Publications | Xiaohan Chen's Homepage

Hyperparameter Tuning is All You Need for LISTA

Learned Iterative Shrinkage-Thresholding Algorithm (LISTA) introduces the concept of unfolding an iterative algorithm and trains it …

*X. Chen, *J. Liu, Z. Wang, W. Yin

The Elastic Lottery Ticket Hypothesis

Lottery Ticket Hypothesis (LTH) raises keen attention to identifying sparse trainable subnetworks, or winning tickets, of training, …

X. Chen, Y. Cheng, S. Wang, Z. Gan, J. Liu, Z. Wang

Preprint PDF Code

Sparse Training via Boosting Pruning Plasticity with Neuroregeneration

Works on lottery ticket hypothesis (LTH) and single-shot network pruning (SNIP) have raised a lot of attention currently on …

S. Liu, T. Chen, X. Chen, Z. Atashgahi, L. Yin, H. Kou, L. Shen, M. Pechenizkiy, Z. Wang, D. M. Mocanu

Sanity Checks for Lottery Tickets: Does Your Winning Ticket Really Win the Jackpot?

There have been long-standing controversies and inconsistencies over the experiment setup and criteria for identifying the …

X. Ma, G. Yuan, X. Shen, T. Chen, X. Chen, X. Chen, N. Liu, M. Qin, S. Liu, Z. Wang, Y. Wang

EarlyBERT: Efficient BERT Training via Early-bird Lottery Tickets

Heavily overparameterized language models such as BERT, XLNet and T5 have achieved impressive success in many NLP tasks. However, their …

X. Chen, Y. Cheng, S. Wang, Z. Gan, Z. Wang, J. Liu

Preprint PDF Code Slides

Learning to Optimize: A Primer and A Benchmark

Learning to optimize (L2O) is an emerging approach that leverages machine learning to develop optimization methods, aiming at reducing …

T. Chen, X. Chen, W. Chen, H. Heaton, J. Liu, Z. Wang, W. Yin

Preprint PDF Code

A Design Space Study for LISTA and Beyond

In recent years, great success has been witnessed in building problem-specific deep networks from unrolling iterative algorithms, for …

*T. Meng, *X. Chen, Y. Jiang, Z. Wang

Project

Learning A Minimax Optimizer: A Pilot Study

Solving continuous minimax optimization is of extensive practical interest, yet notoriously unstable and difficult. This paper …

*J. Shen, *X. Chen, H. Heaton, T. Chen, J. Liu, Z. Wang, Y. Lin

Project

SmartDeal: Re-Modeling Deep Network Weights for Efficient Inference and Training

The record-breaking performance of deep neural networks (DNNs) comes with heavy parameterization, leading to external dynamic …

*X. Chen, *Y. Zhao, Y. Wang, P. Xu, H. You, C. Li, Y. Fu, Y. Lin, Z. Wang

ShiftAddNet: A Hardware-Inspired Deep Network

Multiplication (e.g., convolution) is arguably a cornerstone of modern deep neural networks (DNNs). However, intensive multiplications …

H. You, X. Chen, Y. Zhang, C. Li, S. Li, Z. Liu, Z. Wang, Y. Lin

MATE: Plugging in Model Awareness to Task Embedding for Meta Learning

Meta-learning improves generalization of machine learning models when faced with previously unseen tasks by leveraging experiences from …

X. Chen, Z. Wang, S. Tang, K. Muandet

Safeguarded Learned Convex Optimization

Many applications require repeatedly solving a certain type of optimization problem, eachtime with new (but similar) data. Data-driven …

H. Heaton, X. Chen, Z. Wang, W. Yin

Preprint

Uncertainty Quantification for Deep Context-Aware Mobile Activity Recognition and Unknown Context Discovery

Activity recognition in wearable computing faces two key challenges: i) activity characteristics may be context-dependent and change …

Z. Huo, A. Pakbin, X. Chen, N. Hurley, Y. Yuan, X. Qian, Z. Wang, S. Huang, B. Mortazavi

SmartExchange: Trading Higher-cost Memory Storage/Access for Lower-cost Computation

We present SmartExchange, a hardware-algorithm co-design framework to trade higher cost memory storage/access for lower cost …

*X. Chen, *Y. Zhao, Y. Wang, C. Li, Y. Xie, Z. Wang, Y. Lin

Drawing Early-Bird Tickets: Toward More Efficient Training of Deep Networks

(Frankle & Carbin, 2019) shows that there exist winning tickets (small but critical subnetworks) for dense, randomly initialized …

H. You, C. Li, P. Xu, Y. Fu, X. Chen, Y. Lin, Z. Wang, R. Baraniuk

Preprint PDF Project

E2-Train: Energy-Efficient Deep Network Training with Data-, Model-, and Algorithm-Level Saving

Convolutional neural networks (CNNs) have been increasingly deployed to Internet of Things (IoT) devices. Hence, many efforts have been …

*X. Chen, *Z. Jiang, *Y. Wang, P. Xu, Y. Zhao, Y. Lin, Z. Wang

Preprint PDF Code Project

Plug-and-Play Methods Provably Converge with Properly Trained Denoisers

E. Ryu, J. Liu, S. Wang, X. Chen, Z. Wang, W. Yin

Preprint PDF Code Project Slides Video

ALISTA: Analytic Weights Are As Good As Learned Weights in LISTA

Deep neural networks based on unfolding an iterative algorithm, for example, LISTA (learned iterative shrinkage thresholding …

*X. Chen, *J. Liu, Z. Wang, W. Yin

PDF Code Project Slides

Theoretical Linear Convergence of Unfolded ISTA and its Practical Weights and Thresholds

In recent years, unfolding iterative algorithms as neural networks has become an empirical success in solving sparse recovery problems. …