arXiv subjects

Kai Yi

Publications and source records attributed to Kai Yi.

At least 55 records · Page 3Linked to original sources

arXiv2023

Adaptive Importance Sampling and Quasi-Monte Carlo Methods for 6G URLLC Systems

In this paper, we propose an efficient simulation method based on adaptive importance sampling, which can automatically find the optimal proposal within the Gaussian family based on previous samples, to evaluate the probability of bit error rate (BER) or word error rate (WER). These two measures, which involve high-dimensional black-box integration and rare-event sampling, can characterize the performance of coded modulation. We further integrate the quasi-Monte Carlo method within our framework to improve the convergence speed. The proposed importance sampling algorithm is demonstrated to have much higher efficiency than the standard Monte Carlo method in the AWGN scenario.

stat.ME↗

arXiv2023

EF-BV: A Unified Theory of Error Feedback and Variance Reduction Mechanisms for Biased and Unbiased Compression in Distributed Optimization

In distributed or federated optimization and learning, communication between the different computing units is often the bottleneck and gradient compression is widely used to reduce the number of bits sent within each communication round of iterative methods. There are two classes of compression operators and separate algorithms making use of them. In the case of unbiased random compressors with bounded variance (e.g., rand-k), the DIANA algorithm of Mishchenko et al. (2019), which implements a variance reduction technique for handling the variance introduced by compression, is the current state of the art. In the case of biased and contractive compressors (e.g., top-k), the EF21 algorithm of Richtárik et al. (2021), which instead implements an error-feedback mechanism, is the current state of the art. These two classes of compression schemes and algorithms are distinct, with different analyses and proof techniques. In this paper, we unify them into a single framework and propose a new algorithm, recovering DIANA and EF21 as particular cases. Our general approach works with a new, larger class of compressors, which has two parameters, the bias and the variance, and includes unbiased and biased compressors as particular cases. This allows us to inherit the best of the two worlds: like EF21 and unlike DIANA, biased compressors, like top-k, whose good performance in practice is recognized, can be used. And like DIANA and unlike EF21, independent randomness at the compressors allows to mitigate the effects of compression, with the convergence rate improving when the number of parallel workers is large. This is the first time that an algorithm with all these features is proposed. We prove its linear convergence under certain conditions. Our approach takes a step towards better understanding of two so-far distinct worlds of communication-efficient distributed learning.

cs.LG↗

arXiv2022

Recent CMS results on exotic resonances

Many exotic resonances have been recently observed at the LHC and other experiments. In this report, CMS studies of exotic multiquark states are reported using the data collected in pp collisions at $\sqrt{s}$ = 13 TeV.

hep-ex↗

arXiv2022

Exploring Hierarchical Graph Representation for Large-Scale Zero-Shot Image Classification

The main question we address in this paper is how to scale up visual recognition of unseen classes, also known as zero-shot learning, to tens of thousands of categories as in the ImageNet-21K benchmark. At this scale, especially with many fine-grained categories included in ImageNet-21K, it is critical to learn quality visual semantic representations that are discriminative enough to recognize unseen classes and distinguish them from seen ones. We propose a \emph{H}ierarchical \emph{G}raphical knowledge \emph{R}epresentation framework for the confidence-based classification method, dubbed as HGR-Net. Our experimental results demonstrate that HGR-Net can grasp class inheritance relations by utilizing hierarchical conceptual knowledge. Our method significantly outperformed all existing techniques, boosting the performance by 7\% compared to the runner-up approach on the ImageNet-21K benchmark. We show that HGR-Net is learning-efficient in few-shot scenarios. We also analyzed our method on smaller datasets like ImageNet-21K-P, 2-hops and 3-hops, demonstrating its generalization ability. Our benchmark and code are available at https://kaiyi.me/p/hgrnet.html.

cs.CV↗

arXiv2022

Variance Reduced ProxSkip: Algorithm, Theory and Application to Federated Learning

We study distributed optimization methods based on the {\em local training (LT)} paradigm: achieving communication efficiency by performing richer local gradient-based training on the clients before parameter averaging. Looking back at the progress of the field, we {\em identify 5 generations of LT methods}: 1) heuristic, 2) homogeneous, 3) sublinear, 4) linear, and 5) accelerated. The 5${}^{\rm th}$ generation, initiated by the ProxSkip method of Mishchenko, Malinovsky, Stich and Richtárik (2022) and its analysis, is characterized by the first theoretical confirmation that LT is a communication acceleration mechanism. Inspired by this recent progress, we contribute to the 5${}^{\rm th}$ generation of LT methods by showing that it is possible to enhance them further using {\em variance reduction}. While all previous theoretical results for LT methods ignore the cost of local work altogether, and are framed purely in terms of the number of communication rounds, we show that our methods can be substantially faster in terms of the {\em total training cost} than the state-of-the-art method ProxSkip in theory and practice in the regime when local computation is sufficiently expensive. We characterize this threshold theoretically, and confirm our theoretical predictions with empirical results.

