Automates optimizer design for diverse tasks efficiently.
problem Scalability, generability, and sample efficiency in optimizer search.
method Re-arranged optimizer space into a super-tree, applying tree traversal methods.
result Discover optimizers with only 128 evaluations, surpassing human-designed and prior methods.
LA-MCTS learns search space partition for black-box optimization using Monte Carlo Tree Search.
problem High-dimensional black-box optimization challenges.
method LA-MCTS recursively splits search space into regions with high/low function values, learns nonlinear partition and local models online.
result LA-MCTS achieves strong performance in black-box optimization and reinforcement learning benchmarks, especially for high-dimensional problems.
A game theory study on optimal hiding and searching strategies in discrete locations.
problem Optimal hiding and searching strategies in a two-person zero-sum game between a hider and a searcher.
method Proved the existence of optimal strategies, developed an algorithm to compute them, and compared with a simple strategy.
result Optimal hiding strategy involves hiding in each location with nonzero probability, and optimal searching strategy can be constructed with up to n simple sequences.
NAS helps find best neural network designs.
problem Designing optimal neural network architectures.
method Optimization algorithms and search spaces.
result Introduction to major advances in NAS for CNNs.
A new Randomized-Hyperopt method improves XGBoost hyperparameter tuning.
problem Improving the performance of XGBoost through hyperparameter optimization.
method Proposes Randomized-Hyperopt for XGBoost hyperparameter tuning.
result Randomized-Hyperopt outperforms other methods in terms of accuracy and execution time.
A new algorithm, Regular Tree Search, tackles non-convex simulation optimization problems.
problem Non-convex objective functions in simulation optimization.
method Integrates adaptive sampling with recursive partitioning of the search space.
result Proves global convergence and reliably identifies the global optimum.
Paper tackles NAS problem by modeling it as a sparse supernet.
problem Neural Architecture Search (NAS) problem, particularly Mixed-Path Search.
method Model NAS as a sparse supernet with sparsity constraints. Use hierarchical accelerated proximal gradient algorithm for optimization.
result Proposed method finds compact, general, and powerful neural architectures.
Optimizes search times by resetting agents when a threshold is reached.
problem Improving search efficiency in systems with thresholds.
method Develops a framework for correlated stochastic processes with threshold resetting.
result Optimal resetting can prevent larger losses and is applicable to various stochastic systems.
VES-Gamma adapts EI using information-theoretic principles.
problem Optimizing black-box functions using Bayesian optimization.
method Variational Entropy Search (VES) and VES-Gamma algorithm.
result VES-Gamma improves EI by incorporating information-theoretic concepts.
MiLeNAS improves neural architecture search by reducing approximation errors and achieving better accuracy.
problem Improving efficiency and accuracy in neural architecture search (NAS).
method Mixed-level reformulation (MiLeNAS) to optimize efficiently and reliably.
result MiLeNAS achieves lower validation error and higher accuracy than bilevel optimization methods.
NOVAS uses adaptive stochastic search for non-convex optimization in deep networks.
problem Non-convex optimization challenges in deep neural networks.
method Adaptive stochastic search for non-convex optimization.
result NOVAS outperforms existing alternatives in a structured prediction task.
NeuralArTS categorizes neural ops in a type system for NAS.
problem Manual optimization of search spaces for NAS is inefficient.
method Developed NeuralArTS, a type system for categorizing network ops.
result NeuralArTS can be applied to convolutional layers.
Quality-Diversity algorithms explore multiple high-performing solutions in a search space.
problem Finding multiple high-performing solutions in complex optimization problems.
method Evolutionary computation approach focusing on behavioral space and holistic solution distribution.
result Quality-Diversity algorithms provide a comprehensive view of high-performing solutions in a search space.
A new framework generates large hierarchical search spaces for neural architectures.
problem Discovering neural architectures from simple blocks is hard.
method Context-free grammars for a unified, scalable search space.
result Efficiently searches over complete architectures, outperforming existing methods.
New method improves neural architecture search by optimizing for both performance and diversity.
problem Traditional multi-objective NAS fails to address practical constraints and niches.
method Formulated as quality diversity optimization, introduces multifidelity optimizers.
result Quality diversity NAS outperforms multi-objective NAS in quality and efficiency.
