arXiv subjects

Xin Liu

Publications and source records attributed to Xin Liu.

At least 451 records · Page 25Linked to original sources

arXiv2024

Singular value decompositions of third-order reduced biquaternion tensors

In this paper, we introduce the applications of third-order reduced biquaternion tensors in color video processing. We first develop algorithms for computing the singular value decomposition (SVD) of a third-order reduced biquaternion tensor via a new Ht-product. As theoretical applications, we define the Moore-Penrose inverse of a third-order reduced biquaternion tensor and develop its characterizations. In addition, we discuss the general (or Hermitian) solutions to reduced biquaternion tensor equation $\mathcal{A}\ast_{Ht} \mathcal{X}=\mathcal{B}$ as well as its least-square solution. Finally, we compress the color video by this SVD, and the experimental data shows that our method is faster than the compared scheme.

math.NA↗

arXiv2024

Improving Arabic Multi-Label Emotion Classification using Stacked Embeddings and Hybrid Loss Function

In multi-label emotion classification, particularly for low-resource languages like Arabic, the challenges of class imbalance and label correlation hinder model performance, especially in accurately predicting minority emotions. To address these issues, this study proposes a novel approach that combines stacked embeddings, meta-learning, and a hybrid loss function to enhance multi-label emotion classification for the Arabic language. The study extracts contextual embeddings from three fine-tuned language models-ArabicBERT, MarBERT, and AraBERT-which are then stacked to form enriched embeddings. A meta-learner is trained on these stacked embeddings, and the resulting concatenated representations are provided as input to a Bi-LSTM model, followed by a fully connected neural network for multi-label classification. To further improve performance, a hybrid loss function is introduced, incorporating class weighting, label correlation matrix, and contrastive learning, effectively addressing class imbalances and improving the handling of label correlations. Extensive experiments validate the proposed model's performance across key metrics such as Precision, Recall, F1-Score, Jaccard Accuracy, and Hamming Loss. The class-wise performance analysis demonstrates the hybrid loss function's ability to significantly reduce disparities between majority and minority classes, resulting in a more balanced emotion classification. An ablation study highlights the contribution of each component, showing the superiority of the model compared to baseline approaches and other loss functions. This study not only advances multi-label emotion classification for Arabic but also presents a generalizable framework that can be adapted to other languages and domains, providing a significant step forward in addressing the challenges of low-resource emotion classification tasks.

cs.CV↗

arXiv2024

PICZL: Image-based Photometric Redshifts for AGN

Computing photo-z for AGN is challenging, primarily due to the interplay of relative emissions associated with the SMBH and its host galaxy. SED fitting methods, effective in pencil-beam surveys, face limitations in all-sky surveys with fewer bands available, lacking the ability to capture the AGN contribution to the SED accurately. This limitation affects the many 10s of millions of AGN clearly singled out and identified by SRG/eROSITA. Our goal is to significantly enhance photometric redshift performance for AGN in all-sky surveys while avoiding the need to merge multiple data sets. Instead, we employ readily available data products from the 10th Data Release of the Imaging Legacy Survey for DESI, covering > 20,000 deg$^{2}$ with deep images and catalog-based photometry in the grizW1-W4 bands. We introduce PICZL, a machine-learning algorithm leveraging an ensemble of CNNs. Utilizing a cross-channel approach, the algorithm integrates distinct SED features from images with those obtained from catalog-level data. Full probability distributions are achieved via the integration of Gaussian mixture models. On a validation sample of 8098 AGN, PICZL achieves a variance $σ_{\textrm{NMAD}}$ of 4.5% with an outlier fraction $η$ of 5.6%, outperforming previous attempts to compute accurate photo-z for AGN using ML. We highlight that the model's performance depends on many variables, predominantly the depth of the data. A thorough evaluation of these dependencies is presented in the paper. Our streamlined methodology maintains consistent performance across the entire survey area when accounting for differing data quality. The same approach can be adopted for future deep photometric surveys such as LSST and Euclid, showcasing its potential for wide-scale realisation. With this paper, we release updated photo-z (including errors) for the XMM-SERVS W-CDF-S, ELAIS-S1 and LSS fields.

astro-ph.GA↗

arXiv2024

Enhancing Language Model Factuality via Activation-Based Confidence Calibration and Guided Decoding

