Bayesian optimization outperformed random search in machine learning hyperparameter tuning challenge.
problem Optimizing hyperparameters of machine learning models using derivative-free methods.
method Bayesian optimization vs. random search on real datasets.
result Bayesian optimization significantly outperformed random search in held-out objective functions.
Current state-of-the-art discrete optimization methods struggle behind when it comes to challenging contrast-enhancing discrete energies (i.e., favoring different labels for neighboring variables). This work suggests a multiscale approach for these challenging problems. Deriving an algebraic representation allows us to…
Bayesian design improves experimental optimization.
problem Computational challenges limit BED practical use.
method Recent advances in BED have reduced computational burdens.
result Effective BED design is now feasible.
In this thesis I explore challenging discrete energy minimization problems that arise mainly in the context of computer vision tasks. This work motivates the use of such "hard-to-optimize" non-submodular functionals, and proposes methods and algorithms to cope with the NP-hardness of their optimization. Consequently, t…
This thesis tackles Gaussian Process challenges in low dimensions.
problem Constructing models for large datasets and selecting optimal models.
method Samplet-based approach to efficiently construct and train Gaussian Processes.
result Reduces cubic computational complexity to log-linear scale.
Deep learning models are growing, posing new mathematical challenges.
problem Mathematical challenges in training, inference, generalization, and optimization of deep models.
method Formal mathematical analysis and communication with mathematicians, statisticians, and computer scientists.
result A set of new mathematical challenges in deep learning.
Squirrel switches between optimizers for better performance.
problem Finding the best optimizer for a given problem.
method Switches between different optimizers based on performance.
result Improves performance on various problems.
Survey of GANs challenges and solutions for better model design and optimization.
problem Challenges in training GANs, including mode collapse, non-convergence, and instability.
method Comprehensive survey of GANs design and optimization solutions, proposing a new taxonomy.
result Presentation of promising research directions in GANs.
A new method uses heat diffusion to efficiently solve combinatorial optimization problems.
problem Challenges in combinatorial optimization due to discrete nature and limited search scope.
method Transforming the target function through heat diffusion to enable information flow and more efficient navigation.
result Superior performance across various combinatorial optimization problems.
Survey of AI in finance covering models, strategies, and knowledge systems.
problem Challenges in applying AI to financial markets, especially in high-frequency trading.
method Systematic analysis of financial AI across predictive models, decision frameworks, and knowledge augmentation systems.
result Critical trade-offs and gaps between theoretical advances and practical implementation in financial AI.
A method for high-dimensional Bayesian optimization reduces dimensionality using EDR and Gaussian process.
problem Extending Bayesian optimization to high-dimensional settings.
method Two-step framework: EDR subspace identification followed by Gaussian process optimization.
result Algorithm converges in high-dimensional contexts, validated by numerical experiments.
Optimization of high-dimensional black-box functions is an extremely challenging problem. While Bayesian optimization has emerged as a popular approach for optimizing black-box functions, its applicability has been limited to low-dimensional problems due to its computational and statistical challenges arising from high…
Examines challenges and proposes new approaches in machine learning theory.
problem Challenges in machine learning as a function approximation and optimization.
method Mathematical analysis of gradient descent, fixed network limitations, and RNNs.
result New insights and mathematical approaches to improve machine learning.
Machine Learning models incorporating multiple layered learning networks have been seen to provide effective models for various classification problems. The resulting optimization problem to solve for the optimal vector minimizing the empirical risk is, however, highly nonlinear. This presents a challenge to applicatio…
Paper explores challenges in training PINNs and loss landscape effects.
problem Challenges in training Physics-Informed Neural Networks (PINNs) due to loss landscape issues.
method Examined gradient-based optimizers Adam, L-BFGS, and their combination Adam+L-BFGS, and introduced NysNewton-CG (NNCG).
result Adam+L-BFGS outperforms other optimizers, and NysNewton-CG significantly improves PINN performance.
