arXiv subjects

Xi Chen

Publications and source records attributed to Xi Chen.

At least 685 records · Page 38Linked to original sources

arXiv2023

Active Learning in Physics: From 101, to Progress, and Perspective

Active Learning (AL) is a family of machine learning (ML) algorithms that predates the current era of artificial intelligence. Unlike traditional approaches that require labeled samples for training, AL iteratively selects unlabeled samples to be annotated by an expert. This protocol aims to prioritize the most informative samples, leading to improved model performance compared to training with all labeled samples. In recent years, AL has gained increasing attention, particularly in the field of physics. This paper presents a comprehensive and accessible introduction to the theory of AL reviewing the latest advancements across various domains. Additionally, we explore the potential integration of AL with quantum ML, envisioning a synergistic fusion of these two fields rather than viewing AL as a mere extension of classical ML into the quantum realm.

quant-ph↗

arXiv2023

The space cold atom interferometer for testing the equivalence principle in the China Space Station

The precision of the weak equivalence principle (WEP) test using atom interferometers (AIs) is expected to be extremely high in microgravity environment. The microgravity scientific laboratory cabinet (MSLC) in the China Space Station (CSS) can provide a higher-level microgravity than the CSS itself, which provides a good experimental environment for scientific experiments that require high microgravity. We designed and realized a payload of a dual-species cold rubidium atom interferometer. The payload is highly integrated and has a size of 460 mm * 330 mm * 260 mm. It will be installed in the MSLC to carry out high-precision WEP test experiment. In this article, we introduce the constraints and guidelines of the payload design, the compositions and functions of the scientific payload, the expected test precision in space, and some results of the ground test experiments

physics.atom-ph↗

arXiv2023

Memory-Query Tradeoffs for Randomized Convex Optimization

We show that any randomized first-order algorithm which minimizes a $d$-dimensional, $1$-Lipschitz convex function over the unit ball must either use $Ω(d^{2-δ})$ bits of memory or make $Ω(d^{1+δ/6-o(1)})$ queries, for any constant $δ\in (0,1)$ and when the precision $ε$ is quasipolynomially small in $d$. Our result implies that cutting plane methods, which use $\tilde{O}(d^2)$ bits of memory and $\tilde{O}(d)$ queries, are Pareto-optimal among randomized first-order algorithms, and quadratic memory is required to achieve optimal query complexity for convex optimization.

cs.DS↗

arXiv2023

Voter Coalitions and democracy in Decentralized Finance: Evidence from MakerDAO

Decentralized Autonomous Organization (DAO) provides a decentralized governance solution through blockchain, where decision-making process relies on on-chain voting and follows majority rule. This paper focuses on MakerDAO, and we find three voter coalitions after applying clustering algorithm to voting history. The emergence of a dominant voter coalition is a signal of governance centralization in DAO, and voter coalitions have complicated influence on Maker protocol, which is governed by MakerDAO. This paper presents empirical evidence of multicoalition democracy in DAO and further contributes to the contemporary debate on whether decentralized governance is possible.

cs.SI↗

arXiv2023

Performance of data-driven inner speech decoding with same-task EEG-fMRI data fusion and bimodal models

Decoding inner speech from the brain signal via hybridisation of fMRI and EEG data is explored to investigate the performance benefits over unimodal models. Two different bimodal fusion approaches are examined: concatenation of probability vectors output from unimodal fMRI and EEG machine learning models, and data fusion with feature engineering. Same task inner speech data are recorded from four participants, and different processing strategies are compared and contrasted to previously-employed hybridisation methods. Data across participants are discovered to encode different underlying structures, which results in varying decoding performances between subject-dependent fusion models. Decoding performance is demonstrated as improved when pursuing bimodal fMRI-EEG fusion strategies, if the data show underlying structure.

cs.LG↗

arXiv2023

PolyVoice: Language Models for Speech to Speech Translation

We propose PolyVoice, a language model-based framework for speech-to-speech translation (S2ST) system. Our framework consists of two language models: a translation language model and a speech synthesis language model. We use discretized speech units, which are generated in a fully unsupervised way, and thus our framework can be used for unwritten languages. For the speech synthesis part, we adopt the existing VALL-E X approach and build a unit-based audio language model. This grants our framework the ability to preserve the voice characteristics and the speaking style of the original speech. We examine our system on Chinese $\rightarrow$ English and English $\rightarrow$ Spanish pairs. Experimental results show that our system can generate speech with high translation quality and audio quality. Speech samples are available at https://speechtranslation.github.io/polyvoice.

