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.
Region-specific linear models are widely used in practical applications because of their non-linear but highly interpretable model representations. One of the key challenges in their use is non-convexity in simultaneous optimization of regions and region-specific models. This paper proposes novel convex region-specific…
The study examines the properties of linear regions in DNNs and how optimization techniques affect them.
problem Understanding the expressivity of deep neural networks through their linear regions.
method Empirical analysis of local properties of linear regions, including inspheres, hyperplane directions, decision boundaries, and surrounding regions.
result Different optimization techniques lead to distinct linear regions, even with similar classification accuracy.
Proposes a Quasi-Newton trust region method for policy optimization in reinforcement learning.
problem Lack of stepsize selection criterion and slow convergence in gradient descent for policy optimization.
method Uses a trust region method with Quasi-Newton approximation for the Hessian.
result Demonstrates improved performance and efficiency in continuous control tasks.
The paper develops optimal confidence regions for categorical data.
problem Constructing tight confidence regions for categorical data.
method Develops new theory for minimum average volume confidence regions.
result Shows optimality of the regions for categorical data and its implications for machine learning.
Two multifidelity trust-region methods use low-fidelity models for efficient optimization.
problem Efficiently solving complex optimization problems with limited data.
method Sketched Trust-Region (STR) and SVD Trust-Region (SVDTR) methods using low-fidelity models.
result Potential gain in efficiency demonstrated through numerical examples.
We prove that the optimal way to enclose and separate four planar regions with equal area using the less possible perimeter requires all regions to be connected. Moreover, the topology of such optimal clusters is uniquely determined.
Novel BSG method for efficient stochastic optimization.
problem Efficient optimization of non-convex surfaces in stochastic settings.
method Binary search combined with first order gradient optimization.
result BSG produces more promising results and better generalization than other methods.
AdaScale-TuRBO improves high-dimensional Bayesian optimization by dynamically scaling the GP lengthscale.
problem Inappropriate lengthscale design in TuRBO's local GP model causes suboptimal performance in high dimensions.
method Proposes AdaScale-TuRBO, which scales the GP lengthscale with both problem dimension and trust region size.
result AdaScale-TuRBO robustly outperforms standard TuRBO and other methods on synthetic and real-world tasks.
TREGO improves EGO for global optimization of high-dimensional problems.
problem Efficient Global Optimization struggles with high dimensions and lacks theoretical guarantees.
method TREGO alternates between EGO steps and local steps within a trust region.
result TREGO outperforms EGO and other methods in black-box optimization problems.
TRSVR combines SVRG with trust-region for faster optimization.
problem Unconstrained nonconvex optimization problems.
method Adaptive stochastic trust-region method with variance reduction.
result Converges to first-order stationary points with SVRG.
Bayesian optimization algorithm reduces regret with efficient region pruning.
problem Sequential optimization of unknown functions in high-dimensional spaces.
method Gaussian process-based, domain shrinking through tree-based region pruning.
result Order-optimal regret performance with reduced computational complexity.
Proposes CPO framework for robust decision-making with explainable uncertainty regions.
problem Overly conservative uncertainty regions in data-driven optimization lead to suboptimal decisions.
method Conformal-Predict-Then-Optimize (CPO) framework using conditional generative models and visual summaries.
result Demonstrates improved robustness and explainability in decision-making.
Proposes a new algorithm for solving optimization problems with stochastic objectives and equality constraints.
problem Optimization problems with stochastic objectives and deterministic equality constraints.
method Trust-region stochastic sequential quadratic programming (TR-StoSQP) with adaptive relaxation techniques.
result Established a global almost sure convergence guarantee for TR-StoSQP.
This paper analyzes optimal stopping regions for American options with Poisson exercise opportunities.
problem Analyzing the optimal stopping regions for American options with Poisson exercise opportunities.
method Computing identities related to the first Poisson arrival time to an interval and applying them to the computation of the optimal strategies.
result Explicit expressions of the stopping and continuation regions and the value function are obtained.
Novel method for high-dimensional BO using CMA to define local regions.
problem Challenges in applying BO to high-dimensional optimization problems.
method CMA strategy to learn search distribution and define local regions.
result Our method outperforms existing techniques on various benchmarks.
Optimizes ellipsoids for uncertainty regions in parameter estimation.
problem Learning minimal volume uncertainty ellipsoids for parameter estimation.
method Differentiable optimization approach using neural networks to approximate optimal ellipsoids.
result Approximately computed ellipsoids are smaller and more accurate than existing methods.
