Develops support theorem for analytic transforms in tomography.
problem Analytic wave front set resolution for integral transforms.
method Microlocal analysis, double fibration framework, wave packet transforms.
result Uniqueness and support theorems for analytic transforms.
UGformer uses transformers to learn graph representations.
problem Graph representation learning for various tasks.
method UGformer is a transformer-based GNN model that samples or considers all neighbors for each node.
result UGformer achieves state-of-the-art accuracy on graph classification and text classification tasks.
The complexity of a learning task is increased by transformations in the input space that preserve class identity. Visual object recognition for example is affected by changes in viewpoint, scale, illumination or planar transformations. While drastically altering the visual appearance, these changes are orthogonal to r…
New transforms improve signal classification and data analysis.
problem Improving signal classification and data analysis.
method Algebraic generative models and transport transforms.
result Classes of signals are transformed into convex sets, simplifying classification.
Transformation models are a very important tool for applied statisticians and econometricians. In many applications, the dependent variable is transformed so that homogeneity or normal distribution of the error holds. In this paper, we analyze transformation models in a high-dimensional setting, where the set of potent…
The visibility transformation embeds data position into signature features for efficient pattern recognition.
problem Embedding absolute position into signature features for efficient pattern recognition.
method The visibility transformation is put on a theoretical footing and used to embed absolute position into signature features efficiently.
result The generated feature set simplifies pattern recognition by accommodating nonlinear functions of absolute and relative values.
New neural network learns relevant transformations in data, improving object recognition.
problem Current equivariant architectures consider all possible transformations, ignoring relevant ones.
method Co-attentive equivariant neural networks that focus on co-occurring transformations.
result Outperforms conventional equivariant networks on rotated MNIST and CIFAR-10.
Transformers show better in-context learning resilience under distribution shifts than simple MLPs.
problem Understanding in-context learning under varying distribution shifts.
method Comparing transformers and set-based MLPs on linear regression tasks.
result Transformers better emulate OLS performance and exhibit better resilience to mild distribution shifts.
We interpret the setting for a Radon transform as a submanifold of the space of generalized functions, and compute its extrinsic curvature: it is the Hessian composed with the Radon transform.
Transformers excel at sparse token selection, surpassing FCNs in both worst and average cases.
problem Sparse token selection task
method One-layer transformer trained with gradient descent
result Transformers learn sparse token selection and exhibit strong out-of-distribution length generalization
New insights into how data transformations affect self-supervised clustering.
problem Impact of data transformations on self-supervised clustering convergence.
method Theoretical and empirical analysis of various data transformations.
result Certain transformations help in faster convergence of self-supervised clustering.
A novel transformer model improves classification of partially ordered sequences.
problem Classification of partially ordered sequences with uncertainty in timestamps.
method Developed a transformer-based model for partially ordered sequences, benchmarked against set models.
result Transformer-based model outperforms set models on three datasets.
StrokeCoder uses Transformers to generate images from single examples.
problem Creating diverse images from a single example.
method Transformer Neural Network learns from a single path-based example to generate a set of images.
result The model can generate a large set of deviated images that still represent the original image's style and concept.
New Kelvin transform for anisotropic elliptic problems.
problem Semilinear and quasilinear anisotropic elliptic problems.
method Introducing a new Kelvin-type transform in the anisotropic setting.
result New insights into anisotropic elliptic problems.
The paper examines how nonlinear transformations affect ridge sets in manifold learning.
problem Understanding the impact of nonlinear transformations on ridge sets in manifold learning.
method Examined the effects of nonlinear transformations on ridge sets using mathematical proofs and numerical experiments.
result The inclusion relationship $\cR(f\circ p)\subseteq \cR(p)$ holds for strictly increasing and concave transformations, and the Hausdorff distance between transformed and non-transformed ridge sets is smaller.
We analyze Darboux transformations in very general settings for multidimensional linear partial differential operators. We consider all known types of Darboux transformations, and present a new type. We obtain a full classification of all operators that admit Wronskian type Darboux transformations of first order and a …
Transformers trained on random classification tasks generalize well and can overfit without error.
problem Understanding how transformers generalize and overfit in-context.
method Analysis of implicit regularization during gradient descent training.
result Transformers can overfit without error and still generalize well.