cs.CL↗

arXiv2023

DisC-Diff: Disentangled Conditional Diffusion Model for Multi-Contrast MRI Super-Resolution

Multi-contrast magnetic resonance imaging (MRI) is the most common management tool used to characterize neurological disorders based on brain tissue contrasts. However, acquiring high-resolution MRI scans is time-consuming and infeasible under specific conditions. Hence, multi-contrast super-resolution methods have been developed to improve the quality of low-resolution contrasts by leveraging complementary information from multi-contrast MRI. Current deep learning-based super-resolution methods have limitations in estimating restoration uncertainty and avoiding mode collapse. Although the diffusion model has emerged as a promising approach for image enhancement, capturing complex interactions between multiple conditions introduced by multi-contrast MRI super-resolution remains a challenge for clinical applications. In this paper, we propose a disentangled conditional diffusion model, DisC-Diff, for multi-contrast brain MRI super-resolution. It utilizes the sampling-based generation and simple objective function of diffusion models to estimate uncertainty in restorations effectively and ensure a stable optimization process. Moreover, DisC-Diff leverages a disentangled multi-stream network to fully exploit complementary information from multi-contrast MRI, improving model interpretation under multiple conditions of multi-contrast inputs. We validated the effectiveness of DisC-Diff on two datasets: the IXI dataset, which contains 578 normal brains, and a clinical dataset with 316 pathological brains. Our experimental results demonstrate that DisC-Diff outperforms other state-of-the-art methods both quantitatively and visually.

eess.IV↗

arXiv2023

PaLI: A Jointly-Scaled Multilingual Language-Image Model

Effective scaling and a flexible task interface enable large language models to excel at many tasks. We present PaLI (Pathways Language and Image model), a model that extends this approach to the joint modeling of language and vision. PaLI generates text based on visual and textual inputs, and with this interface performs many vision, language, and multimodal tasks, in many languages. To train PaLI, we make use of large pre-trained encoder-decoder language models and Vision Transformers (ViTs). This allows us to capitalize on their existing capabilities and leverage the substantial cost of training them. We find that joint scaling of the vision and language components is important. Since existing Transformers for language are much larger than their vision counterparts, we train a large, 4-billion parameter ViT (ViT-e) to quantify the benefits from even larger-capacity vision models. To train PaLI, we create a large multilingual mix of pretraining tasks, based on a new image-text training set containing 10B images and texts in over 100 languages. PaLI achieves state-of-the-art in multiple vision and language tasks (such as captioning, visual question-answering, scene-text understanding), while retaining a simple, modular, and scalable design.

cs.CV↗

arXiv2023

Reynolds number asymptotics of wall-turbulence fluctuations

In furtherance of our earlier work (Chen \& Sreenivasan, {\it J. Fluid Mech.} {\bf 908}, 2021, p. R3; {\bf 933}, 2022, p. A20 -- together referred to as CS hereafter), we present a self-consistent Reynolds number asymptotics for wall-normal profiles of variances of streamwise and spanwise velocity fluctuations as well as root-mean-square pressure, across the entire flow region of channel and pipe flows and flat-plate boundary layers. It is first shown that, when normalized by peak values, the Reynolds number dependence and wall-normal variation of all three profiles can be decoupled, in excellent agreement with available data, sharing the common inner expansion of the type $ϕ^+(y^+)=f_0(y^+)+f_1(y^+)/Re^{1/4}_τ$, where $ϕ^+$ is one of the quantities just mentioned, and the functions $f_0$ and $f_1$ depend only on $y^+$. Here, the superscript $+$ indicates normalization by wall variables. Secondly, by matching the above inner expansion and the inviscid outer flow similarity form, a bounded variation $ϕ^+(y^\ast)=α_ϕ-β_ϕy^{\ast{{1}/{4}}}$ is derived beyond the peak where, for each $ϕ^+$, the constants $α_ϕ$ and $β_ϕ$ are independent of $Re_τ$ and $y^\ast$ ($=y^+/Re_τ$, $Re_τ$ being the Reynolds number based on the friction velocity) -- also in excellent agreement with simulations and experimental data. One of the predictions of the analysis is that, for asymptotically high Reynolds numbers, a finite plateau $ϕ^+\approxα_ϕ$ appears in the outer region. This result sheds light on the intriguing issue of the outer shoulder of the variance of the streamwise velocity fluctuation, which should be bounded by the asymptotic plateau of about 10.