New policy combines Thompson sampling with best challenger rule for best arm identification.
problem Best arm identification in bandit framework with fixed confidence.
method Combines Thompson sampling with best challenger rule.
result Asymptotically optimal for any two-armed bandit problems, near optimal for general K-armed bandit problems.
S2M optimizes mining for diverse data subpopulations.
problem Scalability and uniformity in training sets with many labels and diverse data.
method Doubly-stochastic mining (S2M) computes per-example and minibatch losses on hardest labels/examples.
result S2M ensures good performance across all data subpopulations.
We outline a new approach for solving optimization problems which enforce triangle inequalities on output variables. We refer to this as metric-constrained optimization, and give several examples where problems of this form arise in machine learning applications and theoretical approximation algorithms for graph cluste…
Bayesian Optimization tackles hidden constraints in architecture optimization.
problem Optimizing system architectures with hidden constraints using expensive physics-based simulations.
method Surrogate-based optimization with Gaussian Process models, including strategies for handling failed evaluations.
result Best performance achieved with a mixed-discrete GP predicting Probability of Viability (PoV) and minimum PoV threshold selection.
Machine Learning models incorporating multiple layered learning networks have been seen to provide effective models for various classification problems. The resulting optimization problem to solve for the optimal vector minimizing the empirical risk is, however, highly nonconvex. This alone presents a challenge to appl…
The optimization of expensive-to-evaluate black-box functions over combinatorial structures is an ubiquitous task in machine learning, engineering and the natural sciences. The combinatorial explosion of the search space and costly evaluations pose challenges for current techniques in discrete optimization and machine …
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.
Meta-BO method clusters and learns from prior tasks to optimize heterogeneous functions.
problem Optimizing multiple functions with historical data and scalability issues.
method Clustering-based meta-learning, surrogate prototypes, adaptive weighting policies.
result Scalable and robust meta-BO method improves convergence to global optimum.
Machine learning develops rapidly, which has made many theoretical breakthroughs and is widely applied in various fields. Optimization, as an important part of machine learning, has attracted much attention of researchers. With the exponential growth of data amount and the increase of model complexity, optimization met…
This paper analyzes challenges and solutions in deep learning optimization.
problem Gradient vanishing and exploding issues in deep learning.
method Improvement of gradient flow and constraints on Lipschitz constant.
result Enhanced understanding of Jacobian matrices and Lipschitz constants in deep learning modules.
Gradient-based framework for optimizing text prompts in diffusion models.
problem Efficiently optimizing prompts in text-to-image diffusion models with large domain space and non-differentiable embeddings.
method Formulated as discrete optimization over language space, designed compact subspaces, and introduced shortcut text gradient.
result Empirically discovered prompts that enhance or destroy image faithfulness.
Many real-world analytics problems involve two significant challenges: prediction and optimization. Due to the typically complex nature of each challenge, the standard paradigm is predict-then-optimize. By and large, machine learning tools are intended to minimize prediction error and do not account for how the predict…
This paper surveys gradient-based multi-objective deep learning methods.
problem Balancing multiple conflicting objectives in deep learning models.
method Gradient-based techniques adapted from Multi-Objective Optimization.
result Comprehensive survey of gradient-based multi-objective deep learning algorithms.
A new kernel for ranked data tackles computational challenges.
problem Complex geometric structure and partial rankings make existing algorithms infeasible for real-world applications.
method Derives a graph cut kernel that combines submodular optimization and kernel-based methods.
result The graph cut kernel efficiently handles large-scale ranked data.
Proposes CoPO, a new policy optimization method for competitive games.
problem Designing efficient optimization methods for competitive Markov decision processes.
method Competitive policy optimization (CoPO) approach that exploits game-theoretic nature of competitive games.
result Stable optimization, convergence to sophisticated strategies, and higher scores compared to baseline methods.
