arXiv subjects

Yizhuang You

Publications and source records attributed to Yizhuang You.

3 recordsLinked to original sources

arXiv2022

Categorical Representation Learning and RG flow operators for algorithmic classifiers

Following the earlier formalism of the categorical representation learning (arXiv:2103.14770) by the first two authors, we discuss the construction of the "RG-flow based categorifier". Borrowing ideas from theory of renormalization group flows (RG) in quantum field theory, holographic duality, and hyperbolic geometry, and mixing them with neural ODE's, we construct a new algorithmic natural language processing (NLP) architecture, called the RG-flow categorifier or for short the RG categorifier, which is capable of data classification and generation in all layers. We apply our algorithmic platform to biomedical data sets and show its performance in the field of sequence-to-function mapping. In particular we apply the RG categorifier to particular genomic sequences of flu viruses and show how our technology is capable of extracting the information from given genomic sequences, find their hidden symmetries and dominant features, classify them and use the trained data to make stochastic prediction of new plausible generated sequences associated with new set of viruses which could avoid the human immune system. The content of the current article is part of the recent US patent application submitted by first two authors (U.S. Patent Application No.: 63/313.504).

cs.LG↗

arXiv2021

Categorical Representation Learning: Morphism is All You Need

We provide a construction for categorical representation learning and introduce the foundations of "$\textit{categorifier}$". The central theme in representation learning is the idea of $\textbf{everything to vector}$. Every object in a dataset $\mathcal{S}$ can be represented as a vector in $\mathbb{R}^n$ by an $\textit{encoding map}$ $E: \mathcal{O}bj(\mathcal{S})\to\mathbb{R}^n$. More importantly, every morphism can be represented as a matrix $E: \mathcal{H}om(\mathcal{S})\to\mathbb{R}^{n}_{n}$. The encoding map $E$ is generally modeled by a $\textit{deep neural network}$. The goal of representation learning is to design appropriate tasks on the dataset to train the encoding map (assuming that an encoding is optimal if it universally optimizes the performance on various tasks). However, the latter is still a $\textit{set-theoretic}$ approach. The goal of the current article is to promote the representation learning to a new level via a $\textit{category-theoretic}$ approach. As a proof of concept, we provide an example of a text translator equipped with our technology, showing that our categorical learning model outperforms the current deep learning models by 17 times. The content of the current article is part of the recent US patent proposal (patent application number: 63110906).

cs.LG↗

arXiv2012

Evolution from unconventional spin density wave to superconductivity and a novel gap-like phase in NaFe1-xCoxAs

Similar to the cuprate high TC superconductors, the iron pnictide superconductors also lie in close proximity to a magnetically ordered phase. A central debate concerning the superconducting mechanism is whether the local magnetic moments play an indispensable role or the itinerant electron description is sufficient. A key step for resolving this issue is to acquire a comprehensive picture regarding the nature of various phases and interactions in the iron compounds. Here we report the doping, temperature, and spatial evolutions of the electronic structure of NaFe1-xCoxAs studied by scanning tunneling microscopy. The spin density wave gap in the parent state is observed for the first time, which shows a strongly asymmetric lineshape that is incompatible with the conventional Fermi surface nesting scenario. The optimally doped sample exhibits a single, symmetric energy gap, but in the overdoped regime another asymmetric gap-like feature emerges near the Fermi level. This novel gap-like phase coexists with superconductivity in the ground state, persists deep into the normal state, and shows strong spatial variations. The characteristics of the three distinct low energy states, in conjunction with the peculiar high energy spectra, suggest that the coupling between the local moments and itinerant electrons is the fundamental driving force for the phases and phase transitions in the iron pnictides.

cond-mat.supr-con↗