physics.flu-dyn↗

arXiv2023

PaLI-X: On Scaling up a Multilingual Vision and Language Model

We present the training recipe and results of scaling up PaLI-X, a multilingual vision and language model, both in terms of size of the components and the breadth of its training task mixture. Our model achieves new levels of performance on a wide-range of varied and complex tasks, including multiple image-based captioning and question-answering tasks, image-based document understanding and few-shot (in-context) learning, as well as object detection, video question answering, and video captioning. PaLI-X advances the state-of-the-art on most vision-and-language benchmarks considered (25+ of them). Finally, we observe emerging capabilities, such as complex counting and multilingual object detection, tasks that are not explicitly in the training mix.

cs.CV↗

arXiv2023

CONA: A novel CONtext-Aware instruction paradigm for communication using large language model

We introduce CONA, a novel context-aware instruction paradigm for effective knowledge dissemination using generative pre-trained transformer (GPT) models. CONA is a flexible framework designed to leverage the capabilities of Large Language Models (LLMs) and incorporate DIKW (Data, Information, Knowledge, Wisdom) hierarchy to automatically instruct and optimise presentation content, anticipate potential audience inquiries, and provide context-aware answers that adaptive to the knowledge level of the audience group. The unique aspect of the CONA paradigm lies in its combination of an independent advisory mechanism and a recursive feedback loop rooted on the DIKW hierarchy. This synergy significantly enhances context-aware contents, ensuring they are accessible and easily comprehended by the audience. This paradigm is an early pioneer to explore new methods for knowledge dissemination and communication in the LLM era, offering effective support for everyday knowledge sharing scenarios. We conduct experiments on a range of audience roles, along with materials from various disciplines using GPT4. Both quantitative and qualitative results demonstrated that the proposed CONA paradigm achieved remarkable performance compared to the outputs guided by conventional prompt engineering.

cs.CL↗

arXiv2023

Smoothed Complexity of SWAP in Local Graph Partitioning

We give the first quasipolynomial upper bound $ϕn^{\text{polylog}(n)}$ for the smoothed complexity of the SWAP algorithm for local Graph Partitioning (also known as Bisection Width), where $n$ is the number of nodes in the graph and $ϕ$ is a parameter that measures the magnitude of perturbations applied on its edge weights. More generally, we show that the same quasipolynomial upper bound holds for the smoothed complexity of the 2-FLIP algorithm for any binary Maximum Constraint Satisfaction Problem, including local Max-Cut, for which similar bounds were only known for $1$-FLIP. Our results are based on an analysis of cycles formed in long sequences of double flips, showing that it is unlikely for every move in a long sequence to incur a positive but small improvement in the cut weight.

cs.DS↗

arXiv2023

Text Generation with Speech Synthesis for ASR Data Augmentation

Aiming at reducing the reliance on expensive human annotations, data synthesis for Automatic Speech Recognition (ASR) has remained an active area of research. While prior work mainly focuses on synthetic speech generation for ASR data augmentation, its combination with text generation methods is considerably less explored. In this work, we explore text augmentation for ASR using large-scale pre-trained neural networks, and systematically compare those to traditional text augmentation methods. The generated synthetic texts are then converted to synthetic speech using a text-to-speech (TTS) system and added to the ASR training data. In experiments conducted on three datasets, we find that neural models achieve 9%-15% relative WER improvement and outperform traditional methods. We conclude that text augmentation, particularly through modern neural approaches, is a viable tool for improving the accuracy of ASR systems.