DO-IQS recovers optimal stopping region from expert trajectories, addressing specific challenges.
problem Recovering optimal stopping region from expert trajectories with unknown gain functions.
method Dynamics-Aware Offline Inverse Q-Learning incorporating temporal information and confidence-based oversampling.
result Demonstrated performance on real and artificial data, including optimal intervention for critical events.
BALLET filters a high-confidence region of interest for Bayesian optimization.
problem High-dimensional and non-stationary Bayesian optimization challenges.
method Adaptive level-set estimation using two probabilistic models.
result Ballets can efficiently shrink the search space and exhibit tighter regret bounds.
Investigates consumption and investment strategies with preference for liquid assets.
problem Infinite horizon consumption-portfolio problem with liquid and illiquid risky assets.
method Analyzes properties of value function, categorizes solvency regions, and characterizes optimal policy.
result Liquidity preference leads to higher liquid wealth and lower consumption, potentially negative allocation to illiquid asset.
Proposes a novel approach for cluster-aware matching using Laplacian Optimal Transport.
problem Matching point clouds with intrinsic cluster structure requires robust region-to-region alignment over precise point-to-point correspondence.
method Laplacian Optimal Transport (LapOT) with regularization for cluster-aware matching and Refined Simultaneous Clustering (RSC) for consistent partitions.
result Laplacian Optimal Transport produces more consistent and meaningful alignments between point clouds.
Combines global and local search for efficient global optimization with Gaussian processes.
problem Difficulties in building accurate GP models and getting stuck in suboptimal regions.
method Adopting AGLGP model combining global and local GP models, dividing space into regions, and switching between global and local searches.
result Efficiently locates the global optimum with benefits of both global and local search.
Develops ODRPO to improve RL algorithms with better performance and stability.
problem RL algorithms converge to sub-optimal solutions due to limited policy representation.
method Integrates DRO approach to solve trust region constrained optimization problem without parameterizing policies.
result Achieves globally optimal policy update and higher sample efficiency.
PARADE generates provably robust adversarial examples for deep networks.
problem Creating robust adversarial examples for deep neural networks.
method Iterative refinement of adversarial regions using optimization to ensure robustness under various perturbations.
result PARADE finds large, provably robust adversarial regions with high volume under various perturbations.
The paper analyzes and improves a deep learning optimization technique using matrix gradient orthogonality.
problem Improving deep learning training through more effective optimization methods.
method Develops a stochastic non-Euclidean trust-region gradient method for deep learning optimization.
result Proves state-of-the-art convergence results for the proposed algorithm in various scenarios.
RYU framework constructs safe regions for optimization problems.
problem Optimization problems with specific component functions.
method RYU framework for constructing safe regions.
result RYU framework improves upon state-of-the-art methods.
Recently dictionary screening has been proposed as an effective way to improve the computational efficiency of solving the lasso problem, which is one of the most commonly used method for learning sparse representations. To address today's ever increasing large dataset, effective screening relies on a tight region boun…
Inter-subject registration of cortical areas is necessary in functional imaging (fMRI) studies for making inferences about equivalent brain function across a population. However, many high-level visual brain areas are defined as peaks of functional contrasts whose cortical position is highly variable. As such, most ali…
Study on optimal portfolio selection with varying borrowing and saving rates in continuous-time markets.
problem Optimal portfolio selection in markets with different borrowing and saving rates.
method Hamilton-Jacobi-Bellman equation, partial differential equation, verification argument.
result Existence and smoothness of the value function, identification of trading regions and strategies.
A leveraged exchange traded fund (LETF) is an exchange traded fund that uses financial derivatives to amplify the price changes of a basket of goods. In this paper, we consider the robust hedging of European options on a LETF, finding model-free bounds on the price of these options. To obtain an upper bound, we establi…
New sampling strategy improves TR algorithms for stochastic optimization.
problem Derivative-free stochastic optimization with Monte Carlo estimates.
method Stratified adaptive sampling to optimize MC sample size.
result Reduced sample complexity and superior efficiency confirmed.
End-to-end pipeline for data-driven decision making in mixed-integer optimization.
problem Data-driven decision making in mixed-integer optimization with uncertainty.
method Exploiting mixed-integer optimization-representability of machine learning methods, characterizing decision trust regions, and ensembling multiple models.
result Framework generates high-quality prescriptions and controls model robustness.