Calibrating language models (LMs) aligns their generation confidence with the actual likelihood of answer correctness, which can inform users about LMs' reliability and mitigate hallucinated content. However, prior calibration methods, such as self-consistency-based and logit-based approaches, are either limited in inference-time efficiency or fall short of providing informative signals. Moreover, simply filtering out low-confidence responses reduces the LM's helpfulness when the answers are correct. Therefore, effectively using calibration techniques to enhance an LM's factuality remains an unsolved challenge. In this paper, we first propose an activation-based calibration method, ActCab, which trains a linear layer on top of the LM's last-layer activations that can better capture the representations of knowledge. Built on top of ActCab, we further propose CoDec, a confidence-guided decoding strategy to elicit truthful answers with high confidence from LMs. By evaluating on five popular QA benchmarks, ActCab achieves superior calibration performance than all competitive baselines, e.g., by reducing the average expected calibration error (ECE) score by up to 39%. Further experiments on CoDec show consistent improvements in several LMs' factuality on challenging QA datasets, such as TruthfulQA, highlighting the value of confidence signals in enhancing factuality.

cs.CL↗

arXiv2024

A Systematic Search for Candidate Supermassive Black Hole Binaries Using Periodic Mid-Infrared Light Curves of Active Galactic Nuclei

Periodic variability in active galactic nuclei (AGNs) is a promising method for studying sub-parsec supermassive black hole binaries (SMBHBs), which are a challenging detection target. While extensive searches have been made in the optical, X-ray and gamma-ray bands, systematic infrared (IR) studies remain limited. Using data from the Wide-field Infrared Survey Explorer (WISE), which provides unique decade-long mid-IR light curves with a six-month cadence, we have conducted the first systematic search for SMBHB candidates based on IR periodicity. Analyzing a parent sample of 48,932 objects selected from about half a million AGNs, we have identified 28 candidate periodic AGNs with periods ranging from 1,268 to 2,437 days (in the observer frame) by fitting their WISE light curves with sinusoidal functions. However, our mock simulation of the parent sample indicates that stochastic variability can actually produce a similar number of periodic sources, underscoring the difficulty in robustly identifying real periodic signals with WISE light curves, given their current sampling. Notably, we found no overlap between our sample and optical periodic sources, which can be explained by a distinct preference for certain periods due to selection bias. By combining archived data from different surveys, we have identified SDSS J140336.43+174136.1 as a candidate exhibiting periodic behavior in both optical and IR bands, a phenomenon that warrants further validation through observational tests. Our results highlight the potential of IR time-domain surveys, including future missions such as the Nancy Grace-Roman Space Telescope, for identifying periodic AGNs, but complementary tests are still needed to determine their physical origins such as SMBHBs.

astro-ph.HE↗

arXiv2024

Strichartz estimates for orthonormal functions and convergence problem of density functions of Boussinesq operator on manifolds

This paper is devoted to studying the maximal-in-time estimates and Strichartz estimates for orthonormal functions and convergence problem of density functions related to Boussinesq operator on manifolds. Firstly, we present the pointwise convergence of density function related to Boussinesq operator with $γ_{0}\in\mathfrak{S}^β(\dot{H}^{\frac{1}{4}}(\mathbf{R}))(β<2)$ with the aid of the maximal-in-time estimate related to Boussinesq operator with orthonormal function on $\R$. Secondly, we present the pointwise convergence of density function related to Boussinesq operator with $γ_{0}\in\mathfrak{S}^β(\dot{H}^{s})(\frac{d}{4}\leq s<\frac{d}{2},\, 0<α\leq d, 1\leqβ<\fracα{d-2s})$ with the aid of the maximal-in-time estimates related to Boussinesq operator with orthonormal function on the unit ball $\mathbf{B}^{d}(d\geq1)$ established in this paper; we also present the Hausdorff dimension of the divergence set of density function related to Boussinesq operator $dim_{H}D(γ_{0})\leq (d-2s)β$. Thirdly, we show the Strichartz estimates for orthonormal functions and Schatten bound with space-time norms related to Boussinesq operator on $\mathbf{T}$ with the aid of the noncommutative-commutative interpolation theorems established in this paper, which are just Lemmas 3.1-3.4 in this paper; we also prove that Theorems 1.5, 1.6 are optimal. Finally, by using full randomization, we present the probabilistic convergence of density function related to Boussinesq operator on $\R$, $\mathbf{T}$ and $Θ=\{x\in\R^{3}:|x|<1\}$ with $γ_{0}\in\mathfrak{S}^{2}$.

math.AP↗

arXiv2024

Adversarially Trained Weighted Actor-Critic for Safe Offline Reinforcement Learning

