The paper optimizes policies constrained to Schur stabilizing controllers using a Newton-type algorithm.
problem Optimizing policies under linear constraints in control systems.
method Newton-type algorithm on a manifold of Schur stabilizing controllers with a Riemannian metric.
result Local convergence guarantees for the Newton-type algorithm without relying on exponential mapping or retractions.
Proposes a framework for learning constrained motor skills.
problem Learning constrained motor skills in robotic systems.
method Exploits probabilistic properties of multiple demonstrations in a linearly constrained optimization problem.
result Proposes a non-parametric solution for constrained motor skills.
Unified framework for nonconvex matrix completion with linearly parameterized factors.
problem Matrix completion with improved accuracy using linearly parameterized factors.
method Unified nonconvex optimization framework with Correlated Parametric Factorization condition.
result Uniform upper bounds for low-rank estimation at any local minimum.
New projection techniques reduce the frequency of projections in solving LCPs.
problem Solving linearly constrained problems efficiently with reduced projection frequency.
method Delayed projection technique to call a projection less frequently.
result Theoretical and practical improvements in convergence rates and efficiency.
This paper extends forecast reconciliation to non-linearly constrained time series.
problem Forecasting time series with non-linear constraints.
method Non-linearly Constrained Reconciliation (NLCR) algorithm that adjusts forecasts to meet non-linear constraints.
result NLCR significantly improves forecast accuracy compared to benchmarks.
A new algorithm solves bilevel optimization with linear constraints.
problem Solving bilevel optimization problems with coupled linear constraints.
method Penalty and augmented Lagrangian methods reformulate the problem; a single-loop, first-order algorithm proposed.
result Improved convergence rates compared to prior methods.
LinConTS improves regret and constraint violations in probabilistic linearly constrained bandits.
problem Maximizing cumulative reward under probabilistic linear constraints.
method LinConTS, a Thompson Sampling-based algorithm for bandits with linear constraints.
result LinConTS achieves O(log T) regret and constraint violations for suboptimal arms.
Hyper-parameter optimization remains as the core issue of Gaussian process (GP) for machine learning nowadays. The benchmark method using maximum likelihood (ML) estimation and gradient descent (GD) is impractical for processing big data due to its O(n3) complexity. Many sophisticated global or local approximation m…
A new algorithm for solving constrained convex optimization problems efficiently.
problem Constrained convex optimization problems requiring high accuracy solutions.
method Second-Order Conditional Gradient Sliding (SOCGS) algorithm, using projection-free methods to solve quadratic subproblems inexactly.
result Converges quadratically in primal gap after a finite number of linearly convergent iterations.
We develop randomized (block) coordinate descent (CD) methods for linearly constrained convex optimization. Unlike most CD methods, we do not assume the constraints to be separable, but let them be coupled linearly. To our knowledge, ours is the first CD method that allows linear coupling constraints, without making th…
A scalable framework optimizes multi-asset portfolios with constraints.
problem Optimizing multi-asset portfolios with inequality constraints.
method Integrates neural policies with Pontryagin's Maximum Principle, enforcing feasibility via log-barrier regularization.
result Recover KKT-optimal policies in high-dimensional problems without violating constraints.
New method solves constrained stochastic optimization problems efficiently.
problem Online statistical inference of constrained stochastic nonlinear optimization problems.
method Stochastic Sequential Quadratic Programming (StoSQP) with iterative sketching solver.
result The rescaled primal-dual sequence converges to a mean-zero Gaussian distribution.
New methods solve saddle point problems without line search.
problem Solving saddle point problems efficiently and adaptively.
method Auto-conditioned primal-dual hybrid gradient (AC-PDHG) and auto-conditioned ADMM (AC-ADMM) methods.
result Methods achieve optimal complexity and convergence guarantees.
New method calibrates neural network predictions for better reliability.
problem Improper probability estimates from deep networks leading to unreliable predictions.
method Proposes a constrained optimization approach for a monotonic calibration map.
result Achieves state-of-the-art performance across various datasets and models.
Unified framework for ESG-inclusive portfolio optimization and pricing.
problem Incorporating ESG ratings into dynamic asset pricing theory.
method Introducing ESG-valued return as a linear transformation of financial and ESG scores, preserving traditional risk aversion with an ESG affinity parameter.
result Developed a more complex portfolio optimization problem in a space governed by reward, risk, and ESG score.