cs.CL↗

arXiv2023

Self-Supervised Instance Segmentation by Grasping

Instance segmentation is a fundamental skill for many robotic applications. We propose a self-supervised method that uses grasp interactions to collect segmentation supervision for an instance segmentation model. When a robot grasps an item, the mask of that grasped item can be inferred from the images of the scene before and after the grasp. Leveraging this insight, we learn a grasp segmentation model to segment the grasped object from before and after grasp images. Such a model can segment grasped objects from thousands of grasp interactions without costly human annotation. Using the segmented grasped objects, we can "cut" objects from their original scenes and "paste" them into new scenes to generate instance supervision. We show that our grasp segmentation model provides a 5x error reduction when segmenting grasped objects compared with traditional image subtraction approaches. Combined with our "cut-and-paste" generation method, instance segmentation models trained with our method achieve better performance than a model trained with 10x the amount of labeled data. On a real robotic grasping system, our instance segmentation model reduces the rate of grasp errors by over 3x compared to an image subtraction baseline.

cs.CV↗

arXiv2023

Proportional Fairness in Federated Learning

With the increasingly broad deployment of federated learning (FL) systems in the real world, it is critical but challenging to ensure fairness in FL, i.e. reasonably satisfactory performances for each of the numerous diverse clients. In this work, we introduce and study a new fairness notion in FL, called proportional fairness (PF), which is based on the relative change of each client's performance. From its connection with the bargaining games, we propose PropFair, a novel and easy-to-implement algorithm for finding proportionally fair solutions in FL and study its convergence properties. Through extensive experiments on vision and language datasets, we demonstrate that PropFair can approximately find PF solutions, and it achieves a good balance between the average performances of all clients and of the worst 10% clients. Our code is available at \url{https://github.com/huawei-noah/Federated-Learning/tree/main/FairFL}.

cs.LG↗

arXiv2023

Distributional Instance Segmentation: Modeling Uncertainty and High Confidence Predictions with Latent-MaskRCNN

Object recognition and instance segmentation are fundamental skills in any robotic or autonomous system. Existing state-of-the-art methods are often unable to capture meaningful uncertainty in challenging or ambiguous scenes, and as such can cause critical errors in high-performance applications. In this paper, we explore a class of distributional instance segmentation models using latent codes that can model uncertainty over plausible hypotheses of object masks. For robotic picking applications, we propose a confidence mask method to achieve the high precision necessary in industrial use cases. We show that our method can significantly reduce critical errors in robotic systems, including our newly released dataset of ambiguous scenes in a robotic application. On a real-world apparel-picking robot, our method significantly reduces double pick errors while maintaining high performance.

cs.CV↗

arXiv2023

Semimetallic and semiconducting graphene-hBN multilayers with parallel or reverse stacking

We theoretically investigate 3D layered crystals of alternating graphene and hBN layers with different symmetries. Depending on the hopping parameters between the graphene layers, we find that these synthetic 3D materials can feature semimetallic, gapped, or Weyl semimetal phases. Our results demonstrate that 3D crystals stacked from individual 2D materials represent a synthetic materials class with emergent properties different from their constituents.

cond-mat.mtrl-sci↗

arXiv2023

New Lower Bounds for Adaptive Tolerant Junta Testing

We prove a $k^{-Ω(\log(\varepsilon_2 - \varepsilon_1))}$ lower bound for adaptively testing whether a Boolean function is $\varepsilon_1$-close to or $\varepsilon_2$-far from $k$-juntas. Our results provide the first superpolynomial separation between tolerant and non-tolerant testing for a natural property of boolean functions under the adaptive setting. Furthermore, our techniques generalize to show that adaptively testing whether a function is $\varepsilon_1$-close to a $k$-junta or $\varepsilon_2$-far from $(k + o(k))$-juntas cannot be done with $\textsf{poly} (k, (\varepsilon_2 - \varepsilon_1)^{-1})$ queries. This is in contrast to an algorithm by Iyer, Tal and Whitmeyer [CCC 2021] which uses $\textsf{poly} (k, (\varepsilon_2 - \varepsilon_1)^{-1})$ queries to test whether a function is $\varepsilon_1$-close to a $k$-junta or $\varepsilon_2$-far from $O(k/(\varepsilon_2-\varepsilon_1)^2)$-juntas.

cs.DS↗