cs.LG↗

arXiv2022

Approximate Equivariance SO(3) Needlet Convolution

This paper develops a rotation-invariant needlet convolution for rotation group SO(3) to distill multiscale information of spherical signals. The spherical needlet transform is generalized from $\mathbb{S}^2$ onto the SO(3) group, which decomposes a spherical signal to approximate and detailed spectral coefficients by a set of tight framelet operators. The spherical signal during the decomposition and reconstruction achieves rotation invariance. Based on needlet transforms, we form a Needlet approximate Equivariance Spherical CNN (NES) with multiple SO(3) needlet convolutional layers. The network establishes a powerful tool to extract geometric-invariant features of spherical signals. The model allows sufficient network scalability with multi-resolution representation. A robust signal embedding is learned with wavelet shrinkage activation function, which filters out redundant high-pass representation while maintaining approximate rotation invariance. The NES achieves state-of-the-art performance for quantum chemistry regression and Cosmic Microwave Background (CMB) delensing reconstruction, which shows great potential for solving scientific challenges with high-resolution and multi-scale spherical signal representation.

eess.IV↗

arXiv2022

VisualGPT: Data-efficient Adaptation of Pretrained Language Models for Image Captioning

The ability to quickly learn from a small quantity oftraining data widens the range of machine learning applications. In this paper, we propose a data-efficient image captioning model, VisualGPT, which leverages the linguistic knowledge from a large pretrained language model(LM). A crucial challenge is to balance between the use of visual information in the image and prior linguistic knowledge acquired from pretraining. We designed a novel self-resurrecting encoder-decoder attention mechanism to quickly adapt the pretrained LM as the language decoder ona small amount of in-domain training data. The proposed self-resurrecting activation unit produces sparse activations but has reduced susceptibility to zero gradients. We train the proposed model, VisualGPT, on 0.1%, 0.5% and 1% of MSCOCO and Conceptual Captions training data. Under these conditions, we outperform the best baseline model by up to 10.8% CIDEr on MS COCO and upto 5.4% CIDEr on Conceptual Captions. Further, Visual-GPT achieves the state-of-the-art result on IU X-ray, a medical report generation dataset. To the best of our knowledge, this is the first work that improves data efficiency of image captioning by utilizing LM pretrained on unimodal data. Our code is available at: https://github.com/Vision-CAIR/VisualGPT.

cs.CV↗

arXiv2021

Imaginative Walks: Generative Random Walk Deviation Loss for Improved Unseen Learning Representation

We propose a novel loss for generative models, dubbed as GRaWD (Generative Random Walk Deviation), to improve learning representations of unexplored visual spaces. Quality learning representation of unseen classes (or styles) is critical to facilitate novel image generation and better generative understanding of unseen visual classes, i.e., zero-shot learning (ZSL). By generating representations of unseen classes based on their semantic descriptions, e.g., attributes or text, generative ZSL attempts to differentiate unseen from seen categories. The proposed GRaWD loss is defined by constructing a dynamic graph that includes the seen class/style centers and generated samples in the current minibatch. Our loss initiates a random walk probability from each center through visual generations produced from hallucinated unseen classes. As a deviation signal, we encourage the random walk to eventually land after t steps in a feature representation that is difficult to classify as any of the seen classes. We demonstrate that the proposed loss can improve unseen class representation quality inductively on text-based ZSL benchmarks on CUB and NABirds datasets and attribute-based ZSL benchmarks on AWA2, SUN, and aPY datasets. In addition, we investigate the ability of the proposed loss to generate meaningful novel visual art on the WikiArt dataset. The results of experiments and human evaluations demonstrate that the proposed GRaWD loss can improve StyleGAN1 and StyleGAN2 generation quality and create novel art that is significantly more preferable. Our code is made publicly available at https://github.com/Vision-CAIR/GRaWD.

