检索结果-内蒙古大学图书馆

Enhanced Adaptive Gradient Algorithms for Nonconvex-PL Minimax Optimization

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Huang, Feihu College of Computer Science and Technology Nanjing University of Aeronautics and Astro-nautics Nanjing China MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Nanjing China

In the paper, we study a class of nonconvex nonconcave minimax optimization problems (i.e., minx maxy f (x, y)), where f (x, y) is possible nonconvex in x, and it is nonconcave and satisfies the Polyak-Lojasiewicz (PL) condition in y. Moreover, we propose a class of enhanced momentum-based gradient descent ascent methods (i.e., MSGDA and AdaMSGDA) to solve these stochastic Nonconvex-PL minimax problems. In particular, our AdaMSGDA algorithm can use various adaptive learning rates in updating the variables x and y without relying on any global and coordinate-wise adaptive learning rates. Theoretically, we present an effective convergence analysis framework for our methods. Specifically, we prove that our MSGDA and AdaMSGDA methods have the best known sample (gradient) complexity of O(ǫ−3) only requiring one sample at each loop in finding an ǫ-stationary solution (i.e., Ek∇F (x)k ≤ ǫ, where F (x) = maxy f (x, y)). This manuscript commemorates the mathematician Boris Polyak (1935-2023). © 2023, CC BY-NC-SA.

关键词： Stochastic systems

Characteristic AI Agents via Large Language Models

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wang, Xi Dai, Hongliang Gao, Shen Li, Piji College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics China MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Nanjing China School of Computer Science and Technology Shandong University China

The advancement of Large Language Models (LLMs) has led to significant enhancements in the performance of chatbot systems. Many researchers have dedicated their efforts to the development of bringing characteristics to chatbots. While there have been commercial products for developing role-driven chatbots using LLMs, it is worth noting that academic research in this area remains relatively scarce. Our research focuses on investigating the performance of LLMs in constructing Characteristic AI Agents by simulating real-life individuals across different settings. Current investigations have primarily focused on act on roles with simple profiles. In response to this research gap, we create a benchmark for the characteristic AI agents task, including dataset, techniques, and evaluation metrics. A dataset called "Character100" is built for this benchmark, comprising the most-visited people on Wikipedia for language models to role-play. With the constructed dataset, we conduct comprehensive assessment of LLMs across various settings. In addition, we devise a set of automatic metrics for quantitative performance evaluation. The experimental results underscore the potential directions for further improvement in the capabilities of LLMs in constructing characteristic AI agents. The benchmark is available at https://***/nuaa-nlp/Character100. © 2024, CC0.

关键词： Computational linguistics

Guidance Not Obstruction: A Conjugate Consistent Enhanced Strategy for Domain Generalization

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Cao, Meng Chen, Songcan The MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Nanjing University of Aeronautics and Astronautics Nanjing210016 China The College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing210016 China

Domain generalization addresses domain shift in real-world applications. Most approaches adopt a domain angle, seeking invariant representation across domains by aligning their marginal distributions, irrespective of individual classes, naturally leading to insufficient exploration of discriminative information. Switching to a class angle, we find that multiple domain-related peaks or clusters within the same individual classes must emerge due to distribution shift. In other words, marginal alignment does not guarantee conditional alignment, leading to suboptimal generalization. Therefore, we argue that acquiring discriminative generalization between classes within domains is crucial. In contrast to seeking distribution alignment, we endeavor to safeguard domain-related between-class discrimination. To this end, we devise a novel Conjugate Consistent Enhanced Module, namely Con2EM, based on a distribution over domains, i.e., a meta-distribution. Specifically, we employ a novel distribution-level Universum strategy to generate supplementary diverse domain-related class-conditional distributions, thereby enhancing generalization. This allows us to resample from these generated distributions to provide feedback to the primordial instance-level classifier, further improving its adaptability to the target-agnostic. To ensure generation accuracy, we establish an additional distribution-level classifier to regularize these conditional distributions. Extensive experiments have been conducted to demonstrate its effectiveness and low computational cost compared to SOTAs. Copyright © 2024, The Authors. All rights reserved.

