arXiv research

Derives exact gradients for linear optics with single photons.

Test-time training adapts a pretrained model to each prompt via parameter updates, improving accuracy under pretraining-to-test distribution shifts.

This research focuses on invariant probabilistic predictions, showing they are not robust under distribution shifts.

Proposes robust ITRs integrating multiple datasets to handle posterior shift.

New methods for Bayesian inference using mean shift particle systems.

Improves VQAs by balancing classical and quantum training resources.

Researchers adaptively analyze market regimes to reveal investor behavior shifts.

Proposes a new measure to evaluate stability of statistical parameters under distributional shifts.

MELO predicts electricity loads by adapting to shifts without external indicators.

Paper tackles high-dimensional quantile regression with distribution shift using transfer learning.

Practical or scientific considerations often lead to selecting a subset of parameters as ``important.'' Inferences about those parameters often are based on the same data used to select them in the first place. That can make the reported uncertainties deceptively optimistic: confidence intervals that ignore selection g…

Detects changes in classifier scores to identify shifts in class priors.

In the framework of geometric quantization we extend the Bohr-Sommerfeld rules to a full quantization theory which resembles Heisenberg's matrix theory. This extension is possible because Bohr-Sommerfeld rules not only provide an orthogonal basis in the space of quantum states, but also give a lattice structure to this…

Unified framework certifies predictor performance under distribution shift.

Anytime-valid confirmation of label-shift corrections

We are concerned with the vulnerability of computer vision models to distributional shifts. We formulate a combinatorial optimization problem that allows evaluating the regions in the image space where a given model is more vulnerable, in terms of image transformations applied to the input, and face it with standard se…

The Lamarle Formula, given by Kruppa in \cite{Kr}, is known as a relationship between the Gaussian curvature and the distribution parameter of a ruled surface in the surface theory. The ruled surfaces were investigated in 3 different classes with respect to the character of base curves and rulings, \cite{Tu1},\cite{Tu2…

A learning algorithm optimizes beamforming for holographic transceivers in far-field communication.

Study on tracking preference shifts in dueling bandits problems.

This paper improves STL inference reliability under covariate shift.

New Fourier features improve high-precision approximation in large-scale problems.

New rules reduce SLOPE model fitting time by screening out irrelevant variables.

Express Wavenet is an improved optical diffractive neural network. At each layer, it uses wavelet-like pattern to modulate the phase of optical waves. For input image with n2 pixels, express wavenet reduce parameter number from O(n2) to O(n). Only need one percent of the parameters, and the accuracy is still very high.…

This paper presents the construction of a particle filter, which incorporates elements inspired by genetic algorithms, in order to achieve accelerated adaptation of the estimated posterior distribution to changes in model parameters. Specifically, the filter is designed for the situation where the subsequent data in on…

Typically, operational risk losses are reported above some threshold. This paper studies the impact of ignoring data truncation on the 0.999 quantile of the annual loss distribution for operational risk for a broad range of distribution parameters and truncation levels. Loss frequency and severity are modelled by the P…

New method corrects biased predictions and uncertainty estimates in classification with nuisance parameters.

New research shows LLMs can't be explained by statistical generalization alone.

Anchor-TS uses median anchoring to improve online decision-making from offline data with distribution shift.

This work addresses the problem of segmentation in time series data with respect to a statistical parameter of interest in Bayesian models. It is common to assume that the parameters are distinct within each segment. As such, many Bayesian change point detection models do not exploit the segment parameter patterns, whi…

An expanding literature articulates the view that Taylor rules are helpful in predicting exchange rates. In a changing world however, Taylor rule parameters may be subject to structural instabilities, for example during the Global Financial Crisis. This paper forecasts exchange rates using such Taylor rules with Time V…

Proposes PRMs for interpreting financial risk concept drift.

A new policy for contextual bandits adapts to reward vector shifts.

In this paper, we study two classes of planar self-similar fractals $T_\varepsilon$ with a shifting parameter $\varepsilon$. The first one is a class of self-similar tiles by shifting $x$-coordinates of some digits. We give a detailed discussion on the disk-likeness ({\it i.e., the property of being a topological disk}…

SAMPLR optimizes for ground truth in aleatoric parameters to avoid curriculum-induced covariate shift.

We propose an improved LASSO estimation technique based on Stein-rule. We shrink classical LASSO estimator using preliminary test, shrinkage, and positive-rule shrinkage principle. Simulation results have been carried out for various configurations of correlation coefficients ($r$), size of the parameter vector ($β$), …

We consider the problem of function estimation in the case where an underlying causal model can be inferred. This has implications for popular scenarios such as covariate shift, concept drift, transfer learning and semi-supervised learning. We argue that causal knowledge may facilitate some approaches for a given probl…

New algorithm provides robust uncertainty quantification without parameter tuning.

In the artificial intelligence field, learning often corresponds to changing the parameters of a parameterized function. A learning rule is an algorithm or mathematical expression that specifies precisely how the parameters should be changed. When creating an artificial intelligence system, we must make two decisions: …

Machine learning detects tipping points in complex systems.

A probabilistic framework for online test-time adaptation

New optimizer designs respect symmetry, improving deep learning models.

New method tracks shifts in infinite-armed bandits without prior knowledge.

Bayesian method detects change points in time series data.

New method estimates optimal personalized treatment rules from mixed data sources.

FADE adapts machine learning models to evolving data efficiently.

In this study, we have obtained the distribution parameter of a ruled surface generated by a straight line in Frenet trihedron moving along a timelike curve and also along another curve with the same parameter. At this time, the Frenet frames of these timelike curves are not the same. We have moved the director vector …

In this paper, we define a new type of ruled surface called ruled surface by using the alternative frame of a base curve. Then, we study its differential geometric properties such as striction line, distribution parameter, fundamental forms, Gaussian and mean curvatures. Moreover, we find geodesic curvatures, normal cu…

New method encodes function preferences into neural nets for better generalization.