cs.CV↗

arXiv2021

Disentangling semantic features of macromolecules in Cryo-Electron Tomography

Cryo-electron tomography (Cryo-ET) is a 3D imaging technique that enables the systemic study of shape, abundance, and distribution of macromolecular structures in single cells in near-atomic resolution. However, the systematic and efficient $\textit{de novo}$ recognition and recovery of macromolecular structures captured by Cryo-ET are very challenging due to the structural complexity and imaging limits. Even macromolecules with identical structures have various appearances due to different orientations and imaging limits, such as noise and the missing wedge effect. Explicitly disentangling the semantic features of macromolecules is crucial for performing several downstream analyses on the macromolecules. This paper has addressed the problem by proposing a 3D Spatial Variational Autoencoder that explicitly disentangle the structure, orientation, and shift of macromolecules. Extensive experiments on both synthesized and real cryo-ET datasets and cross-domain evaluations demonstrate the efficacy of our method.

q-bio.BM↗

arXiv2021

CIZSL++: Creativity Inspired Generative Zero-Shot Learning

Zero-shot learning (ZSL) aims at understanding unseen categories with no training examples from class-level descriptions. To improve the discriminative power of ZSL, we model the visual learning process of unseen categories with inspiration from the psychology of human creativity for producing novel art. First, we propose CIZSL-v1 as a creativity inspired model for generative ZSL. We relate ZSL to human creativity by observing that ZSL is about recognizing the unseen, and creativity is about creating a likable unseen. We introduce a learning signal inspired by creativity literature that explores the unseen space with hallucinated class-descriptions and encourages careful deviation of their visual feature generations from seen classes while allowing knowledge transfer from seen to unseen classes. Second, CIZSL-v2 is proposed as an improved version of CIZSL-v1 for generative zero-shot learning. CIZSL-v2 consists of an investigation of additional inductive losses for unseen classes along with a semantic guided discriminator. Empirically, we show consistently that CIZSL losses can improve generative ZSL models on the challenging task of generalized ZSL from a noisy text on CUB and NABirds datasets. We also show the advantage of our approach to Attribute-based ZSL on AwA2, aPY, and SUN datasets. We also show that CIZSL-v2 has improved performance compared to CIZSL-v1.

cs.CV↗

arXiv2021

Search for dark photon and dark matter signatures around electron-positron colliders

The search for a dark photon produced at $e^{+}e^{-}$ colliders which subsequently decays into inelastic dark matter particles, is discussed. The heavier dark matter decays into a pair of visible charged particles and a lighter dark matter particle after traveling some distance. The visible decay products can be recorded by a dark matter detector made of emulsions and gas detectors, placed near the main $e^{+}e^{-}$ detector. This setup can not only explore new parameter regions not reached before, but also re-open some regions thought to be excluded by previous experimental data. The physics potential for such a detector around BESIII and Belle II is presented.

hep-ph↗

arXiv2020

Experimental Analysis of Legendre Decomposition in Machine Learning

In this technical report, we analyze Legendre decomposition for non-negative tensor in theory and application. In theory, the properties of dual parameters and dually flat manifold in Legendre decomposition are reviewed, and the process of tensor projection and parameter updating is analyzed. In application, a series of verification experiments and clustering experiments with parameters on submanifold were carried out, hoping to find an effective lower dimensional representation of the input tensor. The experimental results show that the parameters on submanifold have no ability to be directly used as low-rank representations. Combined with analysis, we connect Legendre decomposition with neural networks and low-rank representation applications, and put forward some promising prospects.

cs.LG↗

arXiv2020

CosmoVAE: Variational Autoencoder for CMB Image Inpainting

Cosmic microwave background radiation (CMB) is critical to the understanding of the early universe and precise estimation of cosmological constants. Due to the contamination of thermal dust noise in the galaxy, the CMB map that is an image on the two-dimensional sphere has missing observations, mainly concentrated on the equatorial region. The noise of the CMB map has a significant impact on the estimation precision for cosmological parameters. Inpainting the CMB map can effectively reduce the uncertainty of parametric estimation. In this paper, we propose a deep learning-based variational autoencoder --- CosmoVAE, to restoring the missing observations of the CMB map. The input and output of CosmoVAE are square images. To generate training, validation, and test data sets, we segment the full-sky CMB map into many small images by Cartesian projection. CosmoVAE assigns physical quantities to the parameters of the VAE network by using the angular power spectrum of the Gaussian random field as latent variables. CosmoVAE adopts a new loss function to improve the learning performance of the model, which consists of $\ell_1$ reconstruction loss, Kullback-Leibler divergence between the posterior distribution of encoder network and the prior distribution of latent variables, perceptual loss, and total-variation regularizer. The proposed model achieves state of the art performance for Planck \texttt{Commander} 2018 CMB map inpainting.

