Predicting the future trajectories of nearby objects plays a pivotal role in Robotics and Automation such as autonomous driving. While learning-based trajectory prediction methods have achieved remarkable performance on public benchmarks, the generalization ability of these approaches remains questionable. The poor generalizability on unseen domains, a well-recognized defect of data-driven approaches, can potentially harm the real-world performance of trajectory prediction models. We are thus motivated to improve generalization ability of models instead of merely pursuing high accuracy on average. Due to the lack of benchmarks for quantifying the generalization ability of trajectory predictors, we first construct a new benchmark called argoverse-shift, where the data distributions of domains are significantly different. Using this benchmark for evaluation, we identify that the domain shift problem seriously hinders the generalization of trajectory predictors since state-of-the-art approaches suffer from severe performance degradation when facing those out-of-distribution scenes. To enhance the robustness of models against domain shift problems, we propose a plug-and-play strategy for domain normalization in trajectory prediction. Our strategy utilizes the Frenet coordinate frame for modeling and can effectively narrow the domain gap of different scenes caused by the variety of road geometry and topology. Experiments show that our strategy noticeably boosts the prediction performance of the state-of-the-art in domains that were previously unseen to the models, thereby improving the generalization ability of data-driven trajectory prediction methods.
相關內容
The confluence of Federated Learning (FL) and Large Language Models (LLMs) is ushering in a new era in privacy-preserving natural language processing. However, the intensive memory requirements for fine-tuning LLMs pose significant challenges, especially when deploying on edge devices with limited computational resources. To circumvent this, we explore the novel integration of Memory-efficient Zeroth-Order Optimization within a federated setting, a synergy we denote as FedMeZO. Our study is the first to examine the theoretical underpinnings of FedMeZO in the context of LLMs, tackling key questions regarding the influence of large parameter spaces on optimization behavior, the establishment of convergence properties, and the identification of critical parameters for convergence to inform personalized federated strategies. Our extensive empirical evidence supports the theory, showing that FedMeZO not only converges faster than traditional first-order methods such as SGD but also significantly reduces GPU memory usage during training to levels comparable to those during inference. Moreover, the proposed personalized FL strategy that is built upon the theoretical insights to customize the client-wise learning rate can effectively accelerate loss reduction. We hope our work can help to bridge theoretical and practical aspects of federated fine-tuning for LLMs and facilitate further development and research.
An important prerequisite for autonomous robots is their ability to reliably grasp a wide variety of objects. Most state-of-the-art systems employ specialized or simple end-effectors, such as two-jaw grippers, which limit the range of objects to manipulate. Additionally, they conventionally require a structured and fully predictable environment while the vast majority of our world is complex, unstructured, and dynamic. This paper presents a novel approach to integrate a five-finger hand with visual servo control to enable dynamic grasping and compensate for external disturbances. The multi-fingered end-effector enhances the variety of possible grasps and manipulable objects. It is controlled by a deep learning based generative grasping network. The required virtual model of the unknown target object is iteratively completed by processing visual sensor data. Our experiments on real hardware confirm the system's capability to reliably grasp unknown dynamic target objects. To the best of our knowledge, this is the first method to achieve dynamic multi-fingered grasping for unknown objects. A video of the experiments is available at //youtu.be/5Ou6V_QMrNY.
Linear Convergence of Entropy-Regularized Natural Policy Gradient with Linear Function Approximation
Natural policy gradient (NPG) methods with entropy regularization achieve impressive empirical success in reinforcement learning problems with large state-action spaces. However, their convergence properties and the impact of entropy regularization remain elusive in the function approximation regime. In this paper, we establish finite-time convergence analyses of entropy-regularized NPG with linear function approximation under softmax parameterization. In particular, we prove that entropy-regularized NPG with averaging satisfies the \emph{persistence of excitation} condition, and achieves a fast convergence rate of $\tilde{O}(1/T)$ up to a function approximation error in regularized Markov decision processes. This convergence result does not require any a priori assumptions on the policies. Furthermore, under mild regularity conditions on the concentrability coefficient and basis vectors, we prove that entropy-regularized NPG exhibits \emph{linear convergence} up to a function approximation error.
The inherent diversity of computation types within individual Deep Neural Network (DNN) models imposes a corresponding need for a varied set of computation units within hardware processors. This diversity poses a significant constraint on computation efficiency during the execution of different neural networks. In this study, we present NeuralMatrix, a framework that transforms the computation of entire DNNs into linear matrix operations. This transformation seamlessly enables the execution of various DNN models using a single General-Purpose Matrix Multiplication (GEMM) accelerator. Extensive experimental results spanning different DNN models demonstrate that our approach preserves network accuracy while providing both generality and application-specific levels of computation efficiency. This allows a broad spectrum of DNN models to be executed using a single GEMM accelerator, eliminating the need for additional special function units.