We propose WSAC (Weighted Safe Actor-Critic), a novel algorithm for Safe Offline Reinforcement Learning (RL) under functional approximation, which can robustly optimize policies to improve upon an arbitrary reference policy with limited data coverage. WSAC is designed as a two-player Stackelberg game to optimize a refined objective function. The actor optimizes the policy against two adversarially trained value critics with small importance-weighted Bellman errors, which focus on scenarios where the actor's performance is inferior to the reference policy. In theory, we demonstrate that when the actor employs a no-regret optimization oracle, WSAC achieves a number of guarantees: (i) For the first time in the safe offline RL setting, we establish that WSAC can produce a policy that outperforms any reference policy while maintaining the same level of safety, which is critical to designing a safe algorithm for offline RL. (ii) WSAC achieves the optimal statistical convergence rate of $1/\sqrt{N}$ to the reference policy, where $N$ is the size of the offline dataset. (iii) We theoretically show that WSAC guarantees a safe policy improvement across a broad range of hyperparameters that control the degree of pessimism, indicating its practical robustness. Additionally, we offer a practical version of WSAC and compare it with existing state-of-the-art safe offline RL algorithms in several continuous control environments. WSAC outperforms all baselines across a range of tasks, supporting the theoretical results.

cs.LG↗

arXiv2024

Shopping MMLU: A Massive Multi-Task Online Shopping Benchmark for Large Language Models

Online shopping is a complex multi-task, few-shot learning problem with a wide and evolving range of entities, relations, and tasks. However, existing models and benchmarks are commonly tailored to specific tasks, falling short of capturing the full complexity of online shopping. Large Language Models (LLMs), with their multi-task and few-shot learning abilities, have the potential to profoundly transform online shopping by alleviating task-specific engineering efforts and by providing users with interactive conversations. Despite the potential, LLMs face unique challenges in online shopping, such as domain-specific concepts, implicit knowledge, and heterogeneous user behaviors. Motivated by the potential and challenges, we propose Shopping MMLU, a diverse multi-task online shopping benchmark derived from real-world Amazon data. Shopping MMLU consists of 57 tasks covering 4 major shopping skills: concept understanding, knowledge reasoning, user behavior alignment, and multi-linguality, and can thus comprehensively evaluate the abilities of LLMs as general shop assistants. With Shopping MMLU, we benchmark over 20 existing LLMs and uncover valuable insights about practices and prospects of building versatile LLM-based shop assistants. Shopping MMLU can be publicly accessed at https://github.com/KL4805/ShoppingMMLU. In addition, with Shopping MMLU, we host a competition in KDD Cup 2024 with over 500 participating teams. The winning solutions and the associated workshop can be accessed at our website https://amazon-kddcup24.github.io/.

cs.LG↗

arXiv2024

On the Convergence of Federated Averaging under Partial Participation for Over-parameterized Neural Networks

Federated learning (FL) is a widely employed distributed paradigm for collaboratively training machine learning models from multiple clients without sharing local data. In practice, FL encounters challenges in dealing with partial client participation due to the limited bandwidth, intermittent connection and strict synchronized delay. Simultaneously, there exist few theoretical convergence guarantees in this practical setting, especially when associated with the non-convex optimization of neural networks. To bridge this gap, we focus on the training problem of federated averaging (FedAvg) method for two canonical models: a deep linear network and a two-layer ReLU network. Under the over-parameterized assumption, we provably show that FedAvg converges to a global minimum at a linear rate $\mathcal{O}\left((1-\frac{min_{i \in [t]}|S_i|}{N^2})^t\right)$ after $t$ iterations, where $N$ is the number of clients and $|S_i|$ is the number of the participated clients in the $i$-th iteration. Experimental evaluations confirm our theoretical results.

cs.LG↗

arXiv2024

A Stock Price Prediction Approach Based on Time Series Decomposition and Multi-Scale CNN using OHLCT Images

Recently, deep learning in stock prediction has become an important branch. Image-based methods show potential by capturing complex visual patterns and spatial correlations, offering advantages in interpretability over time series models. However, image-based approaches are more prone to overfitting, hindering robust predictive performance. To improve accuracy, this paper proposes a novel method, named Sequence-based Multi-scale Fusion Regression Convolutional Neural Network (SMSFR-CNN), for predicting stock price movements in the China A-share market. By utilizing CNN to learn sequential features and combining them with image features, we improve the accuracy of stock trend prediction on the A-share market stock dataset. This approach reduces the search space for image features, stabilizes, and accelerates the training process. Extensive comparative experiments on 4,454 A-share stocks show that the model achieves a 61.15% positive predictive value and a 63.37% negative predictive value for the next 5 days, resulting in a total profit of 165.09%.