关键词：

PIE: Physics-inspired Low-light Enhancement

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Liang, Dong Xu, Zhengyan Li, Ling Wei, Mingqiang Chen, Songcan MIIT Key Laboratory of Pattern Analysis and Machine Intelligence College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing China Nanjing Universily of Aeronautics Astronautics Shenzhen Research Institute China

In this paper, we propose a physics-inspired contrastive learning paradigm for low-light enhancement, called PIE. PIE primarily addresses three issues: (i) To resolve the problem of existing learning-based methods often training a LLE model with strict pixel-correspondence image pairs, we eliminate the need for pixel-correspondence paired training data and instead train with unpaired images. (ii) To address the disregard for negative samples and the inadequacy of their generation in existing methods, we incorporate physics-inspired contrastive learning for LLE and design the Bag of Curves (BoC) method to generate more reasonable negative samples that closely adhere to the underlying physical imaging principle. (iii) To overcome the reliance on semantic ground truths in existing methods, we propose an unsupervised regional segmentation module, ensuring regional brightness consistency while eliminating the dependency on semantic ground truths. Overall, the proposed PIE can effectively learn from unpaired positive/negative samples and smoothly realize non-semantic regional enhancement, which is clearly different from existing LLE efforts. Besides the novel architecture of PIE, we explore the gain of PIE on downstream tasks such as semantic segmentation and face detection. Training on readily available open data and extensive experiments demonstrate that our method surpasses the state-of-the-art LLE models over six independent cross-scenes datasets. PIE runs fast with reasonable GFLOPs in test time, making it easy to use on mobile devices. Code available. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantics

Recovering from out-of-sample states via inverse dynamics in offline reinforcement learning 23

学校读者我要写书评

暂无评论

Recovering from out-of-sample states via inverse dynamics in...

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Ke Jiang Jia-yu Yao Xiaoyang Tan College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics and MIIT Key Laboratory of Pattern Analysis and Machine Intelligence School of Electronic and Computer Engineering Peking University

We deal with the state distributional shift problem commonly encountered in offline reinforcement learning during test, where the agent tends to take unreliable actions at out-of-sample (unseen) states. Our idea is to encourage the agent to follow the so called state recovery principle when taking actions, i.e., besides long-term return, the immediate consequences of the current action should also be taken into account and those capable of recovering the state distribution of the behavior policy are preferred. For this purpose, an inverse dynamics model is learned and employed to guide the state recovery behavior of the new policy. Theoretically, we show that the proposed method helps aligning the transited state distribution of the new policy with the offline dataset at out-of-sample states, without the need of explicitly predicting the transited state distribution, which is usually difficult in high-dimensional and complicated environments. The effectiveness and feasibility of the proposed method is demonstrated with the state-of-the-art performance on the general offline RL benchmarks.

关键词：

Relative Difficulty Distillation for Semantic Segmentation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Liang, Dong Sun, Yue Du, Yun Chen, Songcan Huang, Sheng-Jun MIIT Key Laboratory of Pattern Analysis and Machine Intelligence College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing211106 China Nanjing University of Aeronautics Astronautics Shenzhen Research Institute China

Current knowledge distillation (KD) methods primarily focus on transferring various structured knowledge and designing corresponding optimization goals to encourage the student network to imitate the output of the teacher network. However, introducing too many additional optimization objectives may lead to unstable training, such as gradient conflicts. Moreover, these methods ignored the guidelines of relative learning difficulty between the teacher and student networks. Inspired by human cognitive science, in this paper, we redefine knowledge from a new perspective – the student and teacher networks’ relative difficulty of samples, and propose a pixel-level KD paradigm for semantic segmentation named Relative Difficulty Distillation (RDD). We propose a two-stage RDD framework: Teacher-Full Evaluated RDD (TFE-RDD) and Teacher-Student Evaluated RDD (TSE-RDD). RDD allows the teacher network to provide effective guidance on learning focus without additional optimization goals, thus avoiding adjusting learning weights for multiple losses. Extensive experimental evaluations using a general distillation loss function on popular datasets such as Cityscapes, CamVid, Pascal VOC, and ADE20k demonstrate the effectiveness of RDD against state-of-the-art KD methods. Additionally, our research showcases that RDD can integrate with existing KD methods to improve their upper performance bound. Codes are available at https://***/sunyueue/***. Copyright © 2024, The Authors. All rights reserved.

