Related papers: Structural Analysis of Vector Autoregressive Model…

Large language models (LLMs) based on transformer architectures are typically described through collections of architectural components and training procedures, obscuring their underlying computational structure. This review article…

Autoregressive language models are powerful and relatively easy to train. However, these models are usually trained without explicit conditioning labels and do not offer easy ways to control global aspects such as sentiment or topic during…

We study the problem of self-supervised structured representation learning using autoencoders for downstream tasks such as generative modeling. Unlike most methods which rely on matching an arbitrary, relatively unstructured, prior…

Coherence is an important aspect of text quality, and various approaches have been applied to coherence modeling. However, existing methods solely focus on a single document's coherence patterns, ignoring the underlying correlation between…

The fundamental purpose of the present research article is to introduce the basic principles of Dimensional Analysis in the context of the neoclassical economic theory, in order to apply such principles to the fundamental relations that…

Time series models aim for accurate predictions of the future given the past, where the forecasts are used for important downstream tasks like business decision making. In practice, deep learning based time series models come in many forms,…

The mainstream of data-driven abstractive summarization models tends to explore the correlations rather than the causal relationships. Among such correlations, there can be spurious ones which suffer from the language prior learned from the…

We develop a Functional Augmented Vector Autoregression (FunVAR) model to explicitly incorporate firm-level heterogeneity observed in more than one dimension and study its interaction with aggregate macroeconomic fluctuations. Our…

This article discuss a class of tractable model in the form of polynomial type.

Causal analyses of longitudinal data generally assume that the qualitative causal structure relating variables remains invariant over time. In structured systems that transition between qualitatively different states in discrete time steps,…

We describe a basic correspondence between linear algebraic structures within vector embeddings in artificial neural networks and conditional independence constraints on the probability distributions modeled by these networks. Our framework…

We introduce a method for learning the dynamics of complex nonlinear systems based on deep generative models over temporal segments of states and actions. Unlike dynamics models that operate over individual discrete timesteps, we learn the…

This paper provides an ablation-based analysis of latent autoregression in GP-VAE models, building upon our previous work introducing the architecture. Language models typically rely on an autoregressive factorization over tokens. In…

We propose a regularized factor-augmented vector autoregressive (FAVAR) model that allows for sparsity in the factor loadings. In this framework, factors may only load on a subset of variables which simplifies the factor identification and…

These informal notes discuss a few basic notions and examples, with emphasis on constructions that may be relevant for analysis on metric spaces.

These are lecture notes for the course "Analysis and X-ray tomography". The course is a broad overview of various tools in analysis that can be used to study X-ray tomography. The focus is on tools and ideas, not so much on technical…

Deep structured models are widely used for tasks like semantic segmentation, where explicit correlations between variables provide important prior information which generally helps to reduce the data needs of deep nets. However, current…

This paper presents an approach of modeling variability of automotive system architectures using function nets, views and feature diagrams. A function net models an architecture hierarchically and views are used to omit parts of such a…

Compositional vector space models of meaning promise new solutions to stubborn language understanding problems. This paper makes two contributions toward this end: (i) it uses automatically-extracted paraphrase examples as a source of…

This is a set of lecture notes on the operator algebraic approach to 2-dimensional conformal field theory. Representation theoretic aspects and connections to vertex operator algebras are emphasized. No knowledge on operator algebras or…