Search Results for author: Tianyi Liu

Found 28 papers, 5 papers with code

Joint Sparse Estimation with Cardinality Constraint via Mixed-Integer Semidefinite Programming

no code implementations6 Nov 2023 Tianyi Liu, Frederic Matter, Alexander Sorg, Marc E. Pfetsch, Martin Haardt, Marius Pesavento

To further reduce the computation time in such scenarios, a relaxation-based approach can be employed to obtain an approximate solution of the MISDP reformulation, at the expense of a reduced estimation performance.

LEMON: Lossless model expansion

no code implementations12 Oct 2023 Yite Wang, Jiahao Su, Hanlin Lu, Cong Xie, Tianyi Liu, Jianbo Yuan, Haibin Lin, Ruoyu Sun, Hongxia Yang

Our empirical results demonstrate that LEMON reduces computational costs by 56. 7% for Vision Transformers and 33. 2% for BERT when compared to training from scratch.

Let Models Speak Ciphers: Multiagent Debate through Embeddings

no code implementations10 Oct 2023 Chau Pham, Boyi Liu, Yingxiang Yang, Zhengyu Chen, Tianyi Liu, Jianbo Yuan, Bryan A. Plummer, Zhaoran Wang, Hongxia Yang

Although natural language is an obvious choice for communication due to LLM's language understanding capability, the token sampling step needed when generating natural language poses a potential risk of information loss, as it uses only one token to represent the model's belief across the entire vocabulary.

Bitstream-Corrupted Video Recovery: A Novel Benchmark Dataset and Method

1 code implementation NeurIPS 2023 Tianyi Liu, Kejun Wu, Yi Wang, Wenyang Liu, Kim-Hui Yap, Lap-Pui Chau

The past decade has witnessed great strides in video recovery by specialist technologies, like video inpainting, completion, and error concealment.

Video Inpainting

Taxonomy-Structured Domain Adaptation

1 code implementation13 Jun 2023 Tianyi Liu, Zihao Xu, Hao He, Guang-Yuan Hao, Guang-He Lee, Hao Wang

Domain adaptation aims to mitigate distribution shifts among different domains.

Domain Adaptation

Machine Learning Force Fields with Data Cost Aware Training

1 code implementation5 Jun 2023 Alexander Bukharin, Tianyi Liu, Shengjie Wang, Simiao Zuo, Weihao Gao, Wen Yan, Tuo Zhao

To address this issue, we propose a multi-stage computational framework -- ASTEROID, which lowers the data cost of MLFFs by leveraging a combination of cheap inaccurate data and expensive accurate data.

Label Inference Attack against Split Learning under Regression Setting

1 code implementation18 Jan 2023 Shangyu Xie, Xin Yang, Yuanshun Yao, Tianyi Liu, Taiqing Wang, Jiankai Sun

In this work, we step further to study the leakage in the scenario of the regression model, where the private labels are continuous numbers (instead of discrete labels in classification).

Federated Learning Inference Attack +1

UGformer for Robust Left Atrium and Scar Segmentation Across Scanners

no code implementations11 Oct 2022 Tianyi Liu, Size Hou, Jiayuan Zhu, Zilong Zhao, Haochuan Jiang

an enhanced transformer module with deformable convolutions to improve the blending of the transformer information with convolutional information and help predict irregular LAs and scar shapes.

Domain Generalization Image Segmentation +2

Differentially Private Estimation of Hawkes Process

no code implementations15 Sep 2022 Simiao Zuo, Tianyi Liu, Tuo Zhao, Hongyuan Zha

Point process models are of great importance in real world applications.

Differentially Private Multi-Party Data Release for Linear Regression

no code implementations16 Jun 2022 Ruihan Wu, Xin Yang, Yuanshun Yao, Jiankai Sun, Tianyi Liu, Kilian Q. Weinberger, Chong Wang

Differentially Private (DP) data release is a promising technique to disseminate data without compromising the privacy of data subjects.

regression

Tag-assisted Multimodal Sentiment Analysis under Uncertain Missing Modalities

1 code implementation28 Apr 2022 Jiandian Zeng, Tianyi Liu, Jiantao Zhou

Specifically, we design a tag encoding module to cover both the single modality and multiple modalities missing cases, so as to guide the network's attention to those missing modalities.

Multimodal Sentiment Analysis Sentiment Classification +1

Noise Regularizes Over-parameterized Rank One Matrix Recovery, Provably

no code implementations7 Feb 2022 Tianyi Liu, Yan Li, Enlu Zhou, Tuo Zhao

We investigate the role of noise in optimization algorithms for learning over-parameterized models.