The SPS method constructs confidence regions for true parameters with optimal sample complexity.
problem Constructing exact, non-asymptotic confidence regions for true system parameters.
method Sign-Perturbed Sums (SPS) method, generalized to various types of problems.
result High probability upper bounds for SPS confidence regions show optimal shrinkage rate.
Proximal policy optimization (PPO) is one of the most popular deep reinforcement learning (RL) methods, achieving state-of-the-art performance across a wide range of challenging tasks. However, as a model-free RL method, the success of PPO relies heavily on the effectiveness of its exploratory policy search. In this pa…
MF-TRPO optimizes MFGs with finite sample guarantees.
problem Computing approximate Nash equilibria in MFGs.
method Extends TRPO to MFGs, providing convergence guarantees.
result Theoretical guarantees on MF-TRPO's convergence.
TROLL improves RL for LLMs by replacing clipping with a trust region projection.
problem Clipping in RL for LLMs causes instability and suboptimal performance.
method TROLL uses a discrete differentiable trust region projection to replace clipping, balancing computational cost and effectiveness.
result TROLL consistently outperforms PPO-like clipping in training speed, stability, and final success rates.
Adaptive replication improves stochastic function optimization.
problem Challenges in accurately estimating functions with high variance.
method Trust-region-based Bayesian optimization with adaptive replication.
result Adaptive replication substantially improves solution accuracy and efficiency.
BO limits search to lower dimensions with LGPR, improving efficiency and accuracy.
problem High computational costs in BO for high-dimensional optimization.
method Limits search region to lower dimensions and uses LGPR for local Gaussian process regression.
result Search efficiencies improved by about 69% and 40% for Ackley and Rosenbrock functions.
New algorithm improves deep learning stability with limited data.
problem Stability and robustness in reinforcement learning with scarce data.
method Uncertainty-aware trust region approach to policy optimization.
result Stable policy updates adapt to uncertainty levels during learning.
Method constructs confidence regions for linear models with arbitrary predictors.
problem Constructing confidence regions for linear models with non-linear predictors.
method Mixed Integer Linear Programming for constraints.
result Empty confidence regions for hypothesis testing.
SLS optimizes minimum-volume regions for conditional quantiles, bypassing density estimation.
problem Constructing minimum-volume prediction regions that satisfy conditional coverage.
method Super-level-set regression (SLS) directly optimizes geometric boundaries of conditional level sets.
result SLS optimizes regions directly, capturing complex conditional structures end-to-end.
AntBO optimizes antibody design using Bayesian optimization for efficient and effective CDRH3 sequence generation.
problem Designing optimal antigen-specific CDRH3 regions in antibody design due to combinatorial sequence space.
method Combinatorial Bayesian optimization framework with trust region for developability.
result AntBO designs CDRH3 regions with diverse biophysical properties and outperforms existing methods.
We propose to improve trust region policy search with normalizing flows policy. We illustrate that when the trust region is constructed by KL divergence constraints, normalizing flows policy generates samples far from the 'center' of the previous policy iterate, which potentially enables better exploration and helps av…
SDG uses optimal control to improve classifier guidance in low-density regions.
problem Inefficient guidance in low-density regions of posterior distributions.
method Integrates stochastic optimal control with Stein variational inference to compute the steepest descent direction.
result SDG improves guidance in low-density regions, outperforming standard methods.
The paper develops methods for constructing confidence regions for regression functions in binary classification.
problem Building distribution-free confidence regions for regression functions in binary classification.
method Resampling test and empirical risk minimization approach for model classes with finite pseudo-dimensions and inverse Lipschitz parameterizations.
result Strong uniform consistency and exponential probably approximately correct bounds on the L2 sizes of the regions. Paper develops SKPD framework for signal region detection in image regression.
problem Limited research on image region detection in high-resolution image regression.
method Sparse Kronecker Product Decomposition (SKPD) framework for matrices and tensors.
result Computed solutions converge to truth with guaranteed consistency.
The study estimates the expressiveness of GCNs with bounds on the number of linear regions.
problem Characterizing the expressiveness of graph convolutional networks (GCNs).
method Estimates the number of linear regions for one-layer and multi-layer GCNs.
result GCNs with multiple layers have exponentially more expressivity per parameter than one-layer GCNs.
The adaptive optimizer for training neural networks has continually evolved to overcome the limitations of the previously proposed adaptive methods. Recent studies have found the rare counterexamples that Adam cannot converge to the optimal point. Those counterexamples reveal the distortion of Adam due to a small secon…