ST-BCP narrows the coverage gap in BCP by transforming nonconformity scores.
problem The looseness in BCP's coverage guarantee due to Markov's inequality.
method Introduces a data-dependent transformation of nonconformity scores.
result Reduces the average coverage gap from 4.20% to 1.12% on benchmarks.
Random Transformers behave like polynomial models in ICL with asymptotic growth.
problem Understanding in-context learning capabilities of pretrained Transformers.
method Asymptotic analysis of a random Transformer with a fixed first layer and a trained second layer, considering growth in context length, input dimension, hidden dimension, and training parameters.
result The random Transformer's ICL error is equivalent to a finite-degree Hermite polynomial model.
For smooth compact connected manifolds with strictly convex boundary, no conjugate points and a hyperbolic trapped set, we prove an equivalence principle concerning the injectivity of the X-ray transform Im on symmetric solenoidal tensors and the surjectivity of an operator πm∗ on the set of solenoidal tensors…
Transformers can learn optimal regression mixtures efficiently.
problem Limited adoption of tailored regression methods due to their model-specific nature.
method Constructed a generative process for a mixture of linear regressions and used transformers to learn optimal predictors.
result Transformers achieve low mean-squared error and make predictions close to the optimal procedure.
Transformers can simulate MLE for Bayesian network sequences.
problem Understanding transformers' capabilities in Bayesian network sequence generation.
method In-context maximum likelihood estimation (MLE) for autoregressive sequence generation.
result A simple transformer model can estimate Bayesian network probabilities and generate new samples.
Algorithm finds optimal affine transformation to minimize overall distortion.
problem Minimizing distortion in affine transformations.
method Riemannian geometry approach to define and minimize distortion.
result Mean distorting transformation found for minimizing overall distortion.
LLT transforms time series features based on linear laws.
problem Classifying univariate and multivariate time series.
method Time-delay embedding, spectral decomposition, and feature transformation.
result Transformed features improve classification accuracy.
New algebraic-geometry method for Ribaucour transformations.
problem Classical differential geometry problems.
method Algebraic-geometry approach to constructing orthogonal nets.
result Obtains smooth orthogonal nets as Ribaucour transformations.
Efficient algorithms find optimal monotone transforms for calibration under strictly convex losses.
problem Calibrating estimations to improve performance with monotone transforms.
method Proposed linear-time and space algorithm for finding optimal monotone transforms for specific loss functions. Also proposed an anytime algorithm with linear space and pseudo-linearithmic time complexity.
result Optimal monotone transforms are unique and can be found efficiently for various strictly convex loss functions.
Joint alignment of a collection of functions is the process of independently transforming the functions so that they appear more similar to each other. Typically, such unsupervised alignment algorithms fail when presented with complex data sets arising from multiple modalities or make restrictive assumptions about the …
This paper explains how model invariance improves generalization using data transformations.
problem Understanding why model invariance leads to better generalization performance.
method Introducing sample cover induced by transformations and refining generalization bounds.
result The sample covering number can be used to evaluate and select suitable data transformations.
The characteristics (or numerical patterns) of a feature vector in the transform domain of a perturbation model differ significantly from those of its corresponding feature vector in the input domain. These differences - caused by the perturbation techniques used for the transformation of feature patterns - degrade the…
We propose a method for building an interpretable recommender system for personalizing online content and promotions. Historical data available for the system consists of customer features, provided content (promotions), and user responses. Unlike in a standard multi-class classification setting, misclassification cost…
We investigate geometric aspects of the the Bäcklund transform of principal contact element nets. A Bäcklund transform exists if and only if it the principal contact element net is of constant negative Gaussian curvature (a pseudosphere). We describe an elementary construction of the Bäcklund transform and prove its co…
Lower bounds set for infinite-precision transformers.
problem Understanding limitations of infinite-precision transformers.
method Used VC dimension technique to prove lower bounds.
result First lower bounds for two tasks: function composition and SUM2. Study shows stability in X-ray transform on specific hyperbolic manifolds.
problem Stability of X-ray transform on asymptotically hyperbolic manifolds.
method Constructed a parametrix for the normal operator in 0-pseudodifferential calculus.
result Showed a stability estimate for the X-ray transform.
