arXiv research

LaRT models LLMs' response accuracy and CoT length to evaluate reasoning ability and speed.

A new method improves SSVEP BCI to recognize responses in sub-second time with high accuracy.

We present two deep generative models based on Variational Autoencoders to improve the accuracy of drug response prediction. Our models, Perturbation Variational Autoencoder and its semi-supervised extension, Drug Response Variational Autoencoder (Dr.VAE), learn latent representation of the underlying gene states befor…

PEER tackles multi-response regression with incomplete outcomes efficiently.

Faster, more accurate IRT model for large datasets.

RLGP model improves robustness and accuracy for discontinuous response surfaces.

A new model estimates mixed memberships for categorical data with weighted responses.

Improved accuracy in dynamic response variation analysis using multi-fidelity data fusion.

New algorithm speeds up IRT model fitting for large datasets.

Study optimizes classifiers for credit card mail campaigns and default prediction.

How to generate human like response is one of the most challenging tasks for artificial intelligence. In a real application, after reading the same post different people might write responses with positive or negative sentiment according to their own experiences and attitudes. To simulate this procedure, we propose a s…

Incorporating nonlinearity is paramount to predicting the future states of a dynamical system, its response to shocks, and its underlying causal network. However, most existing methods for causality detection and impulse response, such as Vector Autoregression (VAR), assume linearity and are thus unable to capture the …

We build a deep reinforcement learning (RL) agent that can predict the likelihood of an individual testing positive for malaria by asking questions about their household. The RL agent learns to determine which survey question to ask next and when to stop to make a prediction about their likelihood of malaria based on t…

When approximating a black-box function, sampling with active learning focussing on regions with non-linear responses tends to improve accuracy. We present the FLOLA-Voronoi method introduced previously for deterministic responses, and theoretically derive the impact of output uncertainty. The algorithm automatically p…

Improves dialogue response model interpretability using attention and regularization.

In this study we present a kernel based convolution model to characterize neural responses to natural sounds by decoding their time-varying acoustic features. The model allows to decode natural sounds from high-dimensional neural recordings, such as magnetoencephalography (MEG), that track timing and location of human …

The paper proposes a new method to evaluate LLM agent responses using ECDF clustering.

FedIRT enables privacy-preserving psychometric estimation without centralizing data.

DynNet models dynamic responses of linear and nonlinear systems with fewer variables and higher accuracy.

In this paper, we propose deep learning algorithms for ranking response surfaces, with applications to optimal stopping problems in financial mathematics. The problem of ranking response surfaces is motivated by estimating optimal feedback policy maps in stochastic control problems, aiming to efficiently find the index…

New method for sparse kernel selection improves prediction accuracy.

Automates U.S. visa petition document classification and RFE response generation.

Estimating the effect of a treatment on a given outcome, conditioned on a vector of covariates, is central in many applications. However, learning the impact of a treatment on a continuous temporal response, when the covariates suffer extensively from measurement error and even the timing of the treatments is uncertain…

VED framework learns low-dimensional latent representations of physical systems.

ChatGPT's medical response accuracy is 56%, but studies vary widely.

Neuron Shapley identifies key neurons in deep networks, improving model accuracy and fairness.

Hydroxyurea (HU) has been shown to be effective in alleviating the symptoms of Sickle Cell Anemia disease. While Hydroxyurea reduces the complications associated with Sickle Cell Anemia in some patients, others do not benefit from this drug and experience deleterious effects since it is also a chemotherapeutic agent. T…

LLMs can predict CFO responses to economic surveys

Treatment effects can be estimated from observational data as the difference in potential outcomes. In this paper, we address the challenge of estimating the potential outcome when treatment-dose levels can vary continuously over time. Further, the outcome variable may not be measured at a regular frequency. Our propos…

A hybrid method combines model-based and data-driven approaches for multiscale constitutive responses.

In this article, we propose a novel probabilistic framework to improve the accuracy of a weighted majority voting algorithm. In order to assign higher weights to the classifiers which can correctly classify hard-to-classify instances, we introduce the Item Response Theory (IRT) framework to evaluate the samples' diffic…

Softmax is a standard final layer used in Neural Nets (NNs) to summarize information encoded in the trained NN and return a prediction. However, Softmax leverages only a subset of the class-specific structure encoded in the trained model and ignores potentially valuable information: During training, models encode an ar…

Study uses ML to predict non-participation in ELSA COVID-19 follow-up studies.

Study one-shot strategic classification under unknown costs, improving worst-case accuracy.

The paper provides concentration bounds for embeddings of generative models.

The study examines how class imbalance impacts logistic regression models in low-default credit portfolios.

The paper establishes concentration bounds for embeddings of generative models.

Consider a regression problem where there is no labeled data and the only observations are the predictions $f_i(x_j)$ of $m$ experts $f_{i}$ over many samples $x_j$. With no knowledge on the accuracy of the experts, is it still possible to accurately estimate the unknown responses $y_{j}$? Can one still detect the leas…

In this paper, we introduce a novel method to interpret recurrent neural networks (RNNs), particularly long short-term memory networks (LSTMs) at the cellular level. We propose a systematic pipeline for interpreting individual hidden state dynamics within the network using response characterization methods. The ranked …

A hybrid ML method improves ship response predictions across different sea conditions.

The P300 event-related potential (ERP), evoked in scalp-recorded electroencephalography (EEG) by external stimuli, has proven to be a reliable response for controlling a BCI. The P300 component of an event related potential is thus widely used in brain-computer interfaces to translate the subjects' intent by mere thoug…

NASirt automates CNN architecture design for spectral data.

Traditional set prediction models can struggle with simple datasets due to an issue we call the responsibility problem. We introduce a pooling method for sets of feature vectors based on sorting features across elements of the set. This can be used to construct a permutation-equivariant auto-encoder that avoids this re…

Time series models such as dynamical systems are frequently fitted to a cohort of data, ignoring variation between individual entities such as patients. In this paper we show how these models can be personalised to an individual level while retaining statistical power, via use of multi-task learning (MTL). To our knowl…

Study optimizes CANN for actuarial tasks using RSM.

Mean field variational Bayes (MFVB) is a popular posterior approximation method due to its fast runtime on large-scale data sets. However, it is well known that a major failing of MFVB is that it underestimates the uncertainty of model variables (sometimes severely) and provides no information about model variable cova…

ASADG improves data generation for accurate surrogate modeling of complex physical problems.

Deep Claim predicts payer responses from claims data using deep learning.