Stochastic approximation (SA) that involves multiple coupled sequences, known as multiple-sequence SA (MSSA), finds diverse applications in the fields of signal processing and machine learning. However, existing theoretical understandings {of} MSSA are limited: the multi-timescale analysis implies a slow convergence rate, whereas the single-timescale analysis relies on a stringent fixed point smoothness assumption. This paper establishes tighter single-timescale analysis for MSSA, without assuming smoothness of the fixed points. Our theoretical findings reveal that, when all involved operators are strongly monotone, MSSA converges at a rate of $\tilde{\mathcal{O}}(K^{-1})$, where $K$ denotes the total number of iterations. In addition, when all involved operators are strongly monotone except for the main one, MSSA converges at a rate of $\mathcal{O}(K^{-\frac{1}{2}})$. These theoretical findings align with those established for single-sequence SA. Applying these theoretical findings to bilevel optimization and communication-efficient distributed learning offers relaxed assumptions and/or simpler algorithms with performance guarantees, as validated by numerical experiments.
相關內容
Continual Learning (CL) involves adapting the prior Deep Neural Network (DNN) knowledge to new tasks, without forgetting the old ones. However, modern CL techniques focus on provisioning memory capabilities to existing DNN models rather than designing new ones that are able to adapt according to the task at hand. This paper presents the novel Feedback Continual Learning Vision Transformer (FCL-ViT) that uses a feedback mechanism to generate real-time dynamic attention features tailored to the current task. The FCL-ViT operates in two Phases. In phase 1, the generic image features are produced and determine where the Transformer should attend on the current image. In phase 2, task-specific image features are generated that leverage dynamic attention. To this end, Tunable self-Attention Blocks (TABs) and Task Specific Blocks (TSBs) are introduced that operate in both phases and are responsible for tuning the TABs attention, respectively. The FCL-ViT surpasses state-of-the-art performance on Continual Learning compared to benchmark methods, while retaining a small number of trainable DNN parameters.
We propose MM-Vet, an evaluation benchmark that examines large multimodal models (LMMs) on complicated multimodal tasks. Recent LMMs have shown various intriguing abilities, such as solving math problems written on the blackboard, reasoning about events and celebrities in news images, and explaining visual jokes. Rapid model advancements pose challenges to evaluation benchmark development. Problems include: (1) How to systematically structure and evaluate the complicated multimodal tasks; (2) How to design evaluation metrics that work well across question and answer types; and (3) How to give model insights beyond a simple performance ranking. To this end, we present MM-Vet, designed based on the insight that the intriguing ability to solve complicated tasks is often achieved by a generalist model being able to integrate different core vision-language (VL) capabilities. MM-Vet defines 6 core VL capabilities and examines the 16 integrations of interest derived from the capability combination. For evaluation metrics, we propose an LLM-based evaluator for open-ended outputs. The evaluator enables the evaluation across different question types and answer styles, resulting in a unified scoring metric. We evaluate representative LMMs on MM-Vet, providing insights into the capabilities of different LMM system paradigms and models.
Current interactive segmentation approaches, inspired by the success of META's Segment Anything model, have achieved notable advancements, however, they come with substantial limitations that hinder their practical application in 3D radiological scenarios. These include unrealistic human interaction requirements, such as slice-by-slice operations for 2D models on 3D data, a lack of iterative interactive refinement, and insufficient evaluation experiments. These shortcomings prevent accurate assessment of model performance and lead to inconsistent outcomes across studies. The RadioActive benchmark overcomes these challenges by offering a comprehensive and reproducible evaluation of interactive segmentation methods in realistic, clinically relevant scenarios. It includes diverse datasets, target structures, and interactive segmentation methods, and provides a flexible, extendable codebase that allows seamless integration of new models and prompting strategies. We also introduce advanced prompting techniques to enable 2D models on 3D data by reducing the needed number of interaction steps, enabling a fair comparison. We show that surprisingly the performance of slice-wise prompted approaches can match native 3D methods, despite the domain gap. Our findings challenge the current literature and highlight that models not specifically trained on medical data can outperform the current specialized medical methods. By open-sourcing RadioActive, we invite the research community to integrate their models and prompting techniques, ensuring continuous and transparent evaluation of interactive segmentation models in 3D medical imaging.
Compared to supervised variable selection, the research on unsupervised variable selection is far behind. A forward partial-variable clustering full-variable loss (FPCFL) method is proposed for the corresponding challenges. An advantage is that the FPCFL method can distinguish active, redundant, and uninformative variables, which the previous methods cannot achieve. Theoretical and simulation studies show that the performance of a clustering method using all the variables can be worse if many uninformative variables are involved. Better results are expected if the uninformative variables are excluded. The research addresses a previous concern about how variable selection affects the performance of clustering. Rather than many previous methods attempting to select all the relevant variables, the proposed method selects a subset that can induce an equally good result. This phenomenon does not appear in the supervised variable selection problems.