New insights into X-ray transform on hyperbolic disk, with functional relations and range characterizations.
problem Understanding the X-ray transform on hyperbolic geometry.
method Derived new singular value decompositions, range characterizations, and intertwining relations with wedge-type differential operators.
result Sharp understanding of boundary behavior and invertibility settings for the X-ray transform.
Transforms uniquely determine Higgs fields on real-analytic manifolds.
problem Determining Higgs fields from transforms on manifolds.
method Matrix-weighted real-analytic double fibration transforms.
result Higgs fields can be uniquely determined from transforms.
Transformers learn to play games in-context, proving Nash equilibrium.
problem Understanding in-context game-playing capabilities of pre-trained transformers.
method Theoretical guarantees and constructional results for transformer architecture in multi-agent games.
result Pre-trained transformers can learn Nash equilibrium in-context for two-player zero-sum games.
Using the gauge theoretic approach for Lie applicable surfaces, we characterise certain subclasses of surfaces in terms of polynomial conserved quantities. These include isothermic and Guichard surfaces of conformal geometry and L-isothermic surfaces of Laguerre geometry. In this setting one can see that the well kno…
Transformers improve Finnish language modeling, achieving lower perplexity scores.
problem Improving language modeling for Finnish using deep learning models.
method Used BERT and Transformer-XL models in a sub-word setting, compared to LSTM.
result Transformer-XL outperforms LSTM, achieving a 27% better perplexity score.
SPTN uses invertible transformations to improve sum-product networks.
problem Improving inference efficiency and tractability in sum-product networks.
method Integrates invertible transformations into sum-product networks (SPNs).
result SPTNs with Gaussian leaves and affine transformations are as tractable as SPNs.
The paper explores geometric aspects of Miura transformations in integrable systems.
problem Relating different integrable equations and classifying bi-Hamiltonian structures.
method Construction of generalized Miura transformations under algebraic and geometric settings.
result Miura transformations relate integrable curve flows in different geometries and induce moving frame transitions.
The paper offers generalization bounds for Transformers that ignore sequence length.
problem Developing generalization bounds for Transformers that are independent of sequence length.
method Covering number approach to upper bound Rademacher complexity of bounded linear transformations.
result Theoretical bounds for Transformer generalization are independent of sequence length.
Microlocal analysis provides deep insight into singularity structures and is often crucial for solving inverse problems, predominately, in imaging sciences. Of particular importance is the analysis of wavefront sets and the correct extraction of those. In this paper, we introduce the first algorithmic approach to extra…
A method uses ITD and XGBoost for precise power transformer fault diagnosis.
problem Fault diagnosis of power transformers using DGA data.
method Ranking DGA parameters by skewness, extracting ITD features, and using an XGBoost classifier.
result The method achieves over 95% accuracy in classification.
Transformers solve Poisson means estimation via empirical Bayes.
problem Estimating Poisson means under empirical Bayes setting.
method Pre-trained transformer learns to adapt to unknown prior and do in-context learning.
result Transformers achieve vanishing regret with large models and outperform classical algorithms.
Transformers achieve near-optimal dynamic regret in non-stationary reinforcement learning.
problem Understanding and handling non-stationary environments in reinforcement learning.
method Demonstrated that transformers can achieve nearly optimal dynamic regret bounds in non-stationary settings.
result Transformers can approximate and learn strategies for non-stationary environments, matching or outperforming existing expert algorithms.
We show a perturbation result for the boundedness of the Riesz transform : if M and M0 are complete Riemannian manifolds satisfying a Sobolev inequality of dimension n, which are isometric outside a compact set, and if the Riesz transform on M0 is bounded on Lq, then for all $\frac{n}{n-2}, the Riesz trans…
Paper explores EEG-based speech recognition using transformers, showing faster training and better performance for smaller vocabularies.
problem Continuous speech recognition using EEG features.
method Transformer-based ASR model compared to RNN-based models.
result Transformer models perform better for smaller vocabularies but RNN models outperform them for larger vocabularies.
We study ray transforms on spherically symmetric manifolds with a piecewise C1,1 metric. Assuming the Herglotz condition, the X-ray transform is injective on the space of L2 functions on such manifolds. We also prove injectivity results for broken ray transforms (with and without periodicity) on such manifolds …