相关论文: Labeled and Non-labeled Extended Rauzy Classes

Federated Learning (FL) aims to train a machine learning (ML) model in a distributed fashion to strengthen data privacy with limited data migration costs. It is a distributed learning framework naturally suitable for privacy-sensitive…

In-context learning (ICL) has revolutionized the capabilities of transformer models in NLP. In our project, we extend the understanding of the mechanisms underpinning ICL by exploring whether transformers can learn from sequential,…

Potential equivalence transformations (PETs) are effectively applied to a class of nonlinear diffusion-convection equations. For this class all possible potential symmetries are classified and a theorem on connection of them with point ones…

We produce affine interval exchange transformations (AIETs) which are topologically conjugated to (standard) interval exchange maps (IETs) via a singular conjugacy, i.e. a diffeomorphism $h$ of $[0,1]$ which is $C^0$ but not $C^1$ and such…

Several methods have recently been developed for joint structure learning of multiple (related) graphical models or networks. These methods treat individual networks as exchangeable, such that each pair of networks are equally encouraged to…

The problem of open-set noisy labels denotes that part of training data have a different label space that does not contain the true class. Lots of approaches, e.g., loss correction and label correction, cannot handle such open-set noisy…

A standard interval exchange map is a one-to-one map of the interval which is locally a translation except at finitely many singularities. We define for such maps, in terms of the Rauzy-Veech continuous fraction algorithm, a diophantine…

In standard classification, we typically treat class categories as independent of one-another. In many problems, however, we would be neglecting the natural relations that exist between categories, which are often dictated by an underlying…

An interval translation map (ITM) is a map $T \colon I \to I$ defined as a piecewise translation on a finite partition of an interval $I$ into $r \ge 2$ subintervals. Unlike classical interval exchange transformations (IETs), the images of…

We introduce the calculus of Classical Transitions (CT), which extends the research line on the relationship between linear logic and processes to labelled transitions. The key twist from previous work is registering parallelism in typing…

We study the problem of invariant learning when the environment labels are unknown. We focus on the invariant representation notion when the Bayes optimal conditional label distribution is the same across different environments. Previous…

The Euler Characteristic Transform (ECT) has proven to be a powerful representation, combining geometrical and topological characteristics of shapes and graphs. However, the ECT was hitherto unable to learn task-specific representations. We…

This paper proposes a new evaluation protocol for cross-media retrieval which better fits the real-word applications. Both image-text and text-image retrieval modes are considered. Traditionally, class labels in the training and testing…

For irreducible interval exchange transformations, we study the relation between the powers of induced map and the induced maps of powers and raise a condition of equivalence between them. And skew production of Rauzy induction map is set…

We discuss the classical statement of group classification problem and some its extensions in the general case. After that, we carry out the complete extended group classification for a class of (1+1)-dimensional nonlinear…

In this paper, we study the classification problem in which we have access to easily obtainable surrogate for true labels, namely complementary labels, which specify classes that observations do \textbf{not} belong to. Let $Y$ and $\bar{Y}$…

Prior works in cross-lingual named entity recognition (NER) with no/little labeled data fall into two primary categories: model transfer based and data transfer based methods. In this paper we find that both method types can complement each…

We present the first explicit example of an interval exchange transformation with flips (FIET) possessing three distinct invariant ergodic measures. The proof is based on a generalization of M. Keane's method, using the Rauzy induction…

We present two rewriting systems that define labelled explicit substitution lambda-calculi. Our work is motivated by the close correspondence between Levy's labelled lambda-calculus and paths in proof-nets, which played an important role in…

Specialized transformer-based models for encoding tabular data have gained interest in academia. Although tabular data is omnipresent in industry, applications of table transformers are still missing. In this paper, we study how these…