments, supply resources have to be constantly matched to the "right" locations (where customer demand is present) so as to improve quality of life. For instance, ambulances have to be matched to base stations regularly so as to reduce response time for emergency incidents in EMS (Emergency Management Sy…
Estimation in generalized linear models (GLM) is complicated by the presence of constraints. One can handle constraints by maximizing a penalized log-likelihood. Penalties such as the lasso are effective in high dimensions, but often lead to unwanted shrinkage. This paper explores instead penalizing the squared distanc…
IPO optimizes reinforcement learning with constraints for better performance.
problem Maximizing long-term reward while satisfying cumulative constraints in decision problems.
method Interior-point Policy Optimization (IPO) using logarithmic barrier functions.
result IPO outperforms state-of-the-art baselines in reward maximization and constraint satisfaction.
PARAFAC2 has demonstrated success in modeling irregular tensors, where the tensor dimensions vary across one of the modes. An example scenario is modeling treatments across a set of patients with the varying number of medical encounters over time. Despite recent improvements on unconstrained PARAFAC2, its model factors…
The paper explores how to learn models that respect constraints in probabilistic learning.
problem Learning models that respect declared constraints in probabilistic learning.
method Mathematical inquiry on tractable probabilistic models like sum-product networks.
result Determines conditions under which constraints can be integrated with model learning.
Given a collection of N solutions of the (3+1) vacuum Einstein constraint equations which are asymptotically Euclidean, we show how to construct a new solution of the constraints which is itself asymptotically Euclidean, and which contains specified sub-regions of each of the N given solutions. This generalizes earlier…
We address the problem of solving convex optimization problems with many convex constraints in a distributed setting. Our approach is based on an extension of the alternating direction method of multipliers (ADMM) that recently gained a lot of attention in the Big Data context. Although it has been invented decades ago…
The paper proposes modern computational methods for optimizing reinsurance contracts.
problem Optimizing catastrophe excess-of-loss reinsurance contracts with realistic constraints and risk measures.
method Two approaches: simulated annealing for local search and quantum branch & bound for future potential.
result Quantum branch & bound approach shows potential for future optimization with quantum computers.
New algorithm clusters data and learns kernels without relaxing constraints.
problem Learning kernels or distance metrics from pairwise constraints without losing generalization.
method Joint clustering and kernel learning without relaxing constraints.
result Outperforms existing approaches on diverse datasets.
The superior performance of ensemble methods with infinite models are well known. Most of these methods are based on optimization problems in infinite-dimensional spaces with some regularization, for instance, boosting methods and convex neural networks use L1-regularization with the non-negative constraint. However…
In dictionary selection, several atoms are selected from finite candidates that successfully approximate given data points in the sparse representation. We propose a novel efficient greedy algorithm for dictionary selection. Not only does our algorithm work much faster than the known methods, but it can also handle mor…
Bayesian optimization tackles constrained high-dimensional problems with penalties and trust regions.
problem Constrained optimization in high-dimensional black-box settings with expensive evaluations and complex feasibility regions.
method Penalty formulation, surrogate model, trust region strategy, Expected Improvement acquisition function.
result The proposed Trust Region method identifies high-quality feasible solutions with fewer evaluations and maintains stable performance.
We present a general framework for solving a large class of learning problems with non-linear functions of classification rates. This includes problems where one wishes to optimize a non-decomposable performance metric such as the F-measure or G-mean, and constrained training problems where the classifier needs to sati…
CANs improve GANs by enforcing structured constraints during training.
problem Generating valid structured objects like molecules and game maps from examples alone.
method Constrained Adversarial Networks (CANs) embed constraints into the model during training, penalizing invalid structures.
result CANs efficiently generate high-quality and novel valid structures.
Hybrid quantum algorithm tackles binary optimization problems with multiple constraints.
problem Efficiently solving binary optimization problems with multiple constraints using quantum algorithms.
method Combines QAOA with penalty dephasing and Zeno effect for non-Ising constraints.
result Significant improvement in solving practical aircraft loading problems.
Proposes a constraint for deep clustering to handle both simple and complex topologies.
problem Limited prior knowledge for deep clustering methods to perform well on complex topologies.
method Introduces a constraint using symmetric InfoNCE to enhance deep clustering performance.
result The constraint improves deep clustering methods' performance on both simple and complex topologies.
In this paper we explore the idea of looking at the Dirac quantisation conditions as ℏ-dependent constraints on the tangent bundle to phase-space. Starting from the path-integral version of classical mechanics and using the natural Poisson brackets structure present in the cotangent bundle to the tangent bundle o…
HabitatAgent offers a multi-agent system for transparent housing consultation.
problem Opaque reasoning and brittle multi-constraint handling in housing recommendation systems.
method HabitatAgent is a multi-agent architecture with specialized roles for memory, retrieval, generation, and validation.
result HabitatAgent achieves 95% accuracy in real user consultation scenarios, significantly outperforming a strong baseline.