Heuristic algorithm for portfolio optimization reduces solve times to milliseconds.
problem Mean-variance portfolio optimization with various constraints.
method Alternating Direction Method of Multipliers (ADMM).
result Achieves performance bounds and solves problems in milliseconds.
Improved Frank-Wolfe algorithm for constrained convex optimization with nearest extreme point oracle.
problem Constrained smooth convex minimization with limited linear optimization oracle access.
method Frank-Wolfe algorithm with nearest extreme point oracle.
result Improved complexity bounds for specific feasible sets, including linear convergence for 0ext−−1 polytopes. This note presents an analytic construction of the optimal unit-norm direction hat(x) = x/|x| that maximizes or minimizes the objective linear expression, B . hat(x), subject to a system of linear constraints of the form [A] . x = 0, where x is an unknown n-dimensional real vector to be determined up to an overall norm…
Boosted Difference of Convex Functions Algorithm solves VaR constrained portfolio optimization.
problem Designing VaR optimal portfolios under financial regulations.
method Boosted Difference of Convex Functions Algorithm (BDCA) with a novel line search framework.
result BDCA linearly converges to a Karush-Kuhn-Tucker point for VaR constrained portfolio problems.
Neural networks learn vector fields constrained by linear operators.
problem Learning vector fields from physical systems with linear operator constraints.
method Model the target function as a linear transformation of a potential field, which is a neural network.
result Predictions of the target function satisfy the linear operator constraints.
Recent years have witnessed the rapid development of block coordinate update (BCU) methods, which are particularly suitable for problems involving large-sized data and/or variables. In optimization, BCU first appears as the coordinate descent method that works well for smooth problems or those with separable nonsmooth …
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. LCW reduces activation shift in neural networks, improving training efficiency and generalization.
problem Activation shift in neural networks leading to non-zero mean preactivation values.
method Linearly constrained weights (LCW) to reduce activation shift in fully connected and convolutional layers.
result LCW resolves the vanishing gradient problem and improves generalization of neural networks.
We study the estimation of the latent variable Gaussian graphical model (LVGGM), where the precision matrix is the superposition of a sparse matrix and a low-rank matrix. In order to speed up the estimation of the sparse plus low-rank components, we propose a sparsity constrained maximum likelihood estimator based on m…
Paper analyzes LPSA algorithm for constrained optimization, revealing phase transitions and bias-variance trade-offs.
problem Optimization problems with linear constraints.
method Loopless projection stochastic approximation (LPSA) with jump diffusion approximation.
result LPSA trajectories converge to SDEs, revealing asymptotic behaviors and phase transitions.
Unified approach adjusts classifiers to meet system-level constraints.
problem Multi-class classification under system-level constraints.
method Post-processing approach using linearly constrained stochastic program and entropic regularization.
result Finite-sample guarantees for risk and constraint satisfaction.
A new method solves large-scale sparse group square-root Lasso problems efficiently.
problem Large-scale linearly constrained sparse group square-root Lasso problems.
method Dual semismooth Newton based augmented Lagrangian method (ALM).
result The proposed method efficiently solves the problem with numerical experiments demonstrating its effectiveness.
New method tackles bilevel optimization with polyhedral constraints.
problem Challenges in bilevel optimization with active-set changes and expensive Hessian inversions.
method Logarithmic barrier smoothing and proxy-gradient algorithm for differentiable approximation.
result Stationarity rates of O(K−2/3) in deterministic setting and O(K−2/5) under stochastic noise. We consider a modification of the covariance function in Gaussian processes to correctly account for known linear constraints. By modelling the target function as a transformation of an underlying function, the constraints are explicitly incorporated in the model such that they are guaranteed to be fulfilled by any sam…
In this work we establish the first linear convergence result for the stochastic heavy ball method. The method performs SGD steps with a fixed stepsize, amended by a heavy ball momentum term. In the analysis, we focus on minimizing the expected loss and not on finite-sum minimization, which is typically a much harder p…
We algorithmically construct multi-output Gaussian process priors which satisfy linear differential equations. Our approach attempts to parametrize all solutions of the equations using Gröbner bases. If successful, a push forward Gaussian process along the paramerization is the desired prior. We consider several exampl…
Distribution grids are currently challenged by frequent voltage excursions induced by intermittent solar generation. Smart inverters have been advocated as a fast-responding means to regulate voltage and minimize ohmic losses. Since optimal inverter coordination may be computationally challenging and preset local contr…
The study quantifies how many objects can be linearly classified under all views.
problem Understanding the expressivity of group-equivariant representations.
method Generalization of Cover's Function Counting Theorem to quantify separable dichotomies.
result The fraction of separable dichotomies is determined by the fixed space dimension of the group action.