Optimizes neural architecture search to generate novel lightweight models.
problem Over-reliance on expert knowledge limits NAS to local optima, preventing architectural breakthroughs.
method Casts NAS as an optimization problem, introduces a hierarchical graph-based search space, and uses Bayesian optimization.
result Generates extremely lightweight yet competitive models on six benchmark datasets.
Empirical comparison of 18 hyperparameter tuning algorithms for SVM.
problem Tuning hyperparameters C and γ for SVM with RBF kernel. method Compared 18 search algorithms on 115 real-life data sets.
result Trees of Parzen estimators and particle swarm optimization perform similarly to grid search.
Optimizes tree models for better beam search performance.
problem Beam search causes retrieval performance deterioration in tree models.
method Develops Bayes optimality and calibration under beam search, proposes a novel algorithm for optimal tree model learning.
result Eliminates the training-testing discrepancy in tree models.
Efficiently searches through Gaussian process kernels using symbolic representation and Bayesian optimization.
problem Manual selection of kernels in Gaussian processes is complex and computationally expensive.
method Proposes a novel method using symbolic representation and Bayesian optimization to search through a structured kernel space.
result Empirically shows a computationally more efficient way of searching through a discrete kernel space.
Bayesian optimization (BO) is a successful methodology to optimize black-box functions that are expensive to evaluate. While traditional methods optimize each black-box function in isolation, there has been recent interest in speeding up BO by transferring knowledge across multiple related black-box functions. In this …
Global optimization finds applications in a wide range of real world problems. The multi-start methods are a popular class of global optimization techniques, which are based on the ideas of conducting local searches at multiple starting points. In this work we propose a new multi-start algorithm where the starting poin…
Bayesian optimization is an effective method to efficiently optimize unknown objective functions with high evaluation costs. Traditional Bayesian optimization algorithms select one point per iteration for single objective function, whereas in recent years, Bayesian optimization for multi-objective optimization or multi…
Survey of techniques for automating hyperparameter optimization in machine learning.
problem Finding optimal hyperparameters for machine learning algorithms.
method Review of various hyperparameter optimization techniques.
result Unified treatment of hyperparameter optimization techniques.
A hybrid model for Bayesian optimization handles mixed variables using MCTS for categorical and GP for continuous.
problem Optimizing functions with mixed variable types (continuous, integer, categorical).
method Merges MCTS for categorical and GP for continuous variables, integrates UCTS search strategy, and dynamically selects kernels.
result Hybrid models outperform traditional methods in Bayesian optimization.
Bayesian optimization offers a flexible framework to optimize an objective function that is expensive to be evaluated. A Bayesian optimizer iteratively queries the function values on its carefully selected points. Subsequently, it makes a sensible recommendation about where the optimum locates based on its accumulated …
TGLS generates text by optimizing search results and learning from them.
problem Unsupervised text generation without explicit training data.
method TGLS uses simulated annealing to estimate sentence quality, then a conditional generative model learns from search results.
result TGLS outperforms unsupervised baselines and matches state-of-the-art supervised methods in paraphrase generation.
DONNA rapidly finds optimal neural networks across diverse spaces.
problem Efficient scaling and handling of diverse architectural search-spaces in NAS.
method Three-phase pipeline: accuracy predictor, rapid evolutionary search, and optimal model finetuning.
result 100x faster than MNasNet in finding state-of-the-art architectures on-device.
Local PBO methods improve preferential BO in high-dimensional problems.
problem Efficiently optimizing preferential BO in high-dimensional settings.
method Adapting high-dimensional BO techniques to preferential feedback.
result Local PBO methods reduce cumulative regret compared to global baselines.
New algorithms improve neural architecture search with faster convergence.
problem Improving efficiency and accuracy of neural architecture search.
method Geometry-aware gradient algorithms to optimize continuous relaxation of discrete search spaces.
result Exceeds state-of-the-art results on CIFAR and ImageNet benchmarks.
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.
Optimizes sampling in continuous domains by adjusting search distribution.
problem Improving sampling efficiency in continuous domains.
method Analyzes and refines the search distribution based on population size and dimension.
result Explicit values for reshaping the search distribution are provided.