关键词： Distillation

Forgetting, Ignorance or Myopia: Revisiting key Challenges in Online Continual Learning

学校读者我要写书评

暂无评论

arXiv 2024年

Online continual learning (OCL) requires the models to learn from constant, endless streams of data. While significant efforts have been made in this field, most were focused on mitigating the catastrophic forgetting issue to achieve better classification ability, at the cost of a much heavier training workload. They overlooked that in real-world scenarios, e.g., in high-speed data stream environments, data do not pause to accommodate slow models. In this paper, we emphasize that model throughput– defined as the maximum number of training samples that a model can process within a unit of time – is equally important. It directly limits how much data a model can utilize and presents a challenging dilemma for current methods. With this understanding, we revisit key challenges in OCL from both empirical and theoretical perspectives, highlighting two critical issues beyond the well-documented catastrophic forgetting: (i) Model’s ignorance: the single-pass nature of OCL challenges models to learn effective features within constrained training time and storage capacity, leading to a trade-off between effective learning and model throughput;(ii) Model’s myopia: the local learning nature of OCL on the current task leads the model to adopt overly simplified, task-specific features and excessively sparse classifier, resulting in the gap between the optimal solution for the current task and the global objective. To tackle these issues, we propose the Non-sparse Classifier Evolution framework (NsCE) to facilitate effective global discriminative feature learning with minimal time cost. NsCE integrates non-sparse maximum separation regularization and targeted experience replay techniques with the help of pre-trained models, enabling rapid acquisition of new globally discriminative features. Extensive experiments demonstrate the substantial improvements of our framework in performance, throughput and real-world practicality. © 2024, CC BY.

关键词： Contrastive Learning

XL2Bench: A Benchmark for Extremely Long Context Understanding with Long-range Dependencies

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Ni, Xuanfan Cai, Hengyi Wei, Xiaochi Wang, Shuaiqiang Yin, Dawei Li, Piji Nanjing University of Aeronautics and Astronautics Nanjing China MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Nanjing China Institute of Computing Technology CAS Beijing China Baidu Inc. Beijing China

Large Language Models (LLMs) have demonstrated remarkable performance across diverse tasks but are constrained by their small context window sizes. Various efforts have been proposed to expand the context window to accommodate even up to 200K input tokens. Meanwhile, building high-quality benchmarks with much longer text lengths and more demanding tasks to provide comprehensive evaluations is of immense practical interest to facilitate long context understanding research of LLMs. However, prior benchmarks create datasets that ostensibly cater to long-text comprehension by expanding the input of traditional tasks, which falls short to exhibit the unique characteristics of long-text understanding, including long dependency tasks and longer text length compatible with modern LLMs’ context window size. In this paper, we introduce a benchmark for eXtremely Long context understanding with Long-range dependencies, XL2Bench, which includes three scenarios—Fiction Reading, Paper Reading, and Law Reading—and four tasks of increasing complexity: Memory Retrieval, Detailed Understanding, Overall Understanding, and Open-ended Generation, covering 27 subtasks in English and Chinese. It has an average length of 100K+ words (English) and 200K+ characters (Chinese). Evaluating six leading LLMs on XL2Bench, we find that their performance significantly lags behind human levels. Moreover, the observed decline in performance across both the original and enhanced datasets underscores the efficacy of our approach to mitigating data contamination. © 2024, CC BY.

关键词： Benchmarking

StructSR: Refuse Spurious Details in Real-World Image Super-Resolution

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Li, Yachao Liang, Dong Ding, Tianyu Huang, Sheng-Jun College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Collaborative Innovation Center of Novel Software Technology and Industrialization Nanjing211106 China Microsoft Washington United States

Diffusion-based models have shown great promise in real-world image super-resolution (Real-ISR), but often generate content with structural errors and spurious texture details due to the empirical priors and illusions of these models. To address this issue, we introduce StructSR, a simple, effective, and plug-and-play method that enhances structural fidelity and suppresses spurious details for diffusion-based Real-ISR. StructSR operates without the need for additional fine-tuning, external model priors, or high-level semantic knowledge. At its core is the Structure-Aware Screening (SAS) mechanism, which identifies the image with the highest structural similarity to the low-resolution (LR) input in the early inference stage, allowing us to leverage it as a historical structure knowledge to suppress the generation of spurious details. By intervening in the diffusion inference process, StructSR seamlessly integrates with existing diffusion-based Real-ISR models. Our experimental results demonstrate that StructSR significantly improves the fidelity of structure and texture, improving the PSNR and SSIM metrics by an average of 5.27% and 9.36% on a synthetic dataset (DIV2KVal) and 4.13% and 8.64% on two real-world datasets (RealSR and DRealSR) when integrated with four state-of-the-art diffusion-based Real-ISR methods. Code - https://***/LYCEXE/StructSR. Copyright © 2025, The Authors. All rights reserved.

关键词： Inference engines