b'Tuo Zhao'

research

∙ 09/18/2023

Pivotal Estimation of Linear Discriminant Analysis in High Dimensions

We consider the linear discriminant analysis problem in the high-dimensi...

0 Ethan X. Fang, et al. ∙

research

∙ 09/06/2023

Deep Reinforcement Learning from Hierarchical Weak Preference Feedback

Reward design is a fundamental, yet challenging aspect of practical rein...

0 Alexander Bukharin, et al. ∙

research

∙ 07/24/2023

Provable Benefits of Policy Learning from Human Preferences in Contextual Bandit Problems

A crucial task in decision-making problems is reward engineering. It is ...

0 Xiang Ji, et al. ∙

research

∙ 07/04/2023

Nonparametric Classification on Low Dimensional Manifolds using Overparameterized Convolutional Residual Networks

Convolutional residual neural networks (ConvResNets), though overparamet...

0 Kaiqi Zhang, et al. ∙

research

∙ 06/26/2023

Effective Minkowski Dimension of Deep Nonparametric Regression: Function Approximation and Statistical Theories

Existing theories on deep nonparametric regression have shown that when ...

0 Zixuan Zhang, et al. ∙

research

∙ 06/20/2023

LoSparse: Structured Compression of Large Language Models based on Low-Rank and Sparse Approximation

Transformer models have achieved remarkable results in various natural l...

0 Yixiao Li, et al. ∙

research

∙ 03/18/2023

Adaptive Budget Allocation for Parameter-Efficient Fine-Tuning

Fine-tuning large pre-trained language models on downstream tasks has be...

0 Qingru Zhang, et al. ∙

research

∙ 02/25/2023

On Deep Generative Models for Approximation and Estimation of Distributions on Manifolds

Generative networks have experienced great empirical successes in distri...

0 Biraj Dahal, et al. ∙

research

∙ 02/19/2023

HomoDistil: Homotopic Task-Agnostic Distillation of Pre-trained Transformers

Knowledge distillation has been shown to be a powerful model compression...

0 Chen Liang, et al. ∙

research

∙ 02/14/2023

Score Approximation, Estimation and Distribution Recovery of Diffusion Models on Low-Dimensional Data

Diffusion models achieve state-of-the-art performance in various generat...

0 Minshuo Chen, et al. ∙

research

∙ 12/15/2022

Efficient Long Sequence Modeling via State Space Augmented Transformer

Transformer models have achieved superior performance in various natural...

0 Simiao Zuo, et al. ∙

research

∙ 12/01/2022

High Dimensional Binary Classification under Label Shift: Phase Transition and Regularization

Label Shift has been widely believed to be harmful to the generalization...

0 Jiahui Cheng, et al. ∙

research

∙ 10/04/2022

Less is More: Task-aware Layer-wise Distillation for Language Model Compression

Layer-wise distillation is a powerful tool to compress large models (i.e...

0 Chen Liang, et al. ∙

research

∙ 09/21/2022

First-order Policy Optimization for Robust Markov Decision Process

We consider the problem of solving robust Markov decision process (MDP),...

0 Yan Li, et al. ∙

research

∙ 09/15/2022

Context-Aware Query Rewriting for Improving Users' Search Experience on E-commerce Websites

E-commerce queries are often short and ambiguous. Consequently, query un...

0 Simiao Zuo, et al. ∙

research

∙ 09/15/2022

DiP-GNN: Discriminative Pre-Training of Graph Neural Networks

Graph neural network (GNN) pre-training methods have been proposed to en...

0 Simiao Zuo, et al. ∙

research

∙ 09/15/2022

Differentially Private Estimation of Hawkes Process

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

0 Simiao Zuo, et al. ∙

research

∙ 06/25/2022

PLATON: Pruning Large Transformer Models with Upper Confidence Bound of Weight Importance

Large Transformer-based models have exhibited superior performance in va...

0 Qingru Zhang, et al. ∙

research

∙ 06/06/2022

Sample Complexity of Nonparametric Off-Policy Evaluation on Low-Dimensional Manifolds using Deep Networks

We consider the off-policy evaluation problem of reinforcement learning ...

0 Xiang Ji, et al. ∙

research

∙ 05/04/2022

A Manifold Two-Sample Test Study: Integral Probability Metric with Neural Networks

Two-sample tests are important areas aiming to determine whether two col...

1 Jie Wang, et al. ∙

research

∙ 04/15/2022

MoEBERT: from BERT to Mixture-of-Experts via Importance-Guided Adaptation

Pre-trained language models have demonstrated superior performance in va...

0 Simiao Zuo, et al. ∙

research

∙ 04/13/2022

CAMERO: Consistency Regularized Ensemble of Perturbed Language Models with Weight Sharing

Model ensemble is a popular approach to produce a low-variance and well-...

0 Chen Liang, et al. ∙

research

∙ 04/08/2022

CERES: Pretraining of Graph-Conditioned Transformer for Semi-Structured Session Data

User sessions empower many search and recommendation tasks on a daily ba...

0 Rui Feng, et al. ∙

research

∙ 02/07/2022

Noise Regularizes Over-parameterized Rank One Matrix Recovery, Provably

We investigate the role of noise in optimization algorithms for learning...

0 Tianyi Liu, et al. ∙

research

∙ 02/06/2022

No Parameters Left Behind: Sensitivity Guided Adaptive Learning Rate for Training Large Transformer Models

Recent research has shown the existence of significant redundancy in lar...

0 Chen Liang, et al. ∙

research

∙ 01/24/2022

Homotopic Policy Mirror Descent: Policy Convergence, Implicit Regularization, and Improved Sample Complexity

We propose the homotopic policy mirror descent (HPMD) method for solving...

0 Yan Li, et al. ∙

research

∙ 01/15/2022

Block Policy Mirror Descent

In this paper, we present a new class of policy gradient (PG) methods, n...

0 Guanghui Lan, et al. ∙

research

∙ 01/06/2022

Deep Learning Assisted End-to-End Synthesis of mm-Wave Passive Networks with 3D EM Structures: A Study on A Transformer-Based Matching Network

This paper presents a deep learning assisted synthesis approach for dire...

0 Siawpeng Er, et al. ∙

research

∙ 01/01/2022

Deep Nonparametric Estimation of Operators between Infinite Dimensional Spaces

Learning operators between infinitely dimensional spaces is an important...

0 Hao Liu, et al. ∙

research

∙ 12/20/2021

Adaptive Incentive Design with Multi-Agent Meta-Gradient Reinforcement Learning

Critical sectors of human society are progressing toward the adoption of...

0 Jiachen Yang, et al. ∙

research

∙ 10/10/2021

Frequency-aware SGD for Efficient Embedding Learning with Provable Benefits

Embedding learning has found widespread applications in recommendation s...

23 Yan Li, et al. ∙

research

∙ 10/08/2021

Taming Sparsely Activated Transformer with Stochastic Experts

Sparsely activated models (SAMs), such as Mixture-of-Experts (MoE), can ...

2 Simiao Zuo, et al. ∙

research

∙ 10/07/2021

Large Learning Rate Tames Homogeneity: Convergence and Balancing Effect

Recent empirical advances show that training deep models with large lear...

0 Yuqing Wang, et al. ∙

research

∙ 09/15/2021

Self-Training with Differentiable Teacher

Self-training achieves enormous success in various semi-supervised and w...

0 Simiao Zuo, et al. ∙

research

∙ 09/15/2021

ARCH: Efficient Adversarial Regularized Training with Caching

Adversarial regularization can improve model generalization in many natu...

0 Simiao Zuo, et al. ∙

research

∙ 09/07/2021

Besov Function Approximation and Binary Classification on Low-Dimensional Manifolds Using Convolutional Residual Networks

Most of existing statistical theories on deep neural networks have sampl...

0 Hao Liu, et al. ∙

research

∙ 08/19/2021

QUEACO: Borrowing Treasures from Weakly-labeled Behavior Data for Query Attribute Value Extraction

We study the problem of query attribute value extraction, which aims to ...

11 Danqing Zhang, et al. ∙

research

∙ 08/15/2021

Implicit Regularization of Bregman Proximal Point Algorithm and Mirror Descent on Separable Data

Bregman proximal point algorithm (BPPA), as one of the centerpieces in t...

0 Yan Li, et al. ∙

research

∙ 06/16/2021

Named Entity Recognition with Small Strongly Labeled and Large Weakly Labeled Data

Weak supervision has shown promising results in many natural language pr...

17 Haoming Jiang, et al. ∙

research

∙ 05/25/2021

Super Tickets in Pre-Trained Language Models: From Model Compression to Improving Generalization

The Lottery Ticket Hypothesis suggests that an over-parametrized network...

0 Chen Liang, et al. ∙

research

∙ 05/18/2021

Permutation Invariant Policy Optimization for Mean-Field Multi-Agent Reinforcement Learning: A Principled Approach

Multi-agent reinforcement learning (MARL) becomes more challenging in th...

0 Yan Li, et al. ∙

research

∙ 05/03/2021

COUnty aggRegation mixup AuGmEntation (COURAGE) COVID-19 Prediction

The global spread of COVID-19, the disease caused by the novel coronavir...

0 Siawpeng Er, et al. ∙

research

∙ 04/11/2021

Adversarial Training as Stackelberg Game: An Unrolled Optimization Approach

Adversarial training has been shown to improve the generalization perfor...

0 Simiao Zuo, et al. ∙

research

∙ 03/20/2021

Token-wise Curriculum Learning for Neural Machine Translation

Existing curriculum learning approaches to Neural Machine Translation (N...

0 Chen Liang, et al. ∙

research

∙ 03/01/2021

Reinforcement Learning for Adaptive Mesh Refinement

Large-scale finite element simulations of complex physical systems gover...

17 Jiachen Yang, et al. ∙

research

∙ 02/24/2021

Noisy Gradient Descent Converges to Flat Minima for Nonconvex Matrix Factorization

Numerous empirical evidences have corroborated the importance of noise i...

0 Tianyi Liu, et al. ∙

research

∙ 02/20/2021

Towards Automatic Evaluation of Dialog Systems: A Model-Free Off-Policy Evaluation Approach

Reliable automatic evaluation of dialogue systems under an interactive e...

8 Haoming Jiang, et al. ∙

research

∙ 11/30/2020

A Hypergradient Approach to Robust Regression without Correspondence

We consider a regression problem, where the correspondence between input...

0 Yujia Xie, et al. ∙

research

∙ 11/03/2020

Doubly Robust Off-Policy Learning on Low-Dimensional Manifolds by Deep Neural Networks

Causal inference explores the causation between actions and the conseque...

0 Minshuo Chen, et al. ∙

research

∙ 10/22/2020

Calibrated Language Model Fine-Tuning for In- and Out-of-Distribution Data

Fine-tuned pre-trained language models can suffer from severe miscalibra...

2 Lingkai Kong, et al. ∙

Tuo Zhao

Featured Co-authors