The aim of black-box optimization is to optimize an objective function within the constraints of a given evaluation budget. In this problem, it is generally assumed that the computational cost for evaluating a point is large; thus, it is important to search efficiently with as low budget as possible. Bayesian optimizat…
Automatic methods for Neural Architecture Search (NAS) have been shown to produce state-of-the-art network models. Yet, their main drawback is the computational complexity of the search process. As some primal methods optimized over a discrete search space, thousands of days of GPU were required for convergence. A rece…
Bayesian optimization with Gaussian processes speeds up searches for stationary points.
problem Accelerating searches for stationary points on potential energy surfaces.
method Unified Bayesian optimization view using Gaussian process regression with derivative observations, inverse-distance kernels, and active learning.
result Surrogates can reduce the number of expensive electronic structure evaluations by an order of magnitude.
DrNAS improves neural architecture search with Dirichlet distribution and progressive learning.
problem Efficiently search for neural architectures with improved generalization and exploration.
method Formulates architecture search as a distribution learning problem using Dirichlet distribution and gradient-based optimization. Introduces a progressive learning scheme to handle large-scale tasks.
result Achieves state-of-the-art results on CIFAR-10 and ImageNet, demonstrating improved generalization and exploration.
Unified asymptotics for investment in markets with transaction costs and search frictions.
problem Investment in markets with transaction costs and search frictions.
method Power-utility maximization problem with proportional transaction costs and Poisson-triggered trades, analyzed using a novel asymptotic framework.
result Explicit asymptotics for the no-trade region and value function derived.
In deterministic optimization, line searches are a standard tool ensuring stability and efficiency. Where only stochastic gradients are available, no direct equivalent has so far been formulated, because uncertain gradients do not allow for a strict sequence of decisions collapsing the search space. We construct a prob…
In deterministic optimization, line searches are a standard tool ensuring stability and efficiency. Where only stochastic gradients are available, no direct equivalent has so far been formulated, because uncertain gradients do not allow for a strict sequence of decisions collapsing the search space. We construct a prob…
Paper shows MCTS approximates policy optimization, proposing an improved variant.
problem Improving AI performance through better MCTS algorithms.
method Shows MCTS approximates policy optimization problem, proposes a new algorithm.
result Proposed algorithm reliably outperforms original AlphaZero in multiple domains.
This work proposes searching for optimal operation distribution in neural architecture search.
problem Finding optimal neural architecture with specific operations and connections.
method Search for the optimal operation distribution, providing a stochastic and approximate solution.
result Operation distribution holds enough discriminating power to reliably identify a solution and is easier to optimise than traditional encodings.
Investment strategy optimized in markets with transaction costs and search delays.
problem Maximizing wealth in an illiquid market with transaction costs and search frictions.
method Characterized no-trade region and provided asymptotic expansions of value function for small transaction costs.
result The effects of transaction costs are more pronounced in illiquid markets.
Neural architecture search (NAS) recently attracts much research attention because of its ability to identify better architectures than handcrafted ones. However, many NAS methods, which optimize the search process in a discrete search space, need many GPU days for convergence. Recently, DARTS, which constructs a diffe…
JES optimizes expensive functions by considering joint entropy over input and output spaces.
problem Optimizing expensive functions with limited evaluations.
method Joint Entropy Search (JES) considers joint entropy over input and output spaces.
result JES outperforms other information-theoretic methods in Bayesian optimization.
Paper proposes an efficient bandit-based algorithm for hyperparameter optimization.
problem Efficiently evaluating hyperparameters in deep learning models with large search spaces.
method Sub-Sampling (SS) algorithm combined with Bayesian Optimization (BOSS).
result Theoretical proof of optimality and empirical validation of superior performance.
Design-by-Morphing creates radical airfoil designs without geometric constraints.
problem Design constraints limit airfoil design novelty and small changes.
method Design-by-Morphing (DbM) creates a search space without geometric constraints.
result DbM generates radical airfoils with remarkable lift-over-drag ratio and stall angle tolerance.
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.
LES optimizes designs by sampling descent sequences, achieving strong sample efficiency.
problem Optimizing large, complex design spaces is infeasible and unnecessary.
method LES uses Bayesian optimization to target solutions reachable by iterative optimizers.
result LES achieves strong sample efficiency compared to existing methods.
Driven by the need for parallelizable hyperparameter optimization methods, this paper studies \emph{open loop} search methods: sequences that are predetermined and can be generated before a single configuration is evaluated. Examples include grid search, uniform random search, low discrepancy sequences, and other sampl…