We introduce a minorization-maximization approach to optimizing common measures of discovery significance in high energy physics. The approach alternates between solving a weighted binary classification problem and updating class weights in a simple, closed-form manner. Moreover, an argument based on convex duality sho…
Paper extends knowledge gradient for preferential BO, overcoming computational challenges.
problem Extending knowledge gradient to preferential BO with pairwise comparisons.
method Derive exact and analytical knowledge gradient for preferential BO.
result Exact knowledge gradient outperforms existing acquisition functions on benchmark problems.
SCBO tackles constrained optimization in high dimensions.
problem Optimizing complex, high-dimensional functions with constraints.
method Proposes scalable constrained Bayesian optimization algorithm.
result Demonstrates excellent performance on various benchmarks.
Optimal prototypes found for challenging pathological geometries.
problem Finding optimal prototypes for pathological geometries is challenging.
method Analytical and heuristic algorithms for finding nearly-optimal prototypes.
result Optimal prototypes can be found analytically for challenging geometries.
New findings show optimization is crucial for OPL in large action spaces.
problem Challenges in optimizing policies for large action spaces in offline contextual bandits.
method Weighed log-likelihood objectives and estimator-aware policy parametrization.
result Simple weighted log-likelihood objectives enjoy better optimization properties and recover competitive policies.
We address challenges in collaborative black-box optimization through three frameworks.
problem Challenges in distributed experimentation, heterogeneity, and privacy in black-box optimization.
method Three unifying frameworks: global, local, and predictive.
result Shift from descriptive/predictive to prescriptive federated learning in black-box optimization.
Framework learns linear programs from optimal decisions.
problem Learning linear programs from optimal decisions is challenging.
method Gradient-based framework for learning linear programs from optimal decisions.
result Successfully learns linear programs and multi-commodity flow instances.
PDNS tackles multimodal sampling challenges using proximal point method.
problem Multimodal distributions with significant barriers between modes.
method Proximal point method on path measures, decomposing into simpler subproblems.
result PDNS effectively promotes thorough exploration across modes.
MUMBO optimizes multiple tasks efficiently, even with low-cost related functions.
problem Efficiently optimizing multiple related functions with low-cost evaluations.
method Derives a novel multi-task version of entropy search.
result Robust performance with low computational overhead across various optimization challenges.
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. Reinforcement Learning improves insulin bolus decisions for type-I diabetes patients.
problem Optimal insulin bolus decisions for type-I diabetes patients are not well-established.
method Applied Reinforcement Learning to simulated T1DM data.
result Optimal bolus rule differs from standard advisors and can prevent hypoglycemia.
BOAT optimizes multiple antibody properties efficiently.
problem Balancing multiple drug-like properties in antibody design.
method Bayesian optimization framework coupling surrogate modeling and genetic algorithm.
result Competitive performance with state-of-the-art multi-objective protein optimization methods.
Investment challenge study finds luck and strategy equally important.
problem The role of luck and strategic considerations in M6 investment challenge performance.
method Introduced a stylized model to derive and analyze a portfolio strategy.
result Improving chances of winning without attaining abnormal returns possible.
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.
Efficiently solves large-scale robust portfolio optimization problems.
problem High computational demands in large-scale robust portfolio optimization.
method Extended supporting hyperplane approximation for distributionally robust portfolio problems.
result Significantly reduces computational time from several thousand seconds to just a few.
VQAs use classical optimization to train quantum circuits, promising quantum advantage.
problem High computational cost of quantum simulations and solving large-scale problems.
method Variational Quantum Algorithms (VQAs) use classical optimizers to train parametrized quantum circuits.
result VQAs are a promising strategy for obtaining quantum advantage.
New algorithm tackles nonstationary linear bandits with latent dynamics.
problem Nonstationary bandit problem with latent states and unknown dynamics.
method Explore-then-commit algorithm with exploration and commitment phases.
result Achieves ildeO(T2/3) regret. Paper tackles reinforcement learning generalization through invariant policy optimization.
problem Learning policies that generalize beyond training domains.
method Invariant policy optimization principle and novel learning algorithm IPO.
result Significant improvements in generalization performance on unseen domains.