Search Results for author: Yihong Gu

Found 10 papers, 4 papers with code

Causality Pursuit from Heterogeneous Environments via Neural Adversarial Invariance Learning

no code implementations7 May 2024 Yihong Gu, Cong Fang, Peter Bühlmann, Jianqing Fan

As illustrated by the unified non-asymptotic analysis, our adversarial estimation framework can attain provable sample-efficient estimation akin to standard regression under a minimal identification condition for various tasks and models.

The Implicit Bias of Heterogeneity towards Invariance and Causality

no code implementations3 Mar 2024 Yang Xu, Yihong Gu, Cong Fang

It is observed empirically that the large language models (LLM), trained with a variant of regression loss using numerous corpus from the Internet, can unveil causal associations to some extent.

Causal Inference regression

Environment Invariant Linear Least Squares

no code implementations6 Mar 2023 Jianqing Fan, Cong Fang, Yihong Gu, Tong Zhang

To the best of our knowledge, this paper is the first to realize statistically efficient invariance learning in the general linear model.

Causal Inference regression +2

How do noise tails impact on deep ReLU networks?

no code implementations20 Mar 2022 Jianqing Fan, Yihong Gu, Wen-Xin Zhou

This paper investigates the stability of deep ReLU neural networks for nonparametric regression under the assumption that the noise has only a finite p-th moment.


How to Characterize The Landscape of Overparameterized Convolutional Neural Networks

1 code implementation NeurIPS 2020 Yihong Gu, Weizhong Zhang, Cong Fang, Jason D. Lee, Tong Zhang

With the help of a new technique called {\it neural network grafting}, we demonstrate that even during the entire training process, feature distributions of differently initialized networks remain similar at each layer.

Convex Formulation of Overparameterized Deep Neural Networks

no code implementations18 Nov 2019 Cong Fang, Yihong Gu, Weizhong Zhang, Tong Zhang

This new analysis is consistent with empirical observations that deep neural networks are capable of learning efficient feature representations.

Domain Adaptive Imitation Learning

1 code implementation ICML 2020 Kuno Kim, Yihong Gu, Jiaming Song, Shengjia Zhao, Stefano Ermon

We formalize the Domain Adaptive Imitation Learning (DAIL) problem, which is a unified framework for imitation learning in the presence of viewpoint, embodiment, and dynamics mismatch.

Imitation Learning

Cross Domain Imitation Learning

no code implementations25 Sep 2019 Kun Ho Kim, Yihong Gu, Jiaming Song, Shengjia Zhao, Stefano Ermon

Informally, CDIL is the process of learning how to perform a task optimally, given demonstrations of the task in a distinct domain.

Imitation Learning

Language Modeling with Sparse Product of Sememe Experts

1 code implementation EMNLP 2018 Yihong Gu, Jun Yan, Hao Zhu, Zhiyuan Liu, Ruobing Xie, Maosong Sun, Fen Lin, Leyu Lin

Most language modeling methods rely on large-scale data to statistically learn the sequential patterns of words.

Language Modelling

ZhuSuan: A Library for Bayesian Deep Learning

1 code implementation18 Sep 2017 Jiaxin Shi, Jianfei Chen, Jun Zhu, Shengyang Sun, Yucen Luo, Yihong Gu, Yuhao Zhou

In this paper we introduce ZhuSuan, a python probabilistic programming library for Bayesian deep learning, which conjoins the complimentary advantages of Bayesian methods and deep learning.

Probabilistic Programming regression

Cannot find the paper you are looking for? You can Submit a new open access paper.