Optimizes function networks by selectively evaluating parts of the network, reducing costs.
problem Optimizing expensive function networks where full evaluations are costly.
method Knowledge gradient acquisition function for cost-aware partial evaluations.
result Outperforms existing BOFN methods and benchmarks across various problems.
Study proposes a low-cost method to evaluate RNN performance.
problem Hyper-parameter optimization of recurrent neural networks is challenging and costly.
method Employs a low computational cost model to evaluate RNN performance based on weight error distribution.
result Empirically validated as a promising alternative to reduce hyper-parameter exploration costs.
Study adversarial attacks on cost-sensitive classifiers.
problem Safety-critical classification problems with cost-sensitive predictions.
method Used state-of-the-art adversarially-resistant neural networks and analyzed as a two-player zero-sum game.
result Introduced a new cost-sensitive attack that performs better than targeted attacks in some cases.
Cost-aware BO minimizes function evaluations with varying costs.
problem Optimization with varying evaluation costs in expensive functions.
method Cost Apportioned Bayesian Optimization (CArBO) combining initial and cost-cooled phases.
result CArBO finds better hyperparameter configurations with the same cost budget.
Cost-aware multi-objective Bayesian optimization for non-uniformly expensive functions.
problem Non-uniform cost of function evaluations in Bayesian optimization.
method Introduces cost-aware constraints and a new acquisition function to optimize multi-objective functions with varying costs.
result Demonstrates improved optimization in hyperparameter tuning of neural networks and random forests.
FlexiBO optimizes deep neural networks by balancing cost and performance.
problem Optimizing deep neural networks for multiple objectives incurs high costs.
method Decouples and weights cost in multi-objective Bayesian optimization.
result FlexiBO discovers designs with lower hypervolume error.
Accelerates Bayesian optimization of function networks with partial evaluations.
problem Optimizing expensive-to-evaluate function networks with varying node costs.
method Proposes an accelerated algorithm that uses global Monte Carlo simulations to select node-specific candidate inputs.
result Achieves up to a 16x speedup over the original p-KGFN algorithm while maintaining competitive query efficiency.
New method optimizes costly evaluations in Bayesian optimization.
problem Costly evaluations in BO methods, especially in hyperparameter tuning.
method Formulated as a CMDP, developed rollout approximation for optimal policy.
result Improved cost efficiency over standard BO methods.
AlphaX uses MCTS and Meta-DNN to improve NAS efficiency and accuracy.
problem Improving sample efficiency and network evaluation cost in NAS.
method Adaptive MCTS with Meta-DNN for prediction and distributed rollouts for cost reduction.
result AlphaX finds architectures with high accuracy (97.84% on CIFAR-10, 75.5% on ImageNet) in fewer samples.
Proposes ECS-DBN for cost-sensitive deep belief network in imbalanced classification.
problem Imbalanced data classification with unequal misclassification costs.
method ECS-DBN uses adaptive differential evolution to optimize misclassification costs based on training data.
result ECS-DBN consistently outperforms state-of-the-art methods on benchmark and real-world datasets.
Experiment evaluates hospital case cost prediction models using Azure ML.
problem Accurate hospital case cost modelling for efficient financial management.
method Azure Machine Learning Studio tool for comparing 14 regression models.
result Robust regression, boosted decision tree, and decision forest models outperformed others.
New method reduces mixture model evaluation cost for large models.
problem Computational infeasibility of evaluating all mixture components.
method Combining EM and Metropolis-Hastings for stochastic sampling.
result Significantly reduced computational cost for large models.
New method combines neural networks with Monte Carlo for complex system reliability.
problem Estimating small failure probabilities in complex systems.
method Subset Simulation with Hamiltonian Neural Networks.
result High acceptance rates and computational efficiency in low-probability regions.
This paper models and evaluates contagion and stabilisation in interconnected financial markets.
problem Understanding and managing contagion and resilience in multilayer financial networks.
method Formulates an interconnected multiplex structure, models contagion mechanism, and designs minimum-cost stabilisation strategies.
result Empirically validated minimum-cost stabilisation strategies for multichannel contagion containment.
Surveying deep meta-learning to improve quick concept learning.
problem Limitation of deep neural networks in learning new concepts quickly.
method Categorizes deep meta-learning techniques into metric, model, and optimization-based approaches.
result Unified overview of current deep meta-learning techniques.
Develops a new PAC-Bayesian bound for evaluating randomness in predictors.
problem Lack of a PAC-Bayesian bound for deterministic predictors and continuous loss functions.
method PAC-Bayesian transportation bound unifying PAC-Bayesian and chaining methods.
result First PAC-Bayesian bound relating risks of any two predictors by their distance.
A new method reduces log determinant evaluation cost from cubic to quadratic.
problem Efficiently evaluating log determinants in machine learning.
method Variational Bayesian approximation with complexity O(n^2).
result State-of-the-art performance on synthetic and real-world datasets.
This research evaluates neural network robustness through loss visualization and a new metric.
problem Neural networks' robustness property is insufficiently investigated compared to adversarial attacks and defenses.
method Loss visualization and a new robustness metric to evaluate model stability.
result The proposed robustness metric provides a more reliable evaluation of model stability, uniformed across different models and settings.
Pruning filters in neural networks improves performance and reduces costs.
problem Large neural networks have high inference costs and limited resource usage.
method Batch Bridgeout for efficient pruning of convolutional filters.
result Batch Bridgeout trained networks achieve higher accuracy across various pruning intensities.
HOIST uses multiple surrogates to optimize DNN hyperparameters efficiently.
problem Insufficient evaluation data for Bayesian optimization of DNN hyperparameters.
method HOIST combines complete and intermediate evaluation data using weighted bagging of multiple surrogates.
result HOIST outperforms state-of-the-art approaches on various DNN types.
This review explores how multiple agents learn to communicate in complex environments.
problem Learning effective communication strategies among multiple agents in partially observable environments.
method Review of recent algorithms and models for improving communication between agents, including Deep Recurrent Q-Networks.
result Introduction of a novel entropy-based evaluation metric for communication strategies.
DANCE optimizes neural network and accelerator design for faster, more efficient DNN execution.
problem Challenges in optimizing neural network and accelerator design for efficient DNN execution.
method Differentiable approach to co-exploration of accelerator and network architecture design.
result Significantly shorter time to achieve superior accuracy and hardware cost metrics.
BMBO-DARN optimizes expensive functions with varying fidelities.
problem Optimizing expensive, multi-fidelity functions efficiently.
method Batch Multi-fidelity Bayesian Optimization with Deep Auto-Regressive Networks.
result BMBO-DARN improves surrogate learning and optimization performance.
This paper proposes a cost-sensitive feature acquisition method.
problem Choosing features for prediction with low cost and high accuracy.
method Adaptive feature selection using feature relevance and costs.
result Our approach achieves high accuracy with lower cost than state-of-the-art.
Cer-Eval saves LLM evaluation costs while maintaining accuracy.
problem Challenges in evaluating large language models due to large dataset requirements.
method Adapts to different evaluation objectives, uses test sample complexity, and develops a partition-based algorithm.
result Cer-Eval can save 20-40% test points with comparable accuracy and 95% confidence guarantee.
This paper introduces a cost-aware feature acquisition method using denoising autoencoders.
problem Optimizing feature acquisition costs in real-world scenarios.
method Incrementally asks for features based on context and uses denoising autoencoders for unknown features.
result The method efficiently acquires features at test-time in a cost- and context-aware fashion.
A deep reinforcement learning method for cost-sensitive portfolio selection.
problem Non-stationary price series and complex asset correlations make feature learning hard, and practical cost constraints are not considered.
method A two-stream portfolio policy network and a cost-sensitive reward function are developed using deep reinforcement learning.
result The method achieves superior performance in profitability, cost-sensitivity, and representation abilities.
Improves classifier evaluation by aligning with Total Classification Cost.
problem Lack of consensus on evaluation metrics and class imbalance issues.
method Introduces Weighted Accuracy (WA) and a reweighting framework for cost-sensitive scenarios.
result WA aligns with Total Classification Cost (TCC) minimization under realistic conditions.
Novel Bayesian Optimization for cost-effective function evaluation.
problem Optimizing functions with variable evaluation costs.
method Bayesian Optimization with adaptive sampling.
result Significantly reduced optimization overhead compared to previous methods.
New method optimizes costly functions with unknown costs and budget constraints.
problem Optimizing functions with unknown and heterogeneous evaluation costs under a budget constraint.
method Budgeted multi-step expected improvement acquisition function.
result Our method outperforms existing approaches in various synthetic and real problems.
Enhances neural networks for regression tasks with minimal learning time increase.
problem Improving performance of neural networks in regression tasks.
method Extends the learning procedure of a neural network to improve its performance without changing the prediction.
result The modified model performs better than the original model with minimal learning time increase.
Learn effective driving policies from traffic cameras without interaction.
problem Learning policies from observational data in dynamic environments.
method Model-predictive policy learning with uncertainty regularization.
result Effective driving policies learned from observational data.
Adaptive ensembling reduces inference cost for deep neural networks.
problem High inference cost in ensembling multiple predictions.
method Adaptive control of ensembling based on confidence level.
result Adaptive ensembling reduces computation cost significantly without sacrificing accuracy.
Adaptive neural networks cut inference time by 2.8x with minimal accuracy loss.
problem Efficiently evaluate deep neural networks for new examples without sacrificing accuracy.
method Two adaptive schemes: early exit and network selection, learned through binary classification.
result Dramatic reductions in computational cost with minimal accuracy loss.
The paper proposes a technique to speed up evolutionary algorithms by using lower-cost approximations of the objective function.
problem Evolutionary algorithms require many evaluations to solve computationally expensive black-box optimization problems.
method The paper introduces a technique to choose an appropriate approximate function cost during the execution of the optimization algorithm.
result The proposed approach can reach the same objective value in less than half the time in certain cases.
Benchmarking deep learning models for financial time series, focusing on risk-adjusted performance.
problem Optimizing risk-adjusted performance in financial time series prediction.
method Evaluation of various deep learning architectures including linear models, RNNs, transformers, state space models, and sequence representation approaches.
result Hybrid models like VSN with LSTM and xLSTM achieve the highest overall Sharpe ratio and superior downside adjusted characteristics.
This paper proposes CSADA to make DNNs cost-sensitive.
problem Over-parameterization challenges cost-sensitive classification in DNNs.
method CSADA framework using adversarial data augmentation.
result CSADA effectively minimizes overall cost and reduces critical errors.
Deep reinforcement learning optimizes retrosynthetic planning for chemical synthesis.
problem Optimizing chemical synthesis plans from molecular targets to simpler starting materials.
method Deep reinforcement learning to estimate synthesis costs and values of molecules.
result Trained neural networks outperform heuristic approaches in synthesizing unfamiliar molecules.
Study develops a semi-supervised deep ResNet for Wi-Fi mode detection.
problem Utilizing Wi-Fi signals for multimodal transportation mode detection with limited labeled data.
method Semi-supervised deep residual network (ResNet) framework.
result Framework achieves high prediction accuracy (81.8% for walking, 82.5% for biking, 86.0% for driving).
Paper optimizes broker performance by estimating execution costs.
problem Minimizing execution costs for large trades.
method Intraday modeling of execution cost components (linear and quadratic).
result Substantial improvements in estimating execution costs.
Bayesian design improves accuracy without extra cost.
problem Nested inference in complex systems limits BED accuracy and efficiency.
method Grouped geometric pooled posterior with EKI formulation.
result Improved accuracy and stable estimators at comparable cost.
Generative adversarial networks enforce no-arbitrage in volatility surface computation.
problem Efficiently compute volatility surfaces without arbitrage violations.
method Generative adversarial network (GAN) with no-arbitrage constraints.
result Proposed GAN model outperforms ANN approaches in accuracy and computational time.
Certified algorithms optimize functions with varying costs, providing error bounds.
problem Optimizing functions with varying evaluation costs and error bounds.
method Formalized as a min-max game, proposed certified MFDOO algorithm with cost complexity bound.
result Proposed certified MFDOO algorithm has near-optimal cost complexity for Lipschitz functions.
E2CM uses class means for efficient early exits in neural networks.
problem Efficient early exits in neural networks with low computational cost.
method Early Exit Class Means (E2CM) based on class means of samples, without gradient-based training. result E2CM achieves higher accuracy with fixed training time budget and boosts existing early exit schemes. Reduces annotation costs in medical imaging by 50%.
problem Challenges in creating large annotated datasets for medical imaging.
method Integrates active learning and transfer learning into a single framework.
result Reduces annotation efforts by at least half.
InferPy simplifies probabilistic modeling with deep neural networks in Python.
problem Complex probabilistic models with deep neural networks.
method User-friendly API for defining, learning, and evaluating models.
result Compact and simple way to define general hierarchical probabilistic models.
Gradual pruning reduces inference cost by pruning least important channels during training.
problem Reduction of deep neural network inference cost.
method Gradual channel pruning using feature relevance scores during training.
result Achieved significant model compression with minimal accuracy loss.
Paper finds efficient algorithms for computing fixed points in financial networks.
problem Computing fixed points in complex financial networks with potential defaults.
method Tarski's theorem and polynomial-time algorithms for minimal and maximal fixed points.
result Efficient algorithms for computing minimal and maximal fixed points in financial networks.