eess.IV↗

arXiv2020

Deep Learning Based Unsupervised and Semi-supervised Classification for Keratoconus

The transparent cornea is the window of the eye, facilitating the entry of light rays and controlling focusing the movement of the light within the eye. The cornea is critical, contributing to 75% of the refractive power of the eye. Keratoconus is a progressive and multifactorial corneal degenerative disease affecting 1 in 2000 individuals worldwide. Currently, there is no cure for keratoconus other than corneal transplantation for advanced stage keratoconus or corneal cross-linking, which can only halt KC progression. The ability to accurately identify subtle KC or KC progression is of vital clinical significance. To date, there has been little consensus on a useful model to classify KC patients, which therefore inhibits the ability to predict disease progression accurately. In this paper, we utilised machine learning to analyse data from 124 KC patients, including topographical and clinical variables. Both supervised multilayer perceptron and unsupervised variational autoencoder models were used to classify KC patients with reference to the existing Amsler-Krumeich (A-K) classification system. Both methods result in high accuracy, with the unsupervised method showing better performance. The result showed that the unsupervised method with a selection of 29 variables could be a powerful tool to provide an automatic classification tool for clinicians. These outcomes provide a platform for additional analysis for the progression and treatment of keratoconus.

stat.ML↗

arXiv2019

Feature Selective Small Object Detection via Knowledge-based Recurrent Attentive Neural Network

At present, the performance of deep neural network in general object detection is comparable to or even surpasses that of human beings. However, due to the limitations of deep learning itself, the small proportion of feature pixels, and the occurence of blur and occlusion, the detection of small objects in complex scenes is still an open question. But we can not deny that real-time and accurate object detection is fundamental to automatic perception and subsequent perception-based decision-making and planning tasks of autonomous driving. Considering the characteristics of small objects in autonomous driving scene, we proposed a novel method named KB-RANN, which based on domain knowledge, intuitive experience and feature attentive selection. It can focus on particular parts of image features, and then it tries to stress the importance of these features and strengthenes the learning parameters of them. Our comparative experiments on KITTI and COCO datasets show that our proposed method can achieve considerable results both in speed and accuracy, and can improve the effect of small object detection through self-selection of important features and continuous enhancement of proposed method, and deployed it in our self-developed autonomous driving car.

cs.CV↗

arXiv2018

Things that go bump in the night: From $J/ψϕ$ to other mass spectrum

This article summarizes a brief development of exotic mesons with Vector-Vector (VV) final states starting from the $J/ψϕ$ mass spectrum, as well as extensions to other final states for strong-interaction physics and physics beyond standard model. These VV final states are very suitable to be studied at CEPC through associate production and two-photon production, as well as a visionary low energy photon collider.

hep-ph↗

arXiv2013

Experimental Review of Structures in the $J/ψϕ$ Mass Spectrum

The discovery of numerous new charmonium-like structures since 2003 have revitalized interest in exotic meson spectroscopy. These structures do not fit easily into the conventional charmonium model, and proposals like four-quark states, hybrids, and re-scattering effects have been suggested as explanations. Since 2009, several new structures were reported in the $J/ψϕ$ mass spectrum with the following characteristics: they are the first ones reported decaying into two heavy mesons which contain both a $c\bar{c}$ pair and a $s\bar{s}$ pair; and their masses are well beyond the open charm pair threshold. Conventional $c\bar{c}$ states with a mass beyond the $J/ψϕ$ threshold are not expected to decay into this channel and the width is expected to be large, thus they are good candidates for exotic mesons. My focus in this article is to review the recent developments on the structures in the $J/ψϕ$ mass spectrum from CDF, Belle and LHCb.

hep-ex↗

arXiv2013

Search for Single and Pair-Production of Dijet Resonances with the CMS Detector

Searches for new physics in the single and paired dijet mass spectrum are performed using data collected by the CMS experiment at the LHC at a collision energy of sqrt{s}=7 or sqrt{s}=8 TeV. No evidence for new physics is found and upper limits are set for various models. At 95% confidence level, a string resonance in the single dijet spectrum is excluded for masses between 1 and 4.7 TeV and, for the first time, a coloron in the paired dijet spectrum is excluded for masses between 250 and 740 GeV.

hep-ex↗