cs.LG↗

arXiv2024

FLUX: Fast Software-based Communication Overlap On GPUs Through Kernel Fusion

Large deep learning models have demonstrated strong ability to solve many tasks across a wide range of applications. Those large models typically require training and inference to be distributed. Tensor parallelism is a common technique partitioning computation of an operation or layer across devices to overcome the memory capacity limitation of a single processor, and/or to accelerate computation to meet a certain latency requirement. However, this kind of parallelism introduces additional communication that might contribute a significant portion of overall runtime. Thus limits scalability of this technique within a group of devices with high speed interconnects, such as GPUs with NVLinks in a node. This paper proposes a novel method, Flux, to significantly hide communication latencies with dependent computations for GPUs. Flux over-decomposes communication and computation operations into much finer-grained operations and further fuses them into a larger kernel to effectively hide communication without compromising kernel efficiency. Flux can potentially overlap up to 96% of communication given a fused kernel. Overall, it can achieve up to 1.24x speedups for training over Megatron-LM on a cluster of 128 GPUs with various GPU generations and interconnects, and up to 1.66x and 1.30x speedups for prefill and decoding inference over vLLM on a cluster with 8 GPUs with various GPU generations and interconnects.

cs.LG↗

arXiv2024

Fast generation of arbitrary optical focus array

We report a novel method to generate arbitrary optical focus arrays (OFAs). Our approach rapidly produces computer-generated holograms (CGHs) to precisely control the positions and the intensities of the foci. This is achieved by replacing the fast Fourier transform (FFT) operation in the conventional iterative Fourier-transform algorithm (IFTA) with a linear algebra one, identifying/removing zero elements from the matrices, and employing a generalized weighting strategy. On the premise of accelerating the calculation speed by >70 times, we demonstrate OFA with 99% intensity precision in the experiment. Our method proves effective and is applicable for the systems in which real-time OFA generation is essential.

physics.optics↗

arXiv2024

MPDS: A Movie Posters Dataset for Image Generation with Diffusion Model

Movie posters are vital for captivating audiences, conveying themes, and driving market competition in the film industry. While traditional designs are laborious, intelligent generation technology offers efficiency gains and design enhancements. Despite exciting progress in image generation, current models often fall short in producing satisfactory poster results. The primary issue lies in the absence of specialized poster datasets for targeted model training. In this work, we propose a Movie Posters DataSet (MPDS), tailored for text-to-image generation models to revolutionize poster production. As dedicated to posters, MPDS stands out as the first image-text pair dataset to our knowledge, composing of 373k+ image-text pairs and 8k+ actor images (covering 4k+ actors). Detailed poster descriptions, such as movie titles, genres, casts, and synopses, are meticulously organized and standardized based on public movie synopsis, also named movie-synopsis prompt. To bolster poster descriptions as well as reduce differences from movie synopsis, further, we leverage a large-scale vision-language model to automatically produce vision-perceptive prompts for each poster, then perform manual rectification and integration with movie-synopsis prompt. In addition, we introduce a prompt of poster captions to exhibit text elements in posters like actor names and movie titles. For movie poster generation, we develop a multi-condition diffusion framework that takes poster prompt, poster caption, and actor image (for personalization) as inputs, yielding excellent results through the learning of a diffusion model. Experiments demonstrate the valuable role of our proposed MPDS dataset in advancing personalized movie poster generation. MPDS is available at https://anonymous.4open.science/r/MPDS-373k-BD3B.

cs.CV↗

arXiv2024

Scaling Wearable Foundation Models

Wearable sensors have become ubiquitous thanks to a variety of health tracking features. The resulting continuous and longitudinal measurements from everyday life generate large volumes of data; however, making sense of these observations for scientific and actionable insights is non-trivial. Inspired by the empirical success of generative modeling, where large neural networks learn powerful representations from vast amounts of text, image, video, or audio data, we investigate the scaling properties of sensor foundation models across compute, data, and model size. Using a dataset of up to 40 million hours of in-situ heart rate, heart rate variability, electrodermal activity, accelerometer, skin temperature, and altimeter per-minute data from over 165,000 people, we create LSM, a multimodal foundation model built on the largest wearable-signals dataset with the most extensive range of sensor modalities to date. Our results establish the scaling laws of LSM for tasks such as imputation, interpolation and extrapolation, both across time and sensor modalities. Moreover, we highlight how LSM enables sample-efficient downstream learning for tasks like exercise and activity recognition.