Large Language Models (LLMs) play a pivotal role in generating vast arrays of narratives, facilitating a systematic exploration of their effectiveness for communicating life events in narrative form. In this study, we employ a zero-shot structured narrative prompt to generate 24,000 narratives using OpenAI's GPT-4. From this dataset, we manually classify 2,880 narratives and evaluate their validity in conveying birth, death, hiring, and firing events. Remarkably, 87.43% of the narratives sufficiently convey the intention of the structured prompt. To automate the identification of valid and invalid narratives, we train and validate nine Machine Learning models on the classified datasets. Leveraging these models, we extend our analysis to predict the classifications of the remaining 21,120 narratives. All the ML models excelled at classifying valid narratives as valid, but experienced challenges at simultaneously classifying invalid narratives as invalid. Our findings not only advance the study of LLM capabilities, limitations, and validity but also offer practical insights for narrative generation and natural language processing applications.
COVID Long Haul (CLH) is an emerging chronic illness with varied patient experiences. Our understanding of CLH is often limited to data from electronic health records (EHRs), such as diagnoses or problem lists, which do not capture the volatility and severity of symptoms or their impact. To better understand the unique presentation of CLH, we conducted a 3-month long cohort study with 14 CLH patients, collecting objective (EHR, daily Fitbit logs) and subjective (weekly surveys, interviews) data. Our findings reveal a complex presentation of symptoms, associated uncertainty, and the ensuing impact CLH has on patients' personal and professional lives. We identify patient needs, practices, and challenges around adhering to clinical recommendations, engaging with health data, and establishing "new normals" post COVID. We reflect on the potential found at the intersection of these various data streams and the persuasive heuristics possible when designing for this new population and their specific needs.
With the rise of complex cyber devices Cyber Forensics (CF) is facing many new challenges. For example, there are dozens of systems running on smartphones, each with more than millions of downloadable applications. Sifting through this large amount of data and making sense requires new techniques, such as from the field of Artificial Intelligence (AI). To apply these techniques successfully in CF, we need to justify and explain the results to the stakeholders of CF, such as forensic analysts and members of the court, for them to make an informed decision. If we want to apply AI successfully in CF, there is a need to develop trust in AI systems. Some other factors in accepting the use of AI in CF are to make AI authentic, interpretable, understandable, and interactive. This way, AI systems will be more acceptable to the public and ensure alignment with legal standards. An explainable AI (XAI) system can play this role in CF, and we call such a system XAI-CF. XAI-CF is indispensable and is still in its infancy. In this paper, we explore and make a case for the significance and advantages of XAI-CF. We strongly emphasize the need to build a successful and practical XAI-CF system and discuss some of the main requirements and prerequisites of such a system. We present a formal definition of the terms CF and XAI-CF and a comprehensive literature review of previous works that apply and utilize XAI to build and increase trust in CF. We discuss some challenges facing XAI-CF. We also provide some concrete solutions to these challenges. We identify key insights and future research directions for building XAI applications for CF. This paper is an effort to explore and familiarize the readers with the role of XAI applications in CF, and we believe that our work provides a promising basis for future researchers interested in XAI-CF.
Large language models (LLMs) have made fundamental contributions over the last a few years. To train an LLM, one needs to alternatingly run `forward' computations and `backward' computations. The forward computation can be viewed as attention function evaluation, and the backward computation can be viewed as a gradient computation. In previous work by [Alman and Song, NeurIPS 2023], it was proved that the forward step can be performed in almost-linear time in certain parameter regimes, but that there is no truly sub-quadratic time algorithm in the remaining parameter regimes unless the popular hypothesis SETH is false. In this work, we show nearly identical results for the harder-seeming problem of computing the gradient of loss function of one layer attention network, and thus for the entire process of LLM training. This completely characterizes the fine-grained complexity of every step of LLM training.
We present a new methodology for handling AI errors by introducing weakly supervised AI error correctors with a priori performance guarantees. These AI correctors are auxiliary maps whose role is to moderate the decisions of some previously constructed underlying classifier by either approving or rejecting its decisions. The rejection of a decision can be used as a signal to suggest abstaining from making a decision. A key technical focus of the work is in providing performance guarantees for these new AI correctors through bounds on the probabilities of incorrect decisions. These bounds are distribution agnostic and do not rely on assumptions on the data dimension. Our empirical example illustrates how the framework can be applied to improve the performance of an image classifier in a challenging real-world task where training data are scarce.
The dominating NLP paradigm of training a strong neural predictor to perform one task on a specific dataset has led to state-of-the-art performance in a variety of applications (eg. sentiment classification, span-prediction based question answering or machine translation). However, it builds upon the assumption that the data distribution is stationary, ie. that the data is sampled from a fixed distribution both at training and test time. This way of training is inconsistent with how we as humans are able to learn from and operate within a constantly changing stream of information. Moreover, it is ill-adapted to real-world use cases where the data distribution is expected to shift over the course of a model's lifetime. The first goal of this thesis is to characterize the different forms this shift can take in the context of natural language processing, and propose benchmarks and evaluation metrics to measure its effect on current deep learning architectures. We then proceed to take steps to mitigate the effect of distributional shift on NLP models. To this end, we develop methods based on parametric reformulations of the distributionally robust optimization framework. Empirically, we demonstrate that these approaches yield more robust models as demonstrated on a selection of realistic problems. In the third and final part of this thesis, we explore ways of efficiently adapting existing models to new domains or tasks. Our contribution to this topic takes inspiration from information geometry to derive a new gradient update rule which alleviate catastrophic forgetting issues during adaptation.
小貼士
登錄享
相關主題
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191