The topology of broken Lefschetz fibrations is studied by means of handle decompositions. We consider a slight generalization of round handles, and describe the handle diagrams for all that appear in dimension four. We establish simplified handlebody and monodromy representations for a certain subclass of broken Lefsch…
Efficiently verifies neural networks by handling neuron splits, improving speed and accuracy.
problem Handling neuron split constraints in incomplete neural network verification.
method β-CROWN, which optimizes parameters β to encode neuron splits and uses them in bound propagation.
result β-CROWN significantly speeds up verification while maintaining high accuracy.
New algorithm solves minimax games with linear constraints.
problem Nonconvex minimax games with coupled linear constraints.
method Primal-dual alternating proximal gradient (PDAPG) algorithm.
result Achieves ε-stationary solution within O(ε^(-2)) iterations for strongly concave settings.
New method optimizes processes under constraints using bivariate Gaussian models.
problem Optimizing processes with constraints using traditional methods.
method Developed a constrained expected improvement acquisition function using bivariate Gaussian process models.
result Demonstrated improved performance in a manufacturing cure process optimization.
In standard reinforcement learning (RL), a learning agent seeks to optimize the overall reward. However, many key aspects of a desired behavior are more naturally expressed as constraints. For instance, the designer may want to limit the use of unsafe actions, increase the diversity of trajectories to enable exploratio…
The paper develops methods for sampling from log-concave distributions with constraints.
problem Sampling from log-concave distributions with constraints.
method Randomized midpoint discretization of Langevin diffusions with various projections.
result New convergence guarantees for constrained Langevin algorithms.
Paper solves high-order portfolio optimization with cardinality constraint.
problem Solving non-convex cardinality constrained high-order portfolio optimization.
method Transformed cardinality constraint into penalty term, proposed pDCA, pDCAe, and SCA algorithms.
result Proposed algorithms achieve high utility and sparse solutions efficiently.
We present an adaptive online gradient descent algorithm to solve online convex optimization problems with long-term constraints , which are constraints that need to be satisfied when accumulated over a finite number of rounds T , but can be violated in intermediate rounds. For some user-defined trade-off parameter β…
Algorithm improves movie recommendation efficiency with fairness constraints.
problem Improving movie recommendation efficiency with fairness constraints in combinatorial semi-bandits.
method Adopted Thompson Sampling with beta priors and Bernoulli likelihoods to handle fairness constraints.
result Time-averaged regret upper bounded by $\frac{N}{2η} + O\left(\frac{\sqrt{mNT\ln T}}{T}
ight)$, with fairness constraints satisfied.
A new stochastic method handles ensemble creation with cost constraints.
problem Creating ensembles under cost limitations in decision-making.
method Introducing a novel stochastic approach to solve the knapsack problem.
result The approach efficiently incorporates ensemble accuracy and cost constraints.
OLLA framework efficiently samples from constrained distributions with nonconvex constraints.
problem Sampling from constrained distributions with nonconvex constraints is challenging.
method Overdamped Langevin with Landing (OLLA) framework that handles both equality and inequality constraints.
result OLLA converges exponentially fast to the constrained target density in W2 distance. An algorithm for efficient experimentation in a dynamic environment with personalized preferences and context drifts.
problem Efficiently recommending decisions to users with personalized preferences in a context where the environment is changing over time.
method Dri-MED, inspired from the linear version of the MED strategy, adapted to handle non-stationary heteroskedastic noise.
result The instance-dependent regret scales as $ ilde{\mathcal O}\left(\fracκ{ ildeΔ}d^2(\log(T)
ight)$, with ildeΔ being the constraint-aware sub-optimality gap. The optimization of expensive to evaluate, black-box, mixed-variable functions, i.e. functions that have continuous and discrete inputs, is a difficult and yet pervasive problem in science and engineering. In Bayesian optimization (BO), special cases of this problem that consider fully continuous or fully discrete doma…
Algorithm optimizes constrained reinforcement learning with dual variables.
problem Minimizing convex functional subject to convex constraint in large state spaces.
method VPDPO algorithm using Lagrangian and Fenchel duality.
result Achieves sublinear regret and constraint violation, globally optimal policy.
Optimizes portfolios using CPT utility via convex optimization.
problem Maximizing CPT utility in portfolio selection.
method Minorization-maximization (MM) algorithm and convex-concave (CC) procedure.
result Problems can be solved globally and efficiently.
MESMOC optimizes constrained multi-objective problems efficiently.
problem Constrained multi-objective optimization with expensive function evaluations.
method Max-value Entropy Search in the output space.
result MESMOC selects high-quality Pareto solutions efficiently.
Safe reinforcement learning with logical constraints for optimal policy synthesis.
problem Ensuring safety during reinforcement learning while maximizing goal satisfaction.
method Adaptive safe padding that synthesizes optimal control policies satisfying temporal logic formulas.
result The proposed method handles the trade-off between exploration and safety with theoretical guarantees.
TabNAS improves neural architecture search for tabular datasets by rejecting suboptimal architectures.
problem Finding optimal neural architectures for tabular datasets with resource constraints.
method Develops a reinforcement learning controller motivated by rejection sampling to handle resource constraints.
result TabNAS finds better models that obey resource constraints compared to previous methods.