Unified Multimodal Pre-training and Prompt-based Tuning for Vision-Language Understanding and Generation

no code implementations10 Dec 2021 Tianyi Liu, Zuxuan Wu, Wenhan Xiong, Jingjing Chen, Yu-Gang Jiang

Our experiments show that there is a trade-off between understanding tasks and generation tasks while using the same model, and a feasible way to improve both tasks is to use more data.

Image-text matching Language Modelling +8

Extended Successive Convex Approximation for Phase Retrieval with Dictionary Learning

no code implementations13 Sep 2021 Tianyi Liu, Andreas M. Tillmann, Yang Yang, Yonina C. Eldar, Marius Pesavento

The second algorithm, referred to as SCAphase, uses auxiliary variables and is favorable in the case of highly diverse mixture models.

Dictionary Learning Retrieval

Recovery under Side Constraints

no code implementations17 Jun 2021 Khaled Ardah, Martin Haardt, Tianyi Liu, Frederic Matter, Marius Pesavento, Marc E. Pfetsch

Finally, we address the measurement system design for linear and nonlinear measurements of sparse signals.

Dictionary Learning Retrieval

Noisy Gradient Descent Converges to Flat Minima for Nonconvex Matrix Factorization

no code implementations24 Feb 2021 Tianyi Liu, Yan Li, Song Wei, Enlu Zhou, Tuo Zhao

Numerous empirical evidences have corroborated the importance of noise in nonconvex optimization problems.

Regularized Attentive Capsule Network for Overlapped Relation Extraction

no code implementations COLING 2020 Tianyi Liu, Xiangyu Lin, Weijia Jia, Mingliang Zhou, Wei Zhao

Distantly supervised relation extraction has been widely applied in knowledge base construction due to its less requirement of human efforts.

Relation Relation Extraction +1

Towards Understanding the Importance of Shortcut Connections in Residual Networks

no code implementations NeurIPS 2019 Tianyi Liu, Minshuo Chen, Mo Zhou, Simon S. Du, Enlu Zhou, Tuo Zhao

We show, however, that gradient descent combined with proper normalization, avoids being trapped by the spurious local optimum, and converges to a global optimum in polynomial time, when the weight of the first layer is initialized at 0, and that of the second layer is initialized arbitrarily in a ball.

Towards Understanding the Importance of Noise in Training Neural Networks

no code implementations7 Sep 2019 Mo Zhou, Tianyi Liu, Yan Li, Dachao Lin, Enlu Zhou, Tuo Zhao

Numerous empirical evidence has corroborated that the noise plays a crucial rule in effective and efficient training of neural networks.

Improving Abstractive Document Summarization with Salient Information Modeling

no code implementations ACL 2019 Yongjian You, Weijia Jia, Tianyi Liu, Wenmian Yang

Comprehensive document encoding and salient information selection are two major difficulties for generating summaries with adequate salient information.

Document Summarization

Neural Relation Extraction via Inner-Sentence Noise Reduction and Transfer Learning

no code implementations EMNLP 2018 Tianyi Liu, Xinsong Zhang, Wanhao Zhou, Weijia Jia

Extracting relations is critical for knowledge base completion and construction in which distant supervised methods are widely used to extract relational facts automatically with the existing knowledge bases.

Knowledge Base Completion Relation +3

Towards Understanding Acceleration Tradeoff between Momentum and Asynchrony in Nonconvex Stochastic Optimization

no code implementations NeurIPS 2018 Tianyi Liu, Shiyang Li, Jianping Shi, Enlu Zhou, Tuo Zhao

Asynchronous momentum stochastic gradient descent algorithms (Async-MSGD) is one of the most popular algorithms in distributed machine learning.

Stochastic Optimization

A Diffusion Approximation Theory of Momentum SGD in Nonconvex Optimization

no code implementations14 Feb 2018 Tianyi Liu, Zhehui Chen, Enlu Zhou, Tuo Zhao

Our theoretical discovery partially corroborates the empirical success of MSGD in training deep neural networks.

Bayesian Inference Dimensionality Reduction +1

Implementation of Training Convolutional Neural Networks

no code implementations3 Jun 2015 Tianyi Liu, Shuangsang Fang, Yuehui Zhao, Peng Wang, Jun Zhang

Deep learning refers to the shining branch of machine learning that is based on learning levels of representations.

BIG-bench Machine Learning Face Recognition

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