cs.LG↗

arXiv2024

Interpreting Inflammation Prediction Model via Tag-based Cohort Explanation

Machine learning is revolutionizing nutrition science by enabling systems to learn from data and make intelligent decisions. However, the complexity of these models often leads to challenges in understanding their decision-making processes, necessitating the development of explainability techniques to foster trust and increase model transparency. An under-explored type of explanation is cohort explanation, which provides explanations to groups of instances with similar characteristics. Unlike traditional methods that focus on individual explanations or global model behavior, cohort explainability bridges the gap by providing unique insights at an intermediate granularity. We propose a novel framework for identifying cohorts within a dataset based on local feature importance scores, aiming to generate concise descriptions of the clusters via tags. We evaluate our framework on a food-based inflammation prediction model and demonstrated that the framework can generate reliable explanations that match domain knowledge.

cs.LG↗

arXiv2024

Evidence of Cognitive Deficits andDevelopmental Advances in Generative AI: A Clock Drawing Test Analysis

Generative AI's rapid advancement sparks interest in its cognitive abilities, especially given its capacity for tasks like language understanding and code generation. This study explores how several recent GenAI models perform on the Clock Drawing Test (CDT), a neuropsychological assessment of visuospatial planning and organization. While models create clock-like drawings, they struggle with accurate time representation, showing deficits similar to mild-severe cognitive impairment (Wechsler, 2009). Errors include numerical sequencing issues, incorrect clock times, and irrelevant additions, despite accurate rendering of clock features. Only GPT 4 Turbo and Gemini Pro 1.5 produced the correct time, scoring like healthy individuals (4/4). A follow-up clock-reading test revealed only Sonnet 3.5 succeeded, suggesting drawing deficits stem from difficulty with numerical concepts. These findings may reflect weaknesses in visual-spatial understanding, working memory, or calculation, highlighting strengths in learned knowledge but weaknesses in reasoning. Comparing human and machine performance is crucial for understanding AI's cognitive capabilities and guiding development toward human-like cognitive functions.

cs.AI↗

arXiv2024

MoE-Pruner: Pruning Mixture-of-Experts Large Language Model using the Hints from Its Router

Mixture-of-Experts (MoE) architectures face challenges such as high memory consumption and redundancy in experts. Pruning MoE can reduce network weights while maintaining model performance. Motivated by the recent observation of emergent large magnitude features in Large Language Models (LLM) and MoE routing policy, we propose MoE-Pruner, a method that prunes weights with the smallest magnitudes multiplied by the corresponding input activations and router weights, on each output neuron. Our pruning method is one-shot, requiring no retraining or weight updates. We evaluate our method on Mixtral-8x7B and Mixtral-8x22B across multiple language benchmarks. Experimental results show that our pruning method significantly outperforms state-of-the-art LLM pruning methods. Furthermore, our pruned MoE models can benefit from a pretrained teacher model through expert-wise knowledge distillation, improving performance post-pruning. Experimental results demonstrate that the Mixtral-8x7B model with 50% sparsity maintains 99% of the performance of the original model after the expert-wise knowledge distillation.

cs.CL↗

arXiv2024

CDOpt: A Python Package for a Class of Riemannian Optimization

Optimization over the embedded submanifold defined by constraints $c(x) = 0$ has attracted much interest over the past few decades due to its wide applications in various areas. Plenty of related optimization packages have been developed based on Riemannian optimization approaches, which rely on some basic geometrical materials of Riemannian manifolds, including retractions, vector transports, etc. These geometrical materials can be challenging to determine in general. Existing packages only accommodate a few well-known manifolds whose geometrical materials are easily accessible. For other manifolds which are not contained in these packages, the users have to develop the geometric materials by themselves. In addition, it is not always tractable to adopt advanced features from various state-of-the-art unconstrained optimization solvers to Riemannian optimization approaches. We introduce CDOpt (available at https://cdopt.github.io/), a user-friendly Python package for a class Riemannian optimization. Based on constraint dissolving approaches, Riemannian optimization problems are transformed into their equivalent unconstrained counterparts in CDOpt. Therefore, solving Riemannian optimization problems through CDOpt directly benefits from various existing solvers and the rich expertise gained over decades for unconstrained optimization. Moreover, all the computations in CDOpt related to any manifold in question are conducted on its constraints expression, hence users can easily define new manifolds in CDOpt without any background on differential geometry. Furthermore, CDOpt extends the neural layers from PyTorch and Flax, thus allows users to train manifold constrained neural networks directly by the solvers for unconstrained optimization. Extensive numerical experiments demonstrate that CDOpt is highly efficient and robust in solving various classes of Riemannian optimization problems.

math.OC↗