Block Coordinate Update (BCU) methods enjoy low per-update computational complexity because every time only one or a few block variables would need to be updated among possibly a large number of blocks. They are also easily parallelized and thus have been particularly popular for solving problems involving large-scale …
In this paper, we study the stochastic gradient descent (SGD) method for the nonconvex nonsmooth optimization, and propose an accelerated SGD method by combining the variance reduction technique with Nesterov's extrapolation technique. Moreover, based on the local error bound condition, we establish the linear converge…
We develop an encompassing framework for matching, covariate balancing, and doubly-robust methods for causal inference from observational data called generalized optimal matching (GOM). The framework is given by generalizing a new functional-analytical formulation of optimal matching, giving rise to the class of GOM me…
New methods reduce computational cost for Gaussian Markov Random Fields with sparse constraints.
problem Inference and simulation of GMRFs are computationally prohibitive with many constraints.
method Proposes a basis transformation into blocks of constrained and non-constrained subspaces.
result Significantly outperforms existing alternatives in computational cost.
We introduce SCAL, an algorithm designed to perform efficient exploration-exploitation in any unknown weakly-communicating Markov decision process (MDP) for which an upper bound c on the span of the optimal bias function is known. For an MDP with S states, A actions and Γ≤S possible next states, we prove a …
Optimal Transport (OT) problems arise in a wide range of applications, from physics to economics. Getting numerical approximate solution of these problems is a challenging issue of practical importance. In this work, we investigate the relaxation of the OT problem when the marginal constraints are replaced by some mome…
We propose a unified framework to address a family of classical mixed-integer optimization problems with logically constrained decision variables, including network design, facility location, unit commitment, sparse portfolio selection, binary quadratic optimization, sparse principal analysis and sparse learning proble…
Extends GENO framework for GPU optimization of constrained ML problems.
problem Constrained optimization in classical machine learning.
method Extends GENO framework to GPU optimization, specifying problems in a modeling language.
result Solvers on GPU outperform state-of-the-art approaches by several orders of magnitude.
Enhances SSL with mixup and Lipschitz regularization.
problem Improving SSL performance with limited labeled data.
method Adopts mixup for smoothness, adds adversarial Lipschitz regularization.
result Combined regularization improves SSL performance and robustness.
In modern portfolio theory, the balancing of expected returns on investments against uncertainties in those returns is aided by the use of utility functions. The Kelly criterion offers another approach, rooted in information theory, that always implies logarithmic utility. The two approaches seem incompatible, too loos…
A cardinality-constrained portfolio caps the number of stocks to be traded across and within groups or sectors. These limitations arise from real-world scenarios faced by fund managers, who are constrained by transaction costs and client preferences as they seek to maximize return and limit risk. We develop a new appro…
A new method for optimizing non-decomposable metrics with constraints.
problem Optimizing complex machine learning objectives with thresholded constraints.
method Formulate rate-constrained optimization using the Implicit Function theorem and solve with gradient-based methods.
result Demonstrated effectiveness over existing methods on benchmark datasets.
Study how neural networks optimize to stable linearly connected regions.
problem Understanding how neural networks converge to stable solutions under different training conditions.
method Investigate the stability of neural networks to SGD noise and apply it to iterative magnitude pruning.
result Subnetworks that reach full accuracy must be stable to SGD noise, either at initialization or early in training.
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.
We solve hard Gaussian integrals efficiently using geometry and sampling.
problem Hard computation of integrals over linearly constrained Gaussian densities.
method Combines Holmes-Diaconis-Ross method with elliptical slice sampling adapted to linear settings.
result Direct computation of extremely small probability masses.