Evolving from massive multiple-input multiple-output (MIMO) in current 5G communications, ultra-massive MIMO emerges as a seminal technology for fulfilling more stringent requirements of future 6G communications. However, widely-utilized phased arrays relying on active components make the implementation of ultra-massive MIMO in practice increasingly prohibitive from both cost and power consumption perspectives. In contrast, the development of reconfigurable holographic surface (RHS) provides a new paradigm to solve the above issue without the need of costly hardware components. By leveraging the holographic principle, the RHS serves as an ultra-thin and lightweight surface antenna integrated with the transceiver, which is a promising alternative to phased arrays for realizing ultra-massive MIMO. In this paper, we provide a comprehensive overview of the RHS, especially the RHS-aided communication and sensing. We first describe the basic concepts of RHS, and introduce its working principle and unique practical constraints. Moreover, we show how to utilize the RHS to achieve cost-efficient and high-performance wireless communication and sensing, and introduce the key technologies. In particular, we present the implementation of RHS with a wireless communication prototype, and report the experimental measurement results based on it. Finally, we outline some open challenges and potential future directions in this area.
Deep Neural Networks (DNNs) have revolutionized various fields, but their deployment on GPUs often leads to significant energy consumption. Unlike existing methods for reducing GPU energy consumption, which are either hardware-inflexible or limited by workload constraints, this paper addresses the problem at the GPU kernel level. We propose a novel search-based compilation method to generate energy-efficient GPU kernels by incorporating energy efficiency into the search process. To accelerate the energy evaluation process, we develop an accurate energy cost model based on high-level kernel features. Furthermore, we introduce a dynamic updating strategy for the energy cost model, reducing the need for on-device energy measurements and accelerating the search process. Our evaluation demonstrates that the proposed approach can generate GPU kernels with up to 21.69% reduced energy consumption while maintaining low latency.
Few-shot Knowledge Graph (KG) completion is a focus of current research, where each task aims at querying unseen facts of a relation given its few-shot reference entity pairs. Recent attempts solve this problem by learning static representations of entities and references, ignoring their dynamic properties, i.e., entities may exhibit diverse roles within task relations, and references may make different contributions to queries. This work proposes an adaptive attentional network for few-shot KG completion by learning adaptive entity and reference representations. Specifically, entities are modeled by an adaptive neighbor encoder to discern their task-oriented roles, while references are modeled by an adaptive query-aware aggregator to differentiate their contributions. Through the attention mechanism, both entities and references can capture their fine-grained semantic meanings, and thus render more expressive representations. This will be more predictive for knowledge acquisition in the few-shot scenario. Evaluation in link prediction on two public datasets shows that our approach achieves new state-of-the-art results with different few-shot sizes.
The problem of Multiple Object Tracking (MOT) consists in following the trajectory of different objects in a sequence, usually a video. In recent years, with the rise of Deep Learning, the algorithms that provide a solution to this problem have benefited from the representational power of deep models. This paper provides a comprehensive survey on works that employ Deep Learning models to solve the task of MOT on single-camera videos. Four main steps in MOT algorithms are identified, and an in-depth review of how Deep Learning was employed in each one of these stages is presented. A complete experimental comparison of the presented works on the three MOTChallenge datasets is also provided, identifying a number of similarities among the top-performing methods and presenting some possible future research directions.
With the capability of modeling bidirectional contexts, denoising autoencoding based pretraining like BERT achieves better performance than pretraining approaches based on autoregressive language modeling. However, relying on corrupting the input with masks, BERT neglects dependency between the masked positions and suffers from a pretrain-finetune discrepancy. In light of these pros and cons, we propose XLNet, a generalized autoregressive pretraining method that (1) enables learning bidirectional contexts by maximizing the expected likelihood over all permutations of the factorization order and (2) overcomes the limitations of BERT thanks to its autoregressive formulation. Furthermore, XLNet integrates ideas from Transformer-XL, the state-of-the-art autoregressive model, into pretraining. Empirically, XLNet outperforms BERT on 20 tasks, often by a large margin, and achieves state-of-the-art results on 18 tasks including question answering, natural language inference, sentiment analysis, and document ranking.
Multi-relation Question Answering is a challenging task, due to the requirement of elaborated analysis on questions and reasoning over multiple fact triples in knowledge base. In this paper, we present a novel model called Interpretable Reasoning Network that employs an interpretable, hop-by-hop reasoning process for question answering. The model dynamically decides which part of an input question should be analyzed at each hop; predicts a relation that corresponds to the current parsed results; utilizes the predicted relation to update the question representation and the state of the reasoning process; and then drives the next-hop reasoning. Experiments show that our model yields state-of-the-art results on two datasets. More interestingly, the model can offer traceable and observable intermediate predictions for reasoning analysis and failure diagnosis, thereby allowing manual manipulation in predicting the final answer.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191