Search Results for author: Xiang Ji

Found 26 papers, 11 papers with code

Sample Complexity of Preference-Based Nonparametric Off-Policy Evaluation with Deep Networks

no code implementations16 Oct 2023 Zihao Li, Xiang Ji, Minshuo Chen, Mengdi Wang

In fact, human preference data are now used with classic reinforcement learning algorithms such as actor-critic methods, which involve evaluating an intermediate policy over a reward learned from human preference data with distribution shift, known as off-policy evaluation (OPE).

Off-policy evaluation reinforcement-learning

Towards Deep Learning Models Resistant to Transfer-based Adversarial Attacks via Data-centric Robust Learning

no code implementations15 Oct 2023 Yulong Yang, Chenhao Lin, Xiang Ji, Qiwei Tian, Qian Li, Hongshan Yang, Zhibo Wang, Chao Shen

Instead, a one-shot adversarial augmentation prior to training is sufficient, and we name this new defense paradigm Data-centric Robust Learning (DRL).

Fairness

Sample Complexity of Neural Policy Mirror Descent for Policy Optimization on Low-Dimensional Manifolds

no code implementations25 Sep 2023 Zhenghao Xu, Xiang Ji, Minshuo Chen, Mengdi Wang, Tuo Zhao

As a result, by properly choosing the network size and hyperparameters, NPMD can find an $\epsilon$-optimal policy with $\widetilde{O}(\epsilon^{-\frac{d}{\alpha}-2})$ samples in expectation, where $\alpha\in(0, 1]$ indicates the smoothness of environment.

Policy Gradient Methods Reinforcement Learning (RL)

Hard Adversarial Example Mining for Improving Robust Fairness

no code implementations3 Aug 2023 Chenhao Lin, Xiang Ji, Yulong Yang, Qian Li, Chao Shen, Run Wang, Liming Fang

Adversarial training (AT) is widely considered the state-of-the-art technique for improving the robustness of deep neural networks (DNNs) against adversarial examples (AE).

Fairness

Rethinking Video Frame Interpolation from Shutter Mode Induced Degradation

no code implementations ICCV 2023 Xiang Ji, Zhixiang Wang, Zhihang Zhong, Yinqiang Zheng

Image restoration from various motion-related degradations, like blurry effects recorded by a global shutter (GS) and jello effects caused by a rolling shutter (RS), has been extensively studied.

Disentanglement Image Restoration +1

Single Image Deblurring with Row-dependent Blur Magnitude

no code implementations ICCV 2023 Xiang Ji, Zhixiang Wang, Shin'ichi Satoh, Yinqiang Zheng

Image degradation often occurs during fast camera or object movements, regardless of the exposure modes: global shutter (GS) or rolling shutter (RS).

Deblurring Image Deblurring

Blur Interpolation Transformer for Real-World Motion from Blur

1 code implementation CVPR 2023 Zhihang Zhong, Mingdeng Cao, Xiang Ji, Yinqiang Zheng, Imari Sato

This paper studies the challenging problem of recovering motion from blur, also known as joint deblurring and interpolation or blur temporal super-resolution.

Deblurring Super-Resolution

Automatic differentiation is no panacea for phylogenetic gradient computation

2 code implementations3 Nov 2022 Mathieu Fourment, Christiaan J. Swanepoel, Jared G. Galloway, Xiang Ji, Karthik Gangavarapu, Marc A. Suchard, Frederick A. Matsen IV

Gradients of probabilistic model likelihoods with respect to their parameters are essential for modern computational statistics and machine learning.

Variational Inference

Speeding Up Question Answering Task of Language Models via Inverted Index

no code implementations24 Oct 2022 Xiang Ji, Yesim Sungu-Eryilmaz, Elaheh Momeni, Reza Rawassizadeh

Natural language processing applications, such as conversational agents and their question-answering capabilities, are widely used in the real world.

Question Answering

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

no code implementations6 Jun 2022 Xiang Ji, Minshuo Chen, Mengdi Wang, Tuo Zhao

We consider the off-policy evaluation problem of reinforcement learning using deep convolutional neural networks.

Off-policy evaluation

Optimal Estimation of Off-Policy Policy Gradient via Double Fitted Iteration

no code implementations31 Jan 2022 Chengzhuo Ni, Ruiqi Zhang, Xiang Ji, Xuezhou Zhang, Mengdi Wang

Policy gradient (PG) estimation becomes a challenge when we are not allowed to sample with the target policy but only have access to a dataset generated by some unknown behavior policy.

Scalable Bayesian divergence time estimation with ratio transformations

1 code implementation25 Oct 2021 Xiang Ji, Alexander A. Fisher, Shuo Su, Jeffrey L. Thorne, Barney Potter, Philippe Lemey, Guy Baele, Marc A. Suchard

Divergence time estimation is crucial to provide temporal signals for dating biologically important events, from species divergence to viral transmissions in space and time.

Are Missing Links Predictable? An Inferential Benchmark for Knowledge Graph Completion

1 code implementation ACL 2021 Yixin Cao, Xiang Ji, Xin Lv, Juanzi Li, Yonggang Wen, Hanwang Zhang

We present InferWiki, a Knowledge Graph Completion (KGC) dataset that improves upon existing benchmarks in inferential ability, assumptions, and patterns.

Knowledge Graph Completion

Bootstrapping Fitted Q-Evaluation for Off-Policy Inference

no code implementations6 Feb 2021 Botao Hao, Xiang Ji, Yaqi Duan, Hao Lu, Csaba Szepesvári, Mengdi Wang

Bootstrapping provides a flexible and effective approach for assessing the quality of batch reinforcement learning, yet its theoretical property is less understood.

Off-policy evaluation

PROP: Pre-training with Representative Words Prediction for Ad-hoc Retrieval

1 code implementation20 Oct 2020 Xinyu Ma, Jiafeng Guo, Ruqing Zhang, Yixing Fan, Xiang Ji, Xueqi Cheng

Recently pre-trained language representation models such as BERT have shown great success when fine-tuned on downstream tasks including information retrieval (IR).

Information Retrieval Language Modelling +1

Urban Bike Lane Planning with Bike Trajectories: Models, Algorithms, and a Real-World Case Study

no code implementations21 Aug 2020 Sheng Liu, Zuo-Jun Max Shen, Xiang Ji

We formalize the bike lane planning problem in view of the cyclists' utility functions and derive an integer optimization model to maximize the utility.

Management

Gradients do grow on trees: a linear-time ${\cal O}\hspace{-0.2em}\left( N \right)$-dimensional gradient for statistical phylogenetics

1 code implementation29 May 2019 Xiang Ji, Zhen-Yu Zhang, Andrew Holbrook, Akihiko Nishimura, Guy Baele, Andrew Rambaut, Philippe Lemey, Marc A. Suchard

To make this tractable, we present a linear-time algorithm for ${\cal O}\hspace{-0. 2em}\left( N \right)$-dimensional gradient evaluation and apply it to general continuous-time Markov processes of sequence substitution on a phylogenetic tree without a need to assume either stationarity or reversibility.

Computation Populations and Evolution Methodology

MatchZoo: A Learning, Practicing, and Developing System for Neural Text Matching

1 code implementation24 May 2019 Jiafeng Guo, Yixing Fan, Xiang Ji, Xue-Qi Cheng

Text matching is the core problem in many natural language processing (NLP) tasks, such as information retrieval, question answering, and conversation.

Information Retrieval Question Answering +2

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