arXiv research

New classifier robust to adversarial perturbations from high-accuracy models.

This work improves surrogate models for balancing accuracy and cost in multi-fidelity methods.

CNNs overinterpret inputs, leading to high accuracy without meaningful features.

Attack reveals model details from counterfactual explanations.

Deploying machine learning systems in the real world requires both high accuracy on clean data and robustness to naturally occurring corruptions. While architectural advances have led to improved accuracy, building robust models remains challenging. Prior work has argued that there is an inherent trade-off between robu…

A deep learning model predicts future cache accesses with high accuracy.

We propose a novel adaptive approximation approach for test-time resource-constrained prediction. Given an input instance at test-time, a gating function identifies a prediction model for the input among a collection of models. Our objective is to minimize overall average cost without sacrificing accuracy. We learn gat…

EnSF improves accuracy in tracking high-dimensional nonlinear systems.

High-dimensional spectroscopy data makes ML models achieve near-perfect accuracy, even when chemical distinctions are absent.

G-Net constructs binary neural networks with high accuracy using randomized binary embeddings.

We present a dynamic model selection approach for resource-constrained prediction. Given an input instance at test-time, a gating function identifies a prediction model for the input among a collection of models. Our objective is to minimize overall average cost without sacrificing accuracy. We learn gating and predict…

JTT improves model worst-group accuracy without group annotations.

Extensive neural networks eliminate the need for SABR pricing formulas.

Improved ridge estimators avoid tuning parameters for high-dimensional data.

Hybrid model combines VAR and neural network for OFI prediction.

In a model extraction attack, an adversary steals a copy of a remotely deployed machine learning model, given oracle prediction access. We taxonomize model extraction attacks around two objectives: *accuracy*, i.e., performing well on the underlying learning task, and *fidelity*, i.e., matching the predictions of the r…

The shortage of high-resolution urban digital elevation model (DEM) datasets has been a challenge for modelling urban flood and managing its risk. A solution is to develop effective approaches to reconstruct high-resolution DEMs from their low-resolution equivalents that are more widely available. However, the current …

This study compares machine learning methods for high-cardinality categorical variables.

Study privacy and accuracy in high-dimensional LASSO with perturbation mechanisms.

ProductNet is a collection of high-quality product datasets for better product understanding. Motivated by ImageNet, ProductNet aims at supporting product representation learning by curating product datasets of high quality with properly chosen taxonomy. In this paper, the two goals of building high-quality product dat…

DF2M uses deep neural networks within a factor model for high-dimensional functional time series forecasting.

The paper tackles fairness and accuracy in ML models under domain shifts.

SynergicLearning combines NN and HD models for high accuracy and efficiency.

With the increased affordability and availability of whole-genome sequencing, large-scale and high-throughput gene expression is widely used to characterize diseases, including cancers. However, establishing specificity in cancer diagnosis using gene expression data continues to pose challenges due to the high dimensio…

TARP tests accuracy of generative posterior estimators.

New method uses low-fidelity simulations to efficiently infer parameters of high-fidelity models.

Newfluence improves model interpretability in high-dimensional AI models.

Deep learning models predict stock prices with high accuracy.

A simple, yet reasonably accurate, analytical technique is proposed for multi-factor structural credit portfolio models. The accuracy of the technique is demonstrated by benchmarking against Monte Carlo simulations. The approach presented here may be of high interest to practitioners looking for transparent, intuitive,…

Proposes a new prior for complex models to improve prediction accuracy.

Optimal kernel learning improves GP regression for high-dimensional inputs.

Adversarial training can hurt robust accuracy in small sample size scenarios.

Proposes an accuracy-preserving calibration method for DNNs.

Much of human knowledge sits in large databases of unstructured text. Leveraging this knowledge requires algorithms that extract and record metadata on unstructured text documents. Assigning topics to documents will enable intelligent search, statistical characterization, and meaningful classification. Latent Dirichlet…

QubitHD improves HD computing ML efficiency without sacrificing accuracy.

Learning ReLU networks to high uniform accuracy requires exponentially many samples.

New method estimates graphons from multiple networks with high accuracy and low complexity.

Discriminative jackknife estimates deep learning uncertainty.

SPPCSO addresses multicollinearity in high-dimensional data, improving model stability and predictive accuracy.

New methods combine low and high-fidelity data for accurate surrogate modeling.

This paper proposes BAT to balance accuracy and robustness in adversarial training.

Stochastic methods improve data assimilation with high-frequency sensor data.

Engineering problems often involve data sources of variable fidelity with different costs of obtaining an observation. In particular, one can use both a cheap low fidelity function (e.g. a computational experiment with a CFD code) and an expensive high fidelity function (e.g. a wind tunnel experiment) to generate a dat…

Deep learning predicts NFT prices with high accuracy.

The high cost of communicating gradients is a major bottleneck for federated learning, as the bandwidth of the participating user devices is limited. Existing gradient compression algorithms are mainly designed for data centers with high-speed network and achieve $O(\sqrt{d} \log d)$ per-iteration communication cost at…

Gradient boosting for spatial regression models improves prediction accuracy.

New model predicts travel demand uncertainty with high accuracy.

This study explores training Bayesian neural networks at scale using high-performance computing.