Searcharxiv⌕ Search

arXiv subjects

Han Wu

Publications and source records attributed to Han Wu.

At least 145 records · Page 8Linked to original sources
arXiv2022

Thompson Sampling with Unrestricted Delays

We investigate properties of Thompson Sampling in the stochastic multi-armed bandit problem with delayed feedback. In a setting with i.i.d delays, we establish to our knowledge the first regret bounds for Thompson Sampling with arbitrary delay distributions, including ones with unbounded expectation. Our bounds are qualitatively comparable to the best available bounds derived via ad-hoc algorithms, and only depend on delays via selected quantiles of the delay distributions. Furthermore, in extensive simulation experiments, we find that Thompson Sampling outperforms a number of alternative proposals, including methods specifically designed for settings with delayed feedback.

cs.LG↗
arXiv2022

On Joint Communication and Channel Discrimination

We consider a basic communication and sensing setup comprising a transmitter, a receiver and a sensor. The transmitter sends an encoded sequence to the receiver through a discrete memoryless channel, and the receiver is interested in decoding the sequence. On the other hand, the sensor picks up a noisy version of the transmitted sequence through one of two possible discrete memoryless channels. The sensor knows the transmitted sequence and wishes to discriminate between the two possible channels, i.e. to identify the channel that has generated the output given the input. We study the trade-off between communication and sensing in the asymptotic regime, captured in terms of the coding rate to the receiver against the discrimination error exponent at the sensor. We characterize the optimal rate-exponent trade-off for general discrete memoryless channels with an input cost constraint.

cs.IT↗
arXiv2022

Learning Localization-aware Target Confidence for Siamese Visual Tracking

Siamese tracking paradigm has achieved great success, providing effective appearance discrimination and size estimation by the classification and regression. While such a paradigm typically optimizes the classification and regression independently, leading to task misalignment (accurate prediction boxes have no high target confidence scores). In this paper, to alleviate this misalignment, we propose a novel tracking paradigm, called SiamLA. Within this paradigm, a series of simple, yet effective localization-aware components are introduced, to generate localization-aware target confidence scores. Specifically, with the proposed localization-aware dynamic label (LADL) loss and localization-aware label smoothing (LALS) strategy, collaborative optimization between the classification and regression is achieved, enabling classification scores to be aware of location state, not just appearance similarity. Besides, we propose a separate localization branch, centered on a localization-aware feature aggregation (LAFA) module, to produce location quality scores to further modify the classification scores. Consequently, the resulting target confidence scores, are more discriminative for the location state, allowing accurate prediction boxes tend to be predicted as high scores. Extensive experiments are conducted on six challenging benchmarks, including GOT-10k, TrackingNet, LaSOT, TNL2K, OTB100 and VOT2018. Our SiamLA achieves state-of-the-art performance in terms of both accuracy and efficiency. Furthermore, a stability analysis reveals that our tracking paradigm is relatively stable, implying the paradigm is potential to real-world applications.

cs.CV↗
arXiv2022

Hybrid subconvexity and the partition function

We give an upper bound for the error term in the Hardy-Ramanujan-Rademacher formula for the partition function. The main input is a new hybrid subconvexity bound for the central value $L(\tfrac 12,f\times (\tfrac{q}{\cdot}))$ in the $q$ and spectral parameter aspects, where $f$ is a Hecke-Maass cusp form for $Γ_0(N)$ and $q$ is a fundamental discriminant.

math.NT↗
arXiv2022

Zero-shot Cross-lingual Conversational Semantic Role Labeling

While conversational semantic role labeling (CSRL) has shown its usefulness on Chinese conversational tasks, it is still under-explored in non-Chinese languages due to the lack of multilingual CSRL annotations for the parser training. To avoid expensive data collection and error-propagation of translation-based methods, we present a simple but effective approach to perform zero-shot cross-lingual CSRL. Our model implicitly learns language-agnostic, conversational structure-aware and semantically rich representations with the hierarchical encoders and elaborately designed pre-training objectives. Experimental results show that our model outperforms all baselines by large margins on two newly collected English CSRL test sets. More importantly, we confirm the usefulness of CSRL to non-Chinese conversational tasks such as the question-in-context rewriting task in English and the multi-turn dialogue response generation tasks in English, German and Japanese by incorporating the CSRL information into the downstream conversation-based models. We believe this finding is significant and will facilitate the research of non-Chinese dialogue tasks which suffer the problems of ellipsis and anaphora.

cs.CL↗
arXiv2022

Nonsymmorphic Symmetry-Protected Band Crossings in a Square-Net Metal PtPb$_4$

Topological semimetals with symmetry-protected band crossings have emerged as a rich landscape to explore intriguing electronic phenomena. Nonsymmorphic symmetries in particular have been shown to play an important role in protecting the crossings along a line (rather than a point) in momentum space. Here we report experimental and theoretical evidence for Dirac nodal line crossings along the Brillouin zone boundaries in PtPb$_4$, arising from the nonsymmorphic symmetry of its crystal structure. Interestingly, while the nodal lines would remain gapless in the absence of spin-orbit coupling (SOC), the SOC in this case plays a detrimental role to topology by lifting the band degeneracy everywhere except at a set of isolated points. Nevertheless, the nodal line is observed to have a bandwidth much smaller than that found in density functional theory (DFT). Our findings reveal PtPb$_4$ to be a material system with narrow crossings approximately protected by non-symmorhpic crystalline symmetries.

cond-mat.mtrl-sci↗
arXiv2022

Non-invariance of weak approximation with Brauer--Manin obstruction

In this paper, we study weak approximation with Brauer--Manin obstruction with respect to extensions of number fields. For any nontrivial extension $L/K,$ assuming a conjecture of M. Stoll, we prove that there exists a $K$-threefold satisfying weak approximation with Brauer--Manin obstruction off all archimedean places, while its base change to $L$ fails. Then we illustrate this construction with an explicit unconditional example.

math.NT↗
arXiv2022

Arithmetic of Chatelet surfaces under extensions of base fields

For Châtelet surfaces defined over number fields, we study two arithmetic properties, the Hasse principle and weak approximation, when passing to an extension of the base field. Generalizing a construction of Y. Liang, we show that for an arbitrary extension of number fields $L/K,$ there is a Châtelet surface over $K$ which does not satisfy weak approximation over any intermediate field of $L/K,$ and a Châtelet surface over $K$ which satisfies the Hasse principle over an intermediate field $L'$ if and only if $[L' : K]$ is even.

math.NT↗
arXiv2022

A Sentence is Worth 128 Pseudo Tokens: A Semantic-Aware Contrastive Learning Framework for Sentence Embeddings

Contrastive learning has shown great potential in unsupervised sentence embedding tasks, e.g., SimCSE. However, We find that these existing solutions are heavily affected by superficial features like the length of sentences or syntactic structures. In this paper, we propose a semantics-aware contrastive learning framework for sentence embeddings, termed Pseudo-Token BERT (PT-BERT), which is able to exploit the pseudo-token space (i.e., latent semantic space) representation of a sentence while eliminating the impact of superficial features such as sentence length and syntax. Specifically, we introduce an additional pseudo token embedding layer independent of the BERT encoder to map each sentence into a sequence of pseudo tokens in a fixed length. Leveraging these pseudo sequences, we are able to construct same-length positive and negative pairs based on the attention mechanism to perform contrastive learning. In addition, we utilize both the gradient-updating and momentum-updating encoders to encode instances while dynamically maintaining an additional queue to store the representation of sentence embeddings, enhancing the encoder's learning performance for negative examples. Experiments show that our model outperforms the state-of-the-art baselines on six standard semantic textual similarity (STS) tasks. Furthermore, experiments on alignments and uniformity losses, as well as hard examples with different sentence lengths and syntax, consistently verify the effectiveness of our method.

cs.CL↗
arXiv2022

Ensemble Method for Estimating Individualized Treatment Effects

In many medical and business applications, researchers are interested in estimating individualized treatment effects using data from a randomized experiment. For example in medical applications, doctors learn the treatment effects from clinical trials and in technology companies, researchers learn them from A/B testing experiments. Although dozens of machine learning models have been proposed for this task, it is challenging to determine which model will be best for the problem at hand because ground-truth treatment effects are unobservable. In contrast to several recent papers proposing methods to select one of these competing models, we propose an algorithm for aggregating the estimates from a diverse library of models. We compare ensembling to model selection on 43 benchmark datasets, and find that ensembling wins almost every time. Theoretically, we prove that our ensemble model is (asymptotically) at least as accurate as the best model under consideration, even if the number of candidate models is allowed to grow with the sample size.

stat.ME↗
arXiv2021

Hire-MLP: Vision MLP via Hierarchical Rearrangement

Previous vision MLPs such as MLP-Mixer and ResMLP accept linearly flattened image patches as input, making them inflexible for different input sizes and hard to capture spatial information. Such approach withholds MLPs from getting comparable performance with their transformer-based counterparts and prevents them from becoming a general backbone for computer vision. This paper presents Hire-MLP, a simple yet competitive vision MLP architecture via \textbf{Hi}erarchical \textbf{re}arrangement, which contains two levels of rearrangements. Specifically, the inner-region rearrangement is proposed to capture local information inside a spatial region, and the cross-region rearrangement is proposed to enable information communication between different regions and capture global context by circularly shifting all tokens along spatial directions. Extensive experiments demonstrate the effectiveness of Hire-MLP as a versatile backbone for various vision tasks. In particular, Hire-MLP achieves competitive results on image classification, object detection and semantic segmentation tasks, e.g., 83.8% top-1 accuracy on ImageNet, 51.7% box AP and 44.8% mask AP on COCO val2017, and 49.9% mIoU on ADE20K, surpassing previous transformer-based and MLP-based models with better trade-off for accuracy and throughput. Code is available at https://github.com/ggjy/Hire-Wave-MLP.pytorch.

cs.CV↗
arXiv2021

CSAGN: Conversational Structure Aware Graph Network for Conversational Semantic Role Labeling

Conversational semantic role labeling (CSRL) is believed to be a crucial step towards dialogue understanding. However, it remains a major challenge for existing CSRL parser to handle conversational structural information. In this paper, we present a simple and effective architecture for CSRL which aims to address this problem. Our model is based on a conversational structure-aware graph network which explicitly encodes the speaker dependent information. We also propose a multi-task learning method to further improve the model. Experimental results on benchmark datasets show that our model with our proposed training objectives significantly outperforms previous baselines.

cs.CL↗
arXiv2021

Interpretable Machine Learning for COVID-19: An Empirical Study on Severity Prediction Task

The black-box nature of machine learning models hinders the deployment of some high-accuracy models in medical diagnosis. It is risky to put one's life in the hands of models that medical researchers do not fully understand. However, through model interpretation, black-box models can promptly reveal significant biomarkers that medical practitioners may have overlooked due to the surge of infected patients in the COVID-19 pandemic. This research leverages a database of 92 patients with confirmed SARS-CoV-2 laboratory tests between 18th Jan. 2020 and 5th Mar. 2020, in Zhuhai, China, to identify biomarkers indicative of severity prediction. Through the interpretation of four machine learning models, decision tree, random forests, gradient boosted trees, and neural networks using permutation feature importance, Partial Dependence Plot (PDP), Individual Conditional Expectation (ICE), Accumulated Local Effects (ALE), Local Interpretable Model-agnostic Explanations (LIME), and Shapley Additive Explanation (SHAP), we identify an increase in N-Terminal pro-Brain Natriuretic Peptide (NTproBNP), C-Reaction Protein (CRP), and lactic dehydrogenase (LDH), a decrease in lymphocyte (LYM) is associated with severe infection and an increased risk of death, which is consistent with recent medical research on COVID-19 and other research using dedicated models. We further validate our methods on a large open dataset with 5644 confirmed patients from the Hospital Israelita Albert Einstein, at São Paulo, Brazil from Kaggle, and unveil leukocytes, eosinophils, and platelets as three indicative biomarkers for COVID-19.

cs.LG↗
arXiv2021

Privacy-Preserving Batch-based Task Assignment in Spatial Crowdsourcing with Untrusted Server

In this paper, we study the privacy-preserving task assignment in spatial crowdsourcing, where the locations of both workers and tasks, prior to their release to the server, are perturbed with Geo-Indistinguishability (a differential privacy notion for location-based systems). Different from the previously studied online setting, where each task is assigned immediately upon arrival, we target the batch-based setting, where the server maximizes the number of successfully assigned tasks after a batch of tasks arrive. To achieve this goal, we propose the k-Switch solution, which first divides the workers into small groups based on the perturbed distance between workers/tasks, and then utilizes Homomorphic Encryption (HE) based secure computation to enhance the task assignment. Furthermore, we expedite HE-based computation by limiting the size of the small groups under k. Extensive experiments demonstrate that, in terms of the number of successfully assigned tasks, the k-Switch solution improves batch-based baselines by 5.9X and the existing online solution by 1.74X, with no privacy leak.

cs.CR↗
arXiv2021

Domain-Adaptive Pretraining Methods for Dialogue Understanding

Language models like BERT and SpanBERT pretrained on open-domain data have obtained impressive gains on various NLP tasks. In this paper, we probe the effectiveness of domain-adaptive pretraining objectives on downstream tasks. In particular, three objectives, including a novel objective focusing on modeling predicate-argument relations, are evaluated on two challenging dialogue understanding tasks. Experimental results demonstrate that domain-adaptive pretraining with proper objectives can significantly improve the performance of a strong baseline on these tasks, achieving the new state-of-the-art performances.

cs.CL↗