Computer graphics techniques improve art pricing by measuring painting effort.
problem Traditional art pricing models lack measures for conceptual and painting efforts.
method Applied image recognition to measure line and color variances as proxies for effort.
result Painting effort (line and color variances) significantly positively correlates with sales price.
New algorithms reduce effort for uncertainty in deep learning.
problem Uncertainty computation in deep learning models.
method Natural-gradient algorithms within Adam optimizer for weight perturbation.
result Uncertainty estimates of comparable quality with lower effort.
The paper proposes a method to measure fairness through equality of effort using algorithmic recourse.
problem Measuring fairness through equality of effort in automated systems.
method Applying algorithmic recourse to quantify equality of effort, overcoming previous limitations.
result An algorithm for assessing equality of effort has been developed and validated.
Gaussian process regression cuts energy evaluations for atomic rearrangement paths.
problem Reducing computational effort for minimum energy paths in complex systems.
method Gaussian process regression to approximate energy surfaces and converge to minimum energy paths.
result Significant reduction in energy evaluations (less than a fifth for a test problem).
Bayesian optimization reduces computational effort in aircraft design optimization.
problem High computational cost in industrial aircraft design optimization.
method Constrained Bayesian optimization (Super Efficient Global Optimization with Mixture of Experts)
result Significant computational efficiency improvements over existing Isight optimizers.
Many machine learning techniques sacrifice convenient computational structures to gain estimation robustness and modeling flexibility. However, by exploring the modeling structures, we find these "sacrifices" do not always require more computational efforts. To shed light on such a "free-lunch" phenomenon, we study the…
We consider effort allocation in crowdsourcing, where we wish to assign labeling tasks to imperfect homogeneous crowd workers to maximize overall accuracy in a continuous-time Bayesian setting, subject to budget and time constraints. The Bayes-optimal policy for this problem is the solution to a partially observable Ma…
Edge computing addresses AI on IoT devices by processing data locally.
problem Processing AI on resource-constrained IoT devices is challenging.
method Deploying machine learning systems at the edge of the network.
result Edge computing reduces latency and communication costs.
Two diversity models improve subset selection for image classification tasks.
problem Data scarcity and high costs in human labeling for supervised learning.
method Facility-Location and Disparity-Min models for training data subset selection and active learning.
result Subset selection improves accuracy by 2-3% with less training data.
Auptimizer simplifies hyperparameter tuning for machine learning models.
problem Difficulty and time-consuming hyperparameter tuning for machine learning models.
method General HPO framework that distributes computing resources and integrates various HPO techniques.
result Simplified model tuning and bookkeeping for data scientists.
A new method reduces computational cost for gene expression inference in large microarray data sets.
problem Efficiently predicting gene expression in large datasets with limited resources.
method Adaptive Lipschitz constant inspired learning rate, random sub-sampling, and A-ReLU activation function.
result Remarkable improvement in saving computational cost while maintaining prediction accuracy.
This paper improves MI-based BCIs by applying transfer learning across all components.
problem Reducing calibration effort for new subjects in MI-based BCIs.
method Proposes TL in spatial filtering, feature engineering, and classification blocks, and adds data alignment.
result Integrating data alignment and sophisticated TL significantly improves classification performance and reduces calibration effort.
New framework for probabilistic linear solvers reduces manual effort.
problem Manual implementation of probabilistic iterative methods is laborious.
method Affine Tracing: Automatically constructs PIMs from standard implementations.
result Any realistic affine PIM is calibrated, motivating their adoption.
New method to estimate doctors' effort in annotating medical images.
problem High effort and expense in annotating medical images.
method Proposes a new criterion to evaluate effort, uses active learning and U-shape network for annotation strategy, and fine annotation platform to reduce effort.
result State-of-the-art segmentation performance achieved with only 60% annotation candidates, reducing effort by 44-47%.
Models show strategic agents can influence classifier outcomes by investing effort.
problem How strategic agents can influence classifier outcomes.
method Developed a model to characterize strategic effort investment.
result Simple linear mechanisms can incentivize strategic effort effectively.
This study tackles XVA model risk and computational effort in derivatives pricing.
problem XVA model risk and computational effort in derivatives pricing, especially for counterparty and funding risk.
method Realistic and complete XVA modelling framework based on multi-curve time-dependent volatility G2++ stochastic dynamics, calibrated on real market data, and multi-step Monte Carlo simulation.
result Identification and quantification of model risk sources and computational effort in XVA figures.
The paper introduces effort-centric fairness to address masked inequality in lending decisions.
problem Masked inequality in lending decisions where rejected applicants face unequal burdens in reaching future approval.
method Developed an effort-centric framework measuring effort as minimum weighted cost of feasible changes, distinguishing feature-independent actions from structural shifts. Defined parity by comparing average minimum effort across protected groups and embedded in an in-processing fairness objective.
result Effort parity complements predictive fairness by revealing and mitigating hidden barriers to future credit access while making operational trade-offs explicit.
Serverless cloud computing speeds up double machine learning model estimation.
problem Efficiently estimating double machine learning models with minimal cloud resource management.
method Serverless computing with AWS Lambda for repeated cross-fitting.
result Demonstrates significant reduction in estimation times and costs.
QMC and GSA improve option pricing and risk measures efficiency.
problem Efficiently pricing and hedging complex financial instruments.
method Application of QMC and GSA techniques for financial instrument pricing and hedging, comparing MC vs QMC and analyzing greeks computation.
result QMC outperforms MC in most cases, especially in high-dimensional simulations, leading to faster and more stable convergence.
We analyze general model selection procedures using penalized empirical loss minimization under computational constraints. While classical model selection approaches do not consider computational aspects of performing model selection, we argue that any practical model selection procedure must not only trade off estimat…
Firefly algorithm improves software effort estimation models.
problem Improving accuracy of software effort estimation models.
method Using Firefly Algorithm to optimize COCOMO-based models.
result High accuracy and significant error minimization of Firefly Algorithm.
The study compares Fourier-based pricing methods, identifying the most efficient and accurate.
problem Comparing CPU effort and pricing biases of Fourier-based implementations.
method Numerical analysis of seven Fourier-based implementations, focusing on truncation and discretization errors.
result The multi-strike version of the COS method is notably faster, and the strike-optimized Carr Madan's formula is both faster and more accurate.
Reduces test set maintenance effort by 80-100%.
problem Lack of proper and up-to-date test sets in real-world scenarios.
method Simple technique to reduce labeling effort.
result Significant reduction in test set maintenance effort (80-100%).
The study identifies influential bioinformatics algorithms for scalable computing.
problem Data deluge in bioinformatics and need for scalable computing solutions.
method Identifying and analyzing influential data mining and machine learning algorithms.
result Guiding scalable computing experts to focus on specific bioinformatics algorithms.
CNNs improve signal-background classification in particle physics experiments.
problem Improving accuracy in classifying signal from background in particle physics experiments.
method Extensive convolutional neural architecture search for 2D and 3D image data.
result Achieved high accuracy for signal/background discrimination with CNNs, less parameters than ResNet.
Replication study shows Deep-SE still not as effective as previously thought for agile effort estimation.
problem Improving accuracy in estimating agile software development effort.
method Close replication of Deep-SE using additional data and comparison with multiple baselines.
result Deep-SE outperforms only a few cases, suggesting more work is needed.
Optimizes crypto-oriented neural architectures for faster secure inference.
problem Privacy conflicts between model users and providers in neural network applications.
method Proposes a novel Partial Activation layer to optimize the initial design of crypto-oriented neural architectures.
result Significant improvement in the efficiency of secure inference on common evaluation metrics.
This paper compares AI performance in native vs. browser-based implementations.
problem Performance demands in AI applications, especially client-side.
method Comparison study between native code and browser-based (JS, ASM.js, WebAssembly) implementations.
result Current runtime optimizations push browser performance close to native binary.
New formula calculates volumes of ideal hyperbolic drums.
problem Computing volumes of ideal hyperbolic drums.
method Proved a volume formula for arbitrary ideal hyperbolic antiprisms (drums).
result Volume formula for ideal hyperbolic drums.
We compare the option pricing formulas of Louis Bachelier and Black-Merton-Scholes and observe -- theoretically as well as for Bachelier's original data -- that the prices coincide very well. We illustrate Louis Bachelier's efforts to obtain applicable formulas for option pricing in pre-computer time. Furthermore we ex…
Two methods using Chebyshev tensors improve accuracy and speed in computing Dynamic Initial Margin.
problem Computing Dynamic Initial Margin (DIM) with high accuracy and speed.
method Two methods based on Chebyshev tensors implemented in Monte Carlo engine.
result Better accuracy, speed, and implementation efforts compared to benchmarks.
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.
Adaptive Bernstein copulas improve risk management by preventing overfitting and reducing simulation effort.
problem Overfitting and high simulation effort in estimating dependence models.
method Constructive approach to Bernstein copulas with an admissible discrete skeleton.
result Comparison of different copula approaches in risk management shows improved accuracy and efficiency.
We provide the first experimental results on non-synthetic datasets for the quasi-diagonal Riemannian gradient descents for neural networks introduced in [Ollivier, 2015]. These include the MNIST, SVHN, and FACE datasets as well as a previously unpublished electroencephalogram dataset. The quasi-diagonal Riemannian alg…
ADS automates data preparation for ML/AI, reducing human effort.
problem Manual and time-consuming data preparation for ML/AI.
method Data-driven approach using statistics and ML.
result ADS automates data exploration and processing steps.
Paper simplifies DP composition for adaptive privacy budgets, enabling better privacy and accuracy in deep learning.
problem Tension between efficiency and flexibility in DP composition theorems.
method Rényi Differential Privacy (RDP) for adaptive privacy budgets, proving simpler composition theorem with smaller constants.
result Practical DP composition for adaptive privacy budgets, enabling better privacy and accuracy in deep learning.
Study real-world noisy labels from human annotations for better understanding.
problem Understanding and modeling real-world label noise in machine learning.
method Developed two new benchmark datasets (CIFAR-10N, CIFAR-100N) with human-annotated real-world noisy labels.
result Real-world noisy labels exhibit instance-dependent patterns, not class-dependent as previously assumed.
Probabilistic inference procedures are usually coded painstakingly from scratch, for each target model and each inference algorithm. We reduce this effort by generating inference procedures from models automatically. We make this code generation modular by decomposing inference algorithms into reusable program-to-progr…
Better Hessian approximations improve influence function attributions in deep learning.
problem Influence functions are difficult to compute due to ill-conditioned Hessians, leading to poor data attribution performance.
method Investigated the impact of Hessian approximation quality on influence-function attributions in a controlled setting.
result Better Hessian approximations consistently yield better influence score quality.
CNN improves salt body interpretation in seismic imaging.
problem Manual salt body interpretation is time-consuming and prone to bias.
method U-Net and ResNet with ELU activation and Lovász-Softmax loss.
result CNN predictions match manual interpretations well, especially in weak reflection areas.
Optimal allocation of human effort to correct AI assessments in decision-making.
problem How to allocate costly human effort to correct noisy or biased AI-generated assessments.
method Decision-theoretic framework treating AI assessments as signals and human judgments as costly information. Developed estimation procedures under nonparametric and linear models.
result Our approach substantially outperforms LLM-only predictions and achieves performance comparable to full human review while using only 20-30% of the human information.
We find polynomial-time solutions to the word problem for free-by-cyclic groups, the word problem for automorphism groups of free groups, and the membership problem for the handlebody subgroup of the mapping class group. All of these results follow from observing that automorphisms of the free group strongly resemble s…
Optimal contracts are found for agents with quadratic effort costs.
problem Finding optimal contracts in principal-agent problems with quadratic effort costs.
method Modeling the problem using Hamilton-Jacobi-Bellman (HJB) equations and proving the existence of classical solutions.
result Existence of optimal contracts for agents with quadratic effort costs is proven.
A new neural machine translation method learns from human feedback and reduces human effort.
problem Efficiently reducing human effort in interactive-predictive neural machine translation.
method Learning from human reinforcements, using entropy for feedback triggers, and online model updates.
result Significant improvement in translation quality with reduced human feedback requests.
ControlSHAP stabilizes Shapley value approximations using control variates.
problem High computational cost of exact Shapley values in blackbox models.
method ControlSHAP uses Monte Carlo control variates to stabilize Shapley value approximations.
result Significant reduction in Monte Carlo variability of Shapley estimates.
In Classical Knot Theory and in the new Theory of Quantum Invariants substantial effort was directed toward the search for unknotting moves on links. We solve, in this note, several classical problems concerning unknotting moves. Our approach uses a new concept, Burnside groups of links, which establishes unexpected re…
Transfer Neural AutoML speeds up deep learning architecture design.
problem High computational cost in Neural AutoML.
method Transfer learning to speed up architecture design.
result Reduces convergence time by over an order of magnitude.
aLIME produces clear rule-based explanations for model predictions.
problem Interpreting machine learning models for accurate human predictions.
method Anchor-LIME (aLIME) for model-agnostic rule-based explanations.
result aLIME produces high-precision rule-based explanations with clear coverage boundaries.