arXiv research

Efficient method for high confidence level inference using parallel stochastic optimization.

Structural equation models and Bayesian networks have been widely used to study causal relationships between continuous variables. Recently, a non-Gaussian method called LiNGAM was proposed to discover such causal models and has been extended in various directions. An important problem with LiNGAM is that the results a…

Novel confidence sets improve linear bandit performance by adapting to unknown noise levels.

This paper studies the geometry of minimum-volume confidence sets for multinomial parameters.

LLMs generate answers under incomplete context, and their uncertainty should scale with missing information.

The paper finds a fundamental trade-off between confidence and efficiency in transductive conformal prediction.

Hypothesis testing is an important problem with applications in target localization, clinical trials etc. Many active hypothesis testing strategies operate in two phases: an exploration phase and a verification phase. In the exploration phase, selection of experiments is such that a moderate level of confidence on the …

New flexible confidence sequences for robust statistical inference.

The estimation of probabilities of default (PDs) for low default portfolios by means of upper confidence bounds is a well established procedure in many financial institutions. However, there are often discussions within the institutions or between institutions and supervisors about which confidence level to use for the…

Fuzzy prediction sets generalize binary predictions to include elements at varying confidence levels.

The paper addresses the gap between theoretical and practical confidence set widths in universal inference.

New method for online learning IC models with node-level feedback.

BILBO optimizes bilevel problems without repeated lower-level optimizations.

A modification of the confidence screening mechanism based on adaptive weighing of every training instance at each cascade level of the Deep Forest is proposed. The idea underlying the modification is very simple and stems from the confidence screening mechanism idea proposed by Pang et al. to simplify the Deep Forest …

Bayesian approach improves online prediction accuracy without distributional assumptions.

We present a confidence-based single-layer feed-forward learning algorithm SPIRAL (Spike Regularized Adaptive Learning) relying on an encoding of activation spikes. We adaptively update a weight vector relying on confidence estimates and activation offsets relative to previous activity. We regularize updates proportion…

One of the problems on the way to successful implementation of neural networks is the quality of annotation. For instance, different annotators can annotate images in a different way and very often their decisions do not match exactly and in extreme cases are even mutually exclusive which results in noisy annotations a…

We study the asymptotic behavior of the difference $Δρ^{X, Y}_α:= ρ_α(X + Y) - ρ_α(X)$ as $α\rightarrow 1$, where $ρ_α$ is a risk measure equipped with a confidence level parameter $0 < α< 1$, and where $X$ and $Y$ are non-negative random variables whose tail probability functions are regularly varying. The case where …

Develops a method to find costly high-confidence errors in black box models.

The paper tackles best arm identification with minimal regret in experiments.

New algorithm resists corruption in linear contextual bandits.

There are two major paradigms of white-box adversarial attacks that attempt to impose input perturbations. The first paradigm, called the fix-perturbation attack, crafts adversarial samples within a given perturbation level. The second paradigm, called the zero-confidence attack, finds the smallest perturbation needed …

This work introduces COLA, a strategy to aggregate conformal prediction sets efficiently.

The paper honors Lai's contributions to multi-armed bandits and establishes new regret bounds.

CCE improves anomaly detection metrics by measuring both confidence and consistency.

This study evaluates methods to measure traffic forecasting model confidence.

Survey of methods to calibrate neural network predictions.

Ensembling multiple predictions is a widely used technique for improving the accuracy of various machine learning tasks. One obvious drawback of ensembling is its higher execution cost during inference. In this paper, we first describe our insights on the relationship between the probability of prediction and the effec…

We study the tradeoff between computational effort and classification accuracy in a cascade of deep neural networks. During inference, the user sets the acceptable accuracy degradation which then automatically determines confidence thresholds for the intermediate classifiers. As soon as the confidence threshold is met,…

New methods improve confidence set calibration in complex models.

New priors improve Bayesian neural networks without cooling.

CP improves robustness against distribution shift using physics-informed structural causal models.

Near-optimal tests and confidence sequences for non-parametric data.

Proposes integrating global and local entropy for more reliable LLMs.

This work is about recognizing human activities occurring in videos at distinct semantic levels, including individual actions, interactions, and group activities. The recognition is realized using a two-level hierarchy of Long Short-Term Memory (LSTM) networks, forming a feed-forward deep architecture, which can be tra…

New method improves level set estimation with theoretical guarantees.

Proposes methods for online conformal prediction with nested prediction sets across multiple confidence levels.

In this paper, we study a simple algorithm to construct asymptotically valid confidence regions for model parameters using the batch means method. The main idea is to cancel out the covariance matrix which is hard/costly to estimate. In the process of developing the algorithm, we establish process-level functional cent…

CONTINA provides adaptive confidence intervals for traffic demand prediction.

Study explores efficient data division for ICPs.

Study three types of uncertainty quantification for binary classification without distributional assumptions.

The contour maps of the error of historical resp. parametric estimates for large random portfolios optimized under the risk measure Expected Shortfall (ES) are constructed. Similar maps for the sensitivity of the portfolio weights to small changes in the returns as well as the VaR of the ES-optimized portfolio are also…

The paper addresses the difficulty of decision makers trusting AI-assisted predictions and proposes a method to improve confidence values.

If the probability of default parameters (PDs) fed as input into a credit portfolio model are estimated as through-the-cycle (TTC) PDs stressed market conditions have little impact on the results of the capital calculations conducted with the model. At first glance, this is totally different if the PDs are estimated as…

All people have to make risky decisions in everyday life. And we do not know how true they are. But is it possible to mathematically assess the correctness of our choice? This article discusses the model of decision making under risk on the example of project management. This is a game with two players, one of which is…

The paper improves NN predictions with reliable confidence intervals.

New algorithm improves best arm identification in Bayesian settings.

Corporate transparency reduces investors' disposition effect by increasing confidence